肝脏CT图像特征提取方法的研究及其在检索中的应用
|
摘要
随着多媒体技术在医学领域中的日益普及和发展,各种医学图像处理系统在临床、教学、科研以及医学图像存储、检索和通信系统都发挥着重要的作用。另外,为有效管理医院每天从CT.MR.X光片中产生的海量数据,PACS (Picture Archiving and Communication Systems)系统被越来越多的医院所采用。当前PACS系统的功能主要集中在医学影像数据的存档、传输及压缩方面,而对影像数据的进一步处理和分析方面还很少涉及。在PACS的基础上扩展如图像检索,辅助诊断等功能是PACS系统发展的必然。传统的医学图像检索方法是基于文本的检索,即根据图像的序列号、病人住院号、病人姓名、诊断报告等文本字段查询图像。它面临着需要对医学图像人工标注的困难,而人工标注由于其不可重复性、易受主观影响、工作量大等缺点,己经渐渐无法满足大规模医学图像数据库的检索需要,为此基于内容的图像检索(Content-Based Image Retrieval,CBIR)技术作为基于文本检索的扩展和补充,成为近年来该领域中的研究热点。
由于CBIR技术使用户仅通过选择视觉上感兴趣的图像就可以从海量医学图像数据库中提取所需的事实上相似、相近的图像,因此在教学和科研上极为需要通过视觉内容访问图像数据库的方法。因此,把视觉特征融合进医学检查是另一个在医学研究领域中令人感兴趣的热点。使用视觉特征的CBIR能够根据样图从图像数据库中不仅可以检索出具有相同或相似诊断的一组图像,还可以搜索出视觉上相似但诊断结论不同的图像集。教学上,CBIR技术可以帮助教师和学生浏览教学图像数据库,并能从视觉上对查询结果进行甄别。
然而,相比其它图像,医学图像分辨率低噪声高,通常只包含灰度信号,难以实现自动化处理,故CBIR在医学应用领域面临巨大挑战。在医学影像诊断中,临床诊断决策一般是根据图像局部特征(感兴趣区域,Region Of Interest,ROI)来完成的。而且,现有的医学图像处理技术还不够成熟,诊断效果往往不够理想。如何将图像处理中的关键技术与医学图像进行有机的结合,为医师提供科学、便捷、准确的医疗手段,并为其诊断提供辅助性的建议,成为人们的主要研究目标。
本文的研究工作是在国家重点基础研究(973)计划项目(No:2010CB732500)下展开的,主要围绕医学图像特征提取技术展开研究,探讨了肝部CT图像的特征提取技术,覆盖的内容主要包括全局特征的提取,感兴趣区域的特征自动提取及基于全局和局部区域特征的医学图像检索。
本文的主要研究成果总结如下：
1.提出了一种腹部图像基于非张量积小波的全局特征提取方法,可以用于医学肝脏带病灶CT图像的计算机辅助诊断(CAD)。鉴于张量积小波仅能获取少数方向信息的问题,构造了四通道不可分二维小波滤波器组,然后用于肝部CT图像的分解,分解后的小波高频子带系数可以用广义高斯模型来近似逼近。实验结果表明,本方法用于检索时结合局部纹理共生矩阵特征和灰度特征,可以提高病灶的检出率。
2.提出了一种肝脏CT图像的全局特征提取方法,目的是提高肝脏病灶的检出率。非张量积小波分解后的低频子带系数直方图可以看做分段的多峰高斯函数,用高斯函数近似逼近分段的系数,此方法利用了低频子带的近似特性,能更好的表达腹部图像的全局特征。通过在肝癌、肝血管瘤、肝囊肿这3种疾病的1688幅CT图像上的实验,验证了此特征提取方法的有效性,实验表明这个方法对提高病灶的检出率具有较好的鲁棒性。
3.在图像的感兴趣区域方面,针对肝脏CT肿瘤图像,如肝癌、肝血管瘤、肝囊肿图像增强后各扫描期的表现,即肝癌图像特征性边缘结节样强化及肝血管瘤强化区域逐步向病灶中心填充、肝囊肿病灶区域无任何变化,本章提出了2种局部特征提取算法,一是引入了梯度图像的作用,提取了梯度图像4个方向等间距的梯度值用于表征病灶区域的特征；二是根据上述3种肝部肿瘤强化后的特点,将分割后的病灶区域进行距离变换,然后利用分形维数自相似性的特点,提取每层数据,即一维曲线的盒维数作为局部特征。实验表明采用了这些具有针对性的特征提取算法后,肝脏肿瘤图像的检索结果有了很大的提高。为进一步提高检索系统的性能,本文对相似距离测度学习进行了研究。重点对Boostmetric算法进行详细介绍,并将LFDA、 LMNN、 BOOSTMETRIC三种学习算法应用于检索系统,实验结果表明Boostmetric效果是三者中最优的。
4.从放射科医师对肝部病变在对比增强三期扫描CT图像表现的诊断得到2方面的事实。其一,肝癌和肝血管瘤的病灶大部分有特定的特征性变化,而肝囊肿的病变没有发生任何改变。其二,由于三期扫描时病灶及其邻近正常肝实质之间的密度对比变化情况,也是放射科医师诊断的依据之一,可以考虑病灶周边的肝实质。因此,根据分析以及以上的研究,为切合放射学的诊断观点,形成了一种肝脏肿瘤病灶的局部特征提取算法,考虑了强化后病变区域及其邻近正常肝实质的特定表现。提议的特征提取算法源自不同病变以及周边正常肝实质在三期对比增强CT扫描图像上的影像学特点,这也是临床医生或放射科医师对肝脏三种疾病的诊断视角。算法主要包括2部分。第一是距离变换,把病变分为n个区域,且病变周围的肝实质信息考虑作为第n+1个区域,这也表现了空间结构分布。第二是基于各区域的BoW特征表示。后者是关键。一般来说,病灶分为3个区域最符合放射学医师对第二部分中所描述的强化三期扫描后疾病的影像分析。我们研究的目标是形成一个用于计算机辅助诊断的基于内容的图像检索系统,检索出与待查询病人图像的肿瘤类型相类似的影像图像,并执行这个系统的初步评估。
本文通过对肝部CT图像特征提取方法的探讨,研究了腹部图像全局特征与病灶区域局部特征提取的问题。并在此基础上,设计和初步实现一个基于内容的肝部CT图像检索原型系统,结果表明所提方法可以提高图像检索准确率
With the use of multimedia technology widely in the medical field, various medical images processing systems are playing an important role in the clinical, teaching, research, medical image storage, retrieval and communication systems. The function of extensions such as image retrieval, auxiliary diagnosis in PACS is the necessity of development of PACS. Traditional medical image retrieval is text-based query to retrieve medical images by matching exactly database fields or image annotations. Text-based queries face the difficulties of manual annotation for medical imags. Due to several disadvantages such as unrepeatability, being sensitive tosubjective influence, generating heavy workload of manual annotation, text-based methods have been unable to meet the nees of large-scale medical image database retrieval. Thus the techniques of content-based image retrieval (CBIR) for medical image database queries have been major topics instead of text-based searching techniques in recent years.
Because the CBIR technology that only makes users to choose the interested visual images research all the same and similar images in a large medical image database, so it have a much-needed to access image database through visual content in teaching and studying. As we see, the visual features in the medical examination are another interesting focus in the field of medical research. CBIR with visual features not only query the same or similar medical diagnosis, and also query the cases that are similar visually and different in diagnoses result. In teaching, CBIR technology can help teachers and students to browse the image database, and identify query results visually.
However, medical images hasve some disadvantages of the low resolution, high-noise, only gray signal, automation processing hard, which makes CBIR for medical images still face with great challenges. In the process of diagnosis for radiology images, clinic decisions are usually based on region of interest (ROI). Moreover, the existing medical image processing technologies are not mature enough to make satisfing diagnostic results. How to combine the key technologies in image processing with medical images become the main research objective for physicians to provide scientific, convenient and accurate medical instruments.
All the works in the thesis are carried out under Major State Basic Research Development Program (No:2010CB732500) and the key projects supported by national natural science foundation of China (No:30730036). They focus on the study of feature extraction technology of medical images, which include mainly the globle and local (ROI) feature extraction algorithms and image retrieval based on these algorithms.
The main contributions of this dissertation are summarized as follows:
1. A global feature extraction algorithm of hepatic CT images is proposed based on the non-tensor product wavelet, which can be used to the computer-aided diagnosis (CAD) in medical CT images with lesion. With the lackness of direction after separable wavelet transform, four-channal non-separable two dimension wavelet filter banks are constructed, and used to decomposition in hepatic images. The histogram of wavelet coefficients in each high-frequency subband are approximated using generalized Gaussian model (GGM). Experimental results show that this method can improve the retrieval results of lesions.
2. A global feature extraction algorithm of hepatic CT image is proposed, which aims to improve the detection rate of liver lesions. The proposed method uses the low frequency subband coefficient of wavelet decomposition based on the non-tensor product coefficient. These coefficients are modeled by Gaussian distribution piecewise. which utilizes the approximate characteristic of low frequency subband and could better express the global feature of hepatic image. The experiment on1688CT images confirms that retrieval perform based on this algorithm have robust result.
3. With respect to lesion of liver (ROI), two kinds of local feature extraction algorithm are proposes considering the behavior of liver cancer, liver hemangioma, liver cyst images after enhancement, that is, enhancement of liver cancer can described as "fast in and fast out", and enhancement region of hemangioma gradually filled to the lesion center, and cysts have no change in lesion. First we introduced the role of gradient image to extract feature points in four directions of the image gradient values. Second, distance transform is carried out on ROI, and the lesion is the fractal dimension features are then compute from the image data of every layer due to the characteristics of self-similarity of fractal dimension. Experiments show that retrieval result based on these two algorithmshave greatly improved. To further improve the retrieval performance, measure of similarity distance learning were studied in this paper. We mainly study Mahanalobis distance measure learning algorithms about k-nearest neighbor classification.The algorithms about Boostmetric is introdcuced detailed, and three learning algorithms LFDA, LMNN, BOOSTMETRIC are used in the liver tumor image.
4. Two facts were summarized taking account of the characteristics of triple-phase contrast-enhanced CT images. First, the lesions of HCC and hepatic hemangiomas mostly had specific characteristic changes, whereas no change occurred in that of cysts. Second, the surrounding liver parenchyma information of lesion was considered because of the discrepancy in density between the lesion and the adjacent normal parenchyma in triple phase scans. Thus, according to these analyses and the studies in the previous chapter, a feature extraction algorithm of lesions came to being considering the specific behavior of focal liver lesions and their surrounding liver parenchyma after enhancement. The proposed feature algorithm originated from distinct imaging characteristics of lesion images and the surrounding liver parenchyma in triple-phase CT images, which was also the diagnosis perspective of clinicians or radiologists for three types of tumor patients. The algorithm mainly included two processes. The first was distance transformation, which was used to partition the lesion into distinct regions and this represented the spatial structure distribution. The second was bag of visual words (BoW) representation based on regions. The latter was the key step. Generally, the lesion was divided into three regions in our experiments, which will fit best with imaging analysis of radiologists in triple phases for the diseases described above. The effect of the number selection on the performance of CBIR will be discussed in this article. The study's aims are to develop a feature extraction algorithm of hepatic lesions considering the radiologists' diagnosis views in triple-phase enhanced CT, and to contribute to a CBIR system to facilitate the retrieval of radiologic patients whose lesion images had similar-appearing with the query patient, and to implement a basis evaluation of this system.
Research around feature extraction of liver CT images is discussed in this dissertation, mainly in study of the globle and local (ROI) feature extraction algorithms and image retrieval based on these algorithms. Finally, a content-based medical imge retrieval system for liver CT images is designed, and the results indicate that these methodes can improve retrieval accuracy.
由于CBIR技术使用户仅通过选择视觉上感兴趣的图像就可以从海量医学图像数据库中提取所需的事实上相似、相近的图像,因此在教学和科研上极为需要通过视觉内容访问图像数据库的方法。因此,把视觉特征融合进医学检查是另一个在医学研究领域中令人感兴趣的热点。使用视觉特征的CBIR能够根据样图从图像数据库中不仅可以检索出具有相同或相似诊断的一组图像,还可以搜索出视觉上相似但诊断结论不同的图像集。教学上,CBIR技术可以帮助教师和学生浏览教学图像数据库,并能从视觉上对查询结果进行甄别。
然而,相比其它图像,医学图像分辨率低噪声高,通常只包含灰度信号,难以实现自动化处理,故CBIR在医学应用领域面临巨大挑战。在医学影像诊断中,临床诊断决策一般是根据图像局部特征(感兴趣区域,Region Of Interest,ROI)来完成的。而且,现有的医学图像处理技术还不够成熟,诊断效果往往不够理想。如何将图像处理中的关键技术与医学图像进行有机的结合,为医师提供科学、便捷、准确的医疗手段,并为其诊断提供辅助性的建议,成为人们的主要研究目标。
本文的研究工作是在国家重点基础研究(973)计划项目(No:2010CB732500)下展开的,主要围绕医学图像特征提取技术展开研究,探讨了肝部CT图像的特征提取技术,覆盖的内容主要包括全局特征的提取,感兴趣区域的特征自动提取及基于全局和局部区域特征的医学图像检索。
本文的主要研究成果总结如下：
1.提出了一种腹部图像基于非张量积小波的全局特征提取方法,可以用于医学肝脏带病灶CT图像的计算机辅助诊断(CAD)。鉴于张量积小波仅能获取少数方向信息的问题,构造了四通道不可分二维小波滤波器组,然后用于肝部CT图像的分解,分解后的小波高频子带系数可以用广义高斯模型来近似逼近。实验结果表明,本方法用于检索时结合局部纹理共生矩阵特征和灰度特征,可以提高病灶的检出率。
2.提出了一种肝脏CT图像的全局特征提取方法,目的是提高肝脏病灶的检出率。非张量积小波分解后的低频子带系数直方图可以看做分段的多峰高斯函数,用高斯函数近似逼近分段的系数,此方法利用了低频子带的近似特性,能更好的表达腹部图像的全局特征。通过在肝癌、肝血管瘤、肝囊肿这3种疾病的1688幅CT图像上的实验,验证了此特征提取方法的有效性,实验表明这个方法对提高病灶的检出率具有较好的鲁棒性。
3.在图像的感兴趣区域方面,针对肝脏CT肿瘤图像,如肝癌、肝血管瘤、肝囊肿图像增强后各扫描期的表现,即肝癌图像特征性边缘结节样强化及肝血管瘤强化区域逐步向病灶中心填充、肝囊肿病灶区域无任何变化,本章提出了2种局部特征提取算法,一是引入了梯度图像的作用,提取了梯度图像4个方向等间距的梯度值用于表征病灶区域的特征；二是根据上述3种肝部肿瘤强化后的特点,将分割后的病灶区域进行距离变换,然后利用分形维数自相似性的特点,提取每层数据,即一维曲线的盒维数作为局部特征。实验表明采用了这些具有针对性的特征提取算法后,肝脏肿瘤图像的检索结果有了很大的提高。为进一步提高检索系统的性能,本文对相似距离测度学习进行了研究。重点对Boostmetric算法进行详细介绍,并将LFDA、 LMNN、 BOOSTMETRIC三种学习算法应用于检索系统,实验结果表明Boostmetric效果是三者中最优的。
4.从放射科医师对肝部病变在对比增强三期扫描CT图像表现的诊断得到2方面的事实。其一,肝癌和肝血管瘤的病灶大部分有特定的特征性变化,而肝囊肿的病变没有发生任何改变。其二,由于三期扫描时病灶及其邻近正常肝实质之间的密度对比变化情况,也是放射科医师诊断的依据之一,可以考虑病灶周边的肝实质。因此,根据分析以及以上的研究,为切合放射学的诊断观点,形成了一种肝脏肿瘤病灶的局部特征提取算法,考虑了强化后病变区域及其邻近正常肝实质的特定表现。提议的特征提取算法源自不同病变以及周边正常肝实质在三期对比增强CT扫描图像上的影像学特点,这也是临床医生或放射科医师对肝脏三种疾病的诊断视角。算法主要包括2部分。第一是距离变换,把病变分为n个区域,且病变周围的肝实质信息考虑作为第n+1个区域,这也表现了空间结构分布。第二是基于各区域的BoW特征表示。后者是关键。一般来说,病灶分为3个区域最符合放射学医师对第二部分中所描述的强化三期扫描后疾病的影像分析。我们研究的目标是形成一个用于计算机辅助诊断的基于内容的图像检索系统,检索出与待查询病人图像的肿瘤类型相类似的影像图像,并执行这个系统的初步评估。
本文通过对肝部CT图像特征提取方法的探讨,研究了腹部图像全局特征与病灶区域局部特征提取的问题。并在此基础上,设计和初步实现一个基于内容的肝部CT图像检索原型系统,结果表明所提方法可以提高图像检索准确率
With the use of multimedia technology widely in the medical field, various medical images processing systems are playing an important role in the clinical, teaching, research, medical image storage, retrieval and communication systems. The function of extensions such as image retrieval, auxiliary diagnosis in PACS is the necessity of development of PACS. Traditional medical image retrieval is text-based query to retrieve medical images by matching exactly database fields or image annotations. Text-based queries face the difficulties of manual annotation for medical imags. Due to several disadvantages such as unrepeatability, being sensitive tosubjective influence, generating heavy workload of manual annotation, text-based methods have been unable to meet the nees of large-scale medical image database retrieval. Thus the techniques of content-based image retrieval (CBIR) for medical image database queries have been major topics instead of text-based searching techniques in recent years.
Because the CBIR technology that only makes users to choose the interested visual images research all the same and similar images in a large medical image database, so it have a much-needed to access image database through visual content in teaching and studying. As we see, the visual features in the medical examination are another interesting focus in the field of medical research. CBIR with visual features not only query the same or similar medical diagnosis, and also query the cases that are similar visually and different in diagnoses result. In teaching, CBIR technology can help teachers and students to browse the image database, and identify query results visually.
However, medical images hasve some disadvantages of the low resolution, high-noise, only gray signal, automation processing hard, which makes CBIR for medical images still face with great challenges. In the process of diagnosis for radiology images, clinic decisions are usually based on region of interest (ROI). Moreover, the existing medical image processing technologies are not mature enough to make satisfing diagnostic results. How to combine the key technologies in image processing with medical images become the main research objective for physicians to provide scientific, convenient and accurate medical instruments.
All the works in the thesis are carried out under Major State Basic Research Development Program (No:2010CB732500) and the key projects supported by national natural science foundation of China (No:30730036). They focus on the study of feature extraction technology of medical images, which include mainly the globle and local (ROI) feature extraction algorithms and image retrieval based on these algorithms.
The main contributions of this dissertation are summarized as follows:
1. A global feature extraction algorithm of hepatic CT images is proposed based on the non-tensor product wavelet, which can be used to the computer-aided diagnosis (CAD) in medical CT images with lesion. With the lackness of direction after separable wavelet transform, four-channal non-separable two dimension wavelet filter banks are constructed, and used to decomposition in hepatic images. The histogram of wavelet coefficients in each high-frequency subband are approximated using generalized Gaussian model (GGM). Experimental results show that this method can improve the retrieval results of lesions.
2. A global feature extraction algorithm of hepatic CT image is proposed, which aims to improve the detection rate of liver lesions. The proposed method uses the low frequency subband coefficient of wavelet decomposition based on the non-tensor product coefficient. These coefficients are modeled by Gaussian distribution piecewise. which utilizes the approximate characteristic of low frequency subband and could better express the global feature of hepatic image. The experiment on1688CT images confirms that retrieval perform based on this algorithm have robust result.
3. With respect to lesion of liver (ROI), two kinds of local feature extraction algorithm are proposes considering the behavior of liver cancer, liver hemangioma, liver cyst images after enhancement, that is, enhancement of liver cancer can described as "fast in and fast out", and enhancement region of hemangioma gradually filled to the lesion center, and cysts have no change in lesion. First we introduced the role of gradient image to extract feature points in four directions of the image gradient values. Second, distance transform is carried out on ROI, and the lesion is the fractal dimension features are then compute from the image data of every layer due to the characteristics of self-similarity of fractal dimension. Experiments show that retrieval result based on these two algorithmshave greatly improved. To further improve the retrieval performance, measure of similarity distance learning were studied in this paper. We mainly study Mahanalobis distance measure learning algorithms about k-nearest neighbor classification.The algorithms about Boostmetric is introdcuced detailed, and three learning algorithms LFDA, LMNN, BOOSTMETRIC are used in the liver tumor image.
4. Two facts were summarized taking account of the characteristics of triple-phase contrast-enhanced CT images. First, the lesions of HCC and hepatic hemangiomas mostly had specific characteristic changes, whereas no change occurred in that of cysts. Second, the surrounding liver parenchyma information of lesion was considered because of the discrepancy in density between the lesion and the adjacent normal parenchyma in triple phase scans. Thus, according to these analyses and the studies in the previous chapter, a feature extraction algorithm of lesions came to being considering the specific behavior of focal liver lesions and their surrounding liver parenchyma after enhancement. The proposed feature algorithm originated from distinct imaging characteristics of lesion images and the surrounding liver parenchyma in triple-phase CT images, which was also the diagnosis perspective of clinicians or radiologists for three types of tumor patients. The algorithm mainly included two processes. The first was distance transformation, which was used to partition the lesion into distinct regions and this represented the spatial structure distribution. The second was bag of visual words (BoW) representation based on regions. The latter was the key step. Generally, the lesion was divided into three regions in our experiments, which will fit best with imaging analysis of radiologists in triple phases for the diseases described above. The effect of the number selection on the performance of CBIR will be discussed in this article. The study's aims are to develop a feature extraction algorithm of hepatic lesions considering the radiologists' diagnosis views in triple-phase enhanced CT, and to contribute to a CBIR system to facilitate the retrieval of radiologic patients whose lesion images had similar-appearing with the query patient, and to implement a basis evaluation of this system.
Research around feature extraction of liver CT images is discussed in this dissertation, mainly in study of the globle and local (ROI) feature extraction algorithms and image retrieval based on these algorithms. Finally, a content-based medical imge retrieval system for liver CT images is designed, and the results indicate that these methodes can improve retrieval accuracy.
引文
[1]Miiller H, Michoux N, Bandon D, et al. A review of content-based image retrieval systems in medical applications-clinical benefits and future directions [J]. International Journal of Medical Informatics,2004,73(1):1-23.
[2]LeBozec C, Jaulent M-C, Zapletal E, et al. Unified modeling language and design of a case-based retrieval system in medical imaging [C]. in:Proceedings of the Annual Symposium of the American Society for Medical Informatics (AMIA), Nashville, TN, USA,1998.
[3]Bui AAT, Taira RK, Dionision JDN, et al. Evidence-based radiology [J]. Academic Radiology,2002,9(6):662-669.
[4]Giild MO, Kohnen M, Keysers D, et al. Quality of DICOM header information for image categorization [J]. In:International Symposium on Medical Imaging, Vol. 4685 of SPIE Proceedings, San Diego, CA, USA,2002:280-287.
[5]Smeulders AW, Worring M, Santini S, et al. Content-based image retrieval at the end of the early years [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2000,22(12):1349-1380.
[6]Datta R, Joshi D, Li J, Wang JZ. Image Retrieval:Ideas, Influences, and Trends of the New Age [C]. ACM Computing Surveys,2008,40(65).
[7]Datta R, Joshi D, Li J, Wang JZ. Content-Based Image Retrieval-Approaches and Trends of the New Age [C]. Proceedings of the 7th International Workshop on Multimedia Information Retrieval, in conjunction with ACM International Conference on Multimedia, Singapore, ACM, November 2005,253-262.
[8]Yang ZJ, Kuo C-CJ. Survey on Image Content Analysis, Indexing, and Retrieval Techniques and Status Report of MPEG-7 [J]. Tamkang Journal of Science and Engineering,1999,2(3):101-118.
[9]Swain M, Ballard D. Color indexing [J]. Int'l Journal of Computer Vision,1991, 7(1):11-32.
[10]Stricker M, Orengo M. Similarity of color images [J]. In SPIE Storage and Retrieval of Image and Video Databases,1995,2420:381-392.
[11]Smith JR, Li C-S. Image classification and querying using composite region templates [J]. Computer Vision and Image Understanding, Special Issue on Content-Based Access of Image and Video Libraries,1999,75(1/2):165-174.
[12]Pratt WK. Digital Image Processing [M],2nd edition. John Wiley & Sons Publication,1991.
[13]Aksoy S, Haralick RM. Textural features for image database retrieval [C]. In: IEEE CVPR'98 Workshop on Content-Based Access of Image and Video Libraries,1998: 45.
[14]Tamura H, Mori S, Yamawaki T. Texture features corresponding to visual perception [J]. IEEE Trans, on Sys. Man and Cyb,1978,8(6):460-473.
[15]Manjunath B, Wu P, Newsam S, et al. A texture descriptor for browsing and similarity retrieval [J]. Journal of Signal Processing:Image Communication,2000, 16(1-2):33-43.
[16]Ahmadian, Faramarzi E, Sayadian. Image Indexing and Retrieval Using Gabor Wavelet and Legendre Moments [C]. Proceedings of the 25th Annual International Conference of the IEEE EMBS Cancun, Mexico September,2003:17-21.
[17]Chang T, Kuok CCJ. Texture analysis and classification with tree-structured wavelet transform [J]. IEEE Trans,on Image Processing,1993,2(4):429-440.
[18]Simoncelli EP, Portilla J. Texture characterization via joint statistics of wavelet coefficient magnitudes [C]. In:IEEE International Conference on Image Processing,1998:62-66.
[19]Nevel AV. Texture synthesis via matching first and second order statistics of a wavelet frame decomposition [C]. In:IEEE International Conference on Image Processing,1998:72-76.
[20]Hu MK. Visual pattern recognition by moment invariants [J]. IEEE Transaction on Information Theory,1962,8(1):179-187.
[21]Shen L, Rangayyan RM, Desautels JEL. Detection and Classification of Mammographic Calcification [J]. International Journal of Pattern Recognition and Artificial Intelligence,1993,7(6):1403-1416.
[22]Persoon E, Fu KS. Shape discrimination using Fourier descriptors [J], IEEE Trans. System Man Cybernet,1977, SMC-7 (3):170-179.
[23]Zhang DS, Lu G. A comparison of shape retrieval using Fourier descriptors and short-time Fourier descriptors [C]. In:Proceedings of the Second IEEE Conference on Multimedia (PCM01), Beijing, China, October 24-26,2001:855-860.
[24]Jain AK, Vailaya A. Image retrieval using color and shape [J]. Pattern Recognition, 1996,29(8):1233-1244.
[25]Brandt S, Laaksonen J, Oja E. Statistical shape features in content-based image retrieval [C]. In: Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain,2000,2:1062-1065.
[26]Tieng QM, Boles WW. Recognition of 2D object contours using the wavelet transform zero-crossing representation [J]. IEEE Trans. Pattern Anal. Mach. Intell, 1997,19(8):910-916.
[27]Chuang GC-H, Kuo C-CJ. Wavelet descriptor of planar curves:theory and applications [J]. IEEE Trans.on Image Processing,1996,5(1):56-70.
[28]CHAN TF, VESE L. Active contour without edges [J]. IEEE Transon Image Processing,2001,10(2):266-277.
[29]Lim YW, Lee SU. On the Color Image Segmentation Algorithm Based on the Thresholding and the Fuzzy c means Techniques [J]. Pattern Recognition,1990, 23(9):935-51.
[30]Dempster A, Laird N, Rubin D. Maximun Likehood from incomplete data via the EM algorithm [J]. J Royal Stat Soc,1977,39(1):1-38.
[31]章毓晋.图像工程(中)图像分析[M].北京：清华大学出版社,2005：102-103.
[32]Lucchese L, Mitra SK. Color image segmentation: a state-of-the-art survey [C]. Proceedings of the Indian National Science Academy (INSA-A), New Delhi,2001, 67(2):207-221.
[33]Zhang YY, Michael B, Stephen S. Segmentation of brain images through a hidden Markov random field model and the expectation maximization algorithm [J]. IEEE TMI,2001,20(1):45-57.
[34]Niblack W, Barber R, Equitz W, et al. QBIC project:querying images by content, using color, texture, and shape [J]. Proc. SPIE,1993,1908:173-187.
[35]Sebe N, Lew M, Huijsmans DP. Toward improved ranking metrics [J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2000,22(10):l 132-1143.
[36]Rui Y, Huang TS, Ortega M, et al. Relevance feedback:A power tool in interactive content-based image retrieval [J]. IEEE Transactions on Circuit s and Systems for Video Technology,1998,8(5):644-655.
[37]Selaroff S, Taycher L, Cascia ML. Imagerover: A content-based image browser for the World Wide Web [C]. In: proceedings of IEEE Work shop on Content-Based Access of Image and Video Libraries, San Juan, Puerto Rico, June 1997:2-9.
[38]Zhou XS, Huang TS. Relevance Feedback in Image Retrieval:A Comprehensive Review [J]. Multimedia Systems,2003,8:536-544.
[39]吴洪,卢汉清,马颂德.基于内容图像检索中相关反馈技术的回顾[J].计算机学报,2005,28(12)：1969-1979.
[40]张晨光.基于内容的肝脏CT图像检索的研究[D],上海交通大学,2005,PP.1.
[41]Mougiakakou SG, Valavanis IK, Nikita A, et al. Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifier[J]. Artificial Intelligence in Medicine,2007,41(1):25-37,
[42]Zhang XJ, Fujita HS, Qin TF, et al. CAD on liver using CT and MRI, Medical Imaging and Informatics [J]. Lecture Notes in Computer Science,2008,4987: 367-376.
[43]Napel SA, Beaulieu CF, Rodriguez C, et al. Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity: Method and Preliminary Results, Radiology [J].2010,256(l):243-252.
[1]Shyu C, Kak A, Kosaka A, et al. ASSERT: A physician-in-the-loop content based image retrieval system for HRCT image databases [J]. Computer Vision and Image Understanding,1999,75(1):111-132.
[2]Mattie ME, Staib L, Stratmann E, et al. PathMaster:Content-based cell image retrieval using automated feature extraction [J]. Journal of the American Medical Informatics Association,2000,7:404-415.
[3]Wang JZ. Pathfinder: multiresolution region-based searching of pathology images using IRM [J]. Journal of the American Medical Informatics Association,2000,7: 883-887.
[4]Miiller H, Rosset A, Vallee, J-P et al. Comparing features sets for content-based image retrieval in a medical-case database [C]. In:SPIE Conference on Medical Imaging, San Diego, CA, USA,2004:99-109.
[5]Lehmann TM, Guld MO, Keysers D, et al. Similarity of medical images computed from global feature vectors for content-based retrieval [J]. Lecture Notes in Artificial Intelligence,2004,3214:989-995.
[6]Lehmann, TM, Giild MO, Thies C, et al. IRMA—Content-based image retrieval in medical applications [J]. Methods Inf Med,2004,43:354-361.
[7]Antani S, Lee DJ, Long LR, et al. Evaluation of shape similarity measurement methods for spine X-ray images [J]. Journal of Visual Communication and Image Representation,2004,15(3):285-302.
[8]Antani S, Xu X, Long LR, et al. Partial shape matching for CBIR of spine X-ray images [C]. In:Proceedings of IS&T/SPIE Electronic Imaging-Storage and Retrieval Methods and Applications for Multimedia,2004:1-8.
[9]Veropoulos K, Campbell C, Learnmonth G. Image processing and neural computing used in the diagnosis of tuberculosis [C]. In:Proceedings of the Colloquium on Intelligent Methods in Healthcare and Medical Applications (IMHMA), York, England,1998:8/1-8/4.
[10]Brodley C, Kak A, Shyu C, et al. Content-based retrieval from medical image databases: A synergy of human interaction, machine learning and computer vision [C]. In:Proceedings of the 10th National Conference on Artificial Intelligence, Orlando, FL, USA,1999:760-767.
[11]Bueno JM, Chino F, Traina AJM, et al. How to add content-based image retrieval capacity into a PACS [C]. In: Proceedings of the IEEE Symposium on Computer-Based Medical Systems (CBMS 2002), Maribor, Slovenia,2002: 321-326.
[12]Xian GM.An identification method of malignant and benign liver tumors from ultrasonography based on GLCM texture features and fuzzy SVM [J]. Expert Systems with Applications,2010,37(10):6737-6741.
[13]Beretti S, Del Bimbo A, Pala P. Content-based retrieval of 3D cellular structures [C]. In:Proceedings of the second International Conference on Multimedia and Exposition (ICME'2001), IEEE Computer Society, IEEE Computer Society, Tokyo, Japan,2001:1096-1099.
[14]Sastry CS, Ravindranath M, Pujari AK, et al. A modified Gabor function for content based image retrieval [J]. Pattern Recognition Letters,2007,28(2): 293-300.
[15]Tang LH, Hanka R, Ip HHS, et al. Extraction of semantic features of histological images for content-based retrieval of images [C]. In:Proceedings of the IEEE Symposium on Computer-Based Medical Systems (CBMS2000), Houston, TX, USA,2000.
[16]Han J, Ma KK. Rotation-invariant and scale-invariant Gabor features for texture image retrieval [J]. Image and Vision Computing,2007,25(9):1474-1481.
[17]Miiller H, Rosset A, Valleee JP, et al. Integrating content-based visual access methods into a medical case database [C]. In: Proceedings of the Medical Informatics Europe Conference (MIE 2003), St. Malo, France,2003:480-485.
[18]Kwak DM, Kim BS, Yoon OK, et al. Content-based ultrasound image retrieval using a coarse to fine approach [J]. Annals of the New York Academy of Sciences, 2002,980:212-224.
[19]Hu MK. Visual pattern recognition by moment invariants [J]. IEEE Transaction on Information Theory,1962,8(1):179-187
[20]Haralick R.M., Shanmugam K., Texture feature for image classification [J]. IEEE Trans. On System, Man and Cybernetics,1973, SMC-3(6):610-621.
[21]Reis MS, Bauer A. Using Wavelet Texture Analysis in Image-Based Classification and Statistical Process Control of Paper Surface Quality [J]. Computer Aided Chemical Engineering,2009,29:1209-1214.
[22]Osowski S, Nghia DD. Fourier and wavelet descriptors for shape recognition using neural networks—a comparative study [J]. Pattern Recognition,2002,35(9): 1949-1957.
[23]Persoon E, Fu KS. Shape discrimination using Fourier descriptors [J]. IEEE Trans. on PAMI,1986,8:388～397.
[24]Zhang DS, Lu GJ. Study and evaluation of different Fourier methods for image retrieval [J]. Image Vision Computing,2005,23:33-49.
[25]Shen L, Rangayyan RM, Desautels JEL. Detection and classification of mammographic calcification [J]. International Journal of Pattern Recognition and Artificial Intelligence,1993,7(6):1403-1416.
[26]安志勇.基于内容的图像检索关键技术研究[D].博士论文,2008：pp.24.
[27]Santini S, Jain R. Similanrity math [J]. IEEE Trans. On PAMI,1996,18(9): 946-958.
[28]Swain MJ, Ballar DH, Color indexing [C]. Intl.J. on Computer Vision,1991,7(1): 11-32.
[29]庄越挺,潘云鹤,吴飞,网上多媒体信息分析与检索[M].清华大学出版社,北京,2002,pp.42-43.
[30]Hafner J, Sawhney H, Equitz W, et al. Efficient color histogram indexing for quadratic form distance function [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,1995,17(7):729-736.
[31]Weinberger KQ, Blitzer J, Saul LK. Distance metric learning for large margin nearest neighbor classification [C]. In Proc. Adv. Neural Inf. Process. Syst.,2005, 1473-1480.
[32]Zhang DS. Image Retrieval Based on Shape [C], PhD Thesis, Monash University, March,2002.
[33]盛骤,谢式千,潘承毅,概率论与数理统计[M ].高等教育出版社,1989.
[34]Kullback S. Information theory and statistics [M]. Dover, New York, NY,1968.
[35]Puzicha J, Hufinann T, Buhmann J. Non-parametric similarity measure for unsupervised texture segmentation and image retrieval [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 1997, 267-272.
[36]Zhang DS, Lu GJ. Evaluation of similarity measurement for image retrieval [C]. IEEE Int. Conf. Neural Networks & Signal Processing, Nan Jing, China,2003, 928-931.
[37]Lee HY, Lee HK, Ha YH. Spatial color descriptor for image retrieval and video segmentation [J]. IEEE Trans. On Multimedia,2003,5(3):358-367.
[38]Arnold WM, Marcel W, Simone S, et al. Content-based image retrieval at the end of the early years [J]. IEEE Trans. On PAMI.2000,22(12):1349-1379.
[39]Vogel J, Schiele B. Performance evaluation and optimization for content-based image retrieval [J]. Pattern Recognition,2006,39(5):897-909.
[1]Rui Y, Huang TS, Chang SF. Image retrieval:Current techniques, promising directions, and open issues [OL].http://research. microsoft, com/ users/ yongrui/ html/ publication. Html,1999
[2]Manjunath BS, Ohm JR., et al. Color and texture descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11(6):703～715.
[3]Borber M. MPEG-7 visual shape descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11 (6):716～719.
[4]Smith JR, Chang SF. Automated binary texture feature sets for image retrieval [A]. 1996, proc.ICASSP-96.
[5]Wouwer GV, Scheunders P, Dyck DV. Statistical texture characterization from discrete wavelet representations [J]. IEEE Trans. Image Proc.,1999,8(4):592-598.
[6]Do MN, Vetterli M. Rotation invariatnt texture characterization and retrieval using steerable wavelet-domain hidden markov-models [J]. IEEE Trans. On Multimedia. 2002,4:517-527 Dec.
[7]Do MN, Vetterli MN. Wavelet-based texture retrieval using generalized Gaussian density and kullback-leibler distance [J]. IEEE Transactions on Image Processing, 2002,11:146-158.
[8]Miiller H, Michoux N, Bandon D, et al. A review of content-based image retrieval systems in medical applications-clinical benefits and future directions [J]. International Journal of Medical Informatics,2004,73(1):1-23.
[9]Rahman MM, Bhattacharya P, DesaiA BC. Framework for medical image retrieval using machine learning and statistical similarity matching techniques with relevance feedback [J]. IEEE Transactions on Information Technology in Biomedicine,2007,11(1):58-69.
[10]Ohm JR, Bunjamin FB, Liebsch W, et al. A set of visual feature descriptors and their combination in a low-level description scheme [J]. Signal Process. Image Commun.2000,16:157-179.
[11]Tieng QM, Boles WW. Recognition of 2D object contours using the wavelet transform zero-crossing representation [J]. IEEE Trans. Pattern Anal. Mach. Intell, 1997.19 (8):910-916.
[12]Malik A, Zremic T. Classification of medical images using energy information obtained from wavelet transform for medical image retrieval [C]. In: Proceedings of 7th International Workshop on Enterprise networking and Computing in Healthcare Industry,2005:124-129.
[13]He WJ, Lai MJ. Construction of bivariate compactly supported biorthogonal box spline wavelet with arbitrarily high regularities [J]. Applied Comput. Harmonic Analysis,1999,6:53-74
[14]Z. He, X. You, Y. Y Tang, et al. Texture image retrieval using novel non-separable filter banks based on centrally symmetric matrices[J], in: Proceedings of 18th International Conference on Pattern Recognition, August 2006, pp.161-164.
[15]He ZY, You XG, Tang YY. Texture image retrieval based on non-tensor product wavelet filter banks [J]. Signal Processing,2009,89(8):1501-1510.
[16]Zhang DS, Lu G.J. Evaluation of similarity measurement for image retrieval [J], IEEE Int. Conf. Neural Networks & Signal Processing, Nan Jing, China,2003, 928-931.
[1]Smith JR, Chang SF. Automated binary texture feature sets for image retrieval [A]. 1996,proc.ICASSP-96.
[2]Wouwer GV, Scheunders P, Dyck DV. Statistical texture characterization from discrete wavelet representations [J]. IEEE Transactions on Image Processing,1999, 8(4):592-598.
[3]Do MN, Vetterli M. Rotation invariatnt texture characterization and retrieval using steerable wavelet-domain hidden markov-models [J]. IEEE Transactions On Multimedia.2002,4:517-527.
[4]Do MN, Vetterli M. Wavelet-based texture retrieval using generalized Gaussian density and kullback-leibler distance [J]. IEEE Transactions on Image Processing, 2002,11:146-158.
[5]He ZY, You XG, Tang YY. Texture image retrieval based on non-tensor product wavelet filter banks [J]. Signal Processing,2009,89(8):1501-1510.
[6]Yu M, Lu ZT, Feng QJ, et al. Liver CT image retrieval based on non-tensor product wavelet [C].2010 IEEE International Conference on Medical Image Analysis and Clinical Applications (MIACA),67-70.
[7]Furht B, Smoliar SW, Zhang H J. Video and image processing in multimedia systems [M]. Kluwer Academic Publishers,1995:226-70.
[8]Zhang DS, Lu GJ. Evaluation of similarity measurement for image retrieval [J]. Proceedings of the International Conference on Neural Networks and Signal Processing,2003,2:928-31.
[9]Nastar C, Mitschke M, Meihac C. Efficient Query Refinement for Image Retrieval [J]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Santa Barbara, California, IEEE Computer Society,1998, 547-52.
[1]Shyu C, Kak A, Kosaka A, et al. ASSERT: A physician-in-the-loop content based image retrieval system for HRCT image databases [J]. Computer Vision and Image Understanding,1999,75(1):111-132.
[2]Rosenfeld, Pfaltz J. L. Sequential operations in digital picture processing [J]. Journal of ACM,1996,13(4):471-494.
[3]Falconer K.J.Fractal Geometry:Mathematical Foundation and Application [M]. New York:Wiley,1990.
[4]冯晨.基于分形维数的中国海常见浮游植物细胞图像特征提取[D].博士论文,2006.pp：13.
[5]Xia Y, Feng DG, Zhao RC, et al. Multifractal signature estimation for textured image segmentation [J]. Pattern Recognition Letter,2010,31(2):163-169.
[6]Uemura K, Toyama H, Baba S, et al. Generation of fractal dimension images and its application to automatic edge detection in brain MRI [J]. Computerized Medical Imaging and Graphics,2000,24(2):73-85.
[7]Varma V, Garg R. Locally invariant fractal features for statistical texture classification [C]. Proc. IEEE International Conference on Computer Vision,2007: 1-8.
[8]Park PK, Lee CH, Lee S. Determination of cake porosity using image analysis in a coagulation-microfiltration system [J]. Journal of Membrane Science,2007,29(3): 66-72.
[9]Imai K, Ikeda M, Enchi Y, et al. Fractal-Feature Distance Analysis of Radiographic Image [J]. Academic Radiology,2007,14(2):137-143.
[10]Yu L, Zhang D, Wang KQ, et al. Coarse iris classification using box-counting to estimate fractal dimensions [J]. Pattern Recognition,2005,38(11):1791-1798.
[11]Myint SW, Lam N. A study of lacunarity-based texture analysis approaches to improve urban image classification. Computers [J]. Environment and Urban Systems,2005,29(5):501-523.
[12]Pentland AP. Fractal based description of natural scenes [J]. IEEE Trans. Pattern Anal. Mach, Intell,1984,6:661-674.
[13]Hastie T, Tibshirani R. Discriminant adaptive nearest neighbor classification [J]. IEEE Trans.Pattern Anal. Mach. Intell.,1996,18(6):607-616.
[14]Yu J, Amores J, Sebe N, et al. Distance learning for similarity estimation [J]. IEEE Trans. Pattern Anal. Mach. Intell.,2008,30(3):451-462.
[15]Jian B, Vemuri BC. Metric learning using Iwasawa decomposition [C]. In Proceeding IEEE International Conference of Computer Vision,2007,1-6.
[16]Xing EP, Ng AY, Jordan MI, et al. Distance metric learning, with application to clustering with side-information [C]. In Proc. Adv. Neural Inf. Process. Syst. MIT Press,2002.
[17]Bar-Hillel A, HertzT, Shental N, et al. Learning a Mahalanobis metric from equivalence constraints [J]. Journal of Machine Learning Research,2005, 6:937-965.
[18]Fukunage K. Introduction to Statistical Pattern Recognition [M].2nd edition. Boston:Academic Press,1990.
[19]Boyd S, Vandenberghe L. Convex optimization [M]. New York:Cambridge University Press,2006.
[20]Turk M, Pentland A. Eigenfaces for Recognition [J]. Journal of Cognitive Neuroscience,199,3(1):71-86.
[21]Belhumeur PN, Hespanda J, Kriegeman D. Eigenfaces vs. Fisherfaces:Recognition Using Class Specific Linear Projection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[22]Globerson A, Roweis S. Metric learning by collapsing classes [M]. Advances in neural information processing systems 18. Cambridge, MA:MIT Press,2006.
[23]Masashi S. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis [J]. J. Mach. Learn. Res.,2007,8:1027-1061.
[24]Weinberger KQ, Saul LK. Distance metric learning for large margin nearest neighbor classification [J]. The Journal of Machine learning Research,2009,10: 207-244.
[25]Shen CH, Welsh A, Wang L. PSDBoost:Matrix-generation linear programming for positive semidefinite matrices learning [C]. Proc. Adv. Neural Inf. Process. Syst., 2008,1473-1480.
[26]Shen CH, Kim J, Wang L, et al. Positive Semidefinite Metric Learning using Boosting-like Algorithms [J]. Journal of Learning Research,2012,1007-1036.
[27]Schapire RE. Theoretical views of boosting and applications [C]. In Proc. Int. Conf. Algorithmic Learn. Theory,1999,13-25.
[28]Goldberger J, Roweis S, Hinton G. Neighbourhood component analysis [C]. In Proc. Adv. Neural Inf. Process. Syst. MIT Press,2004.
[1]Armato SG, McNitt-Gray MF, Reeves AP, et al. The Lung Image Database Consortium (LIDC):an evaluation of radiologist variability in the identification of lung nodules on CT scans [J]. Academic Radiology,2007,14 (11):1409-1421.
[2]Barlow WE, Chi C, Carney PA, et al. Accuracy of screening mammography interpretation by characteristics of radiologists [J]. Journal of the National Cancer Institute,2004,96 (24):1840-1850.
[3]Robinson PJ. Radiology's Achilles'heel:error and variation in the interpretation of the Rontgen image [J]. The British Journal of Radiology,1997,70 (839):1085 1098.
[4]Yuan K, Tian Z, Zou J, et al. Brain CT image database building for computer-aided diagnosis using content-based image retrieval [J]. Information Processing and Management,2011,47(2):176-185.
[5]Huang YL, Chen JH, Shen WC. Computer-Aided Diagnosis of Liver Tumors in Non-enhanced CT Images [J]. Journal of Medical Physics,2004,9:141-150.
[6]Chen EL, Chung PC, Chen CL, et al. An automatic diagnostic system for CT liver image classification [J]. IEEE Transactions Biomedical Engineering,1998,45(6): 783-794.
[7]Greenspan H, Pinhas AT. Medical image categorization and retrieval for PACS using the GMM-KL framework [J]. IEEE Transactions on Information Technology in Biomedicine,2007,11(2):190-202.
[8]Iakovidis DK, Pelekis N, Kotsifakos EE, et al. A pattern similarity scheme for medical image retrieval [J]. IEEE Transactions on Information Technology in Biomedicine,2009,13(4):442-450.
[9]Rahman MM, Desai BC, Bhattacharya P. Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion [J]. Computerized Medical Imaging and Graphics,2008,32(2):95-108.
[10]Huang Y, Kuo S, Chang C, et al. Image retrieval with principal component analysis for breast cancer diagnosis on various ultrasonic systems [J]. Ultrasound Obstetrics & Gynecology,2005,26(5):558-566.
[11]Jennifer GD, Carla EB, Avi K, et al. Unsupervised feature selection applied to content-based retrieval of lung images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(3):373-378.
[12]Oliveira JD, Machado A, Chavez G, et al. MammoSys:A content-based image retrieval system using breast density patterns [J]. Computer Methods and Programs in Biomedicine,2010,99(3):289-297.
[13]Naqa IE, Yang Y, Galatsanos NP, et al. A similarity learning approach to content-based image retrieval:application to digital mammography [J]. IEEE Transactions on Medical Imaging,2004,23(10):1233-1244.
[14]Manjunath BS, Ohm JR, et al. Color and texture descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11 (6):703-715.
[15]Borber M. MPEG-7 visual shape descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11 (6):716-719.
[16]Farzanegan F. Keep AFIP [J]. Journal of the American College of Radiology,2006, 3 (12):961.
[17]Kreel L, Arnold MM, Lo YF. Radiological-pathological correlation of mass lesions in the liver [J] Australasian Radiology,1991,35 (3):225-232.
[18]Rosenfeld, Pfaltz JL. Sequential operations in digital picture processing [J]. Journal of ACM (JACM),1996,13(4):471-494.
[19]Li FF, Perona P. A bayesian hierarchical model for learning natural scene categories [C]. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05),2:524-531.
[20]Luo HL, H HW, Lai LL. Creating efficient visual codebook ensembles for object categorization [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans,2011,41(2):238-253.
[21]Gemert JC, Snoek CGM, Veenman CJ, et al. Comparing compact codebooks for visual categorization [J]. Computer Vision and Image Understanding,2011,114(4): 450-462.
[22]Perronnin F. Universal and adapted vocabularies for generic visual categorization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30 (7):1243-1256.
[23]Chapelle O, Wu M. Gradient descent optimization of smoothed information retrieval metrics [J]. Information Retrieval,2010,13(4):216-235.
[24]Qin T, Liu TY, Li H. A general approximation framework for direct optimization of information retrieval measures [J]. Information Retrieval,2010,13(4):375-397.
[25]Taylor M, Guiver J, Robertson S, et al. SoftRank:optimizing non-smooth rank metrics [C]. Proceeding of the International Conference on Web Search and Web Data Mining,2008.
[26]Chang H, Yeung DY. Kernel-based distance metric learning for content-based image retrieval [J]. Image and Vision Computing,2007,25(5):695-703.
[27]Friedman JH. Regularized Discriminant Analysis [J]. Journal of Amercian Statistical Association,1989,84(405):165-175.
[28]Ye J, Wang T. Regularized Discriminant Analysis for High Dimensional, Low Sample Size Data [C]. Proceeding of the 12th ACM SIGKDD Int'l Conference on Knowledge Discovery and Data Mining (KDD'06),2006,454-463.
[29]Cai D, He XF, Han JW. SRDA:An Efficient Algorithm for Large Scale Discriminant Analysis [J]. IEEE Transactions on Knowledge and Data Engineering, 2008,20(1):1-12.
[30]Hua G, Brown M, Winder S. Discriminant embedding for local image descriptors [C]. Proceeding of IEEE the 11th International Conference on Computer Vision, 2007,1-8.
[31]Mikolajczyk K, Matas J. Improving descriptors for fast tree matching by optimal linear projection [C]. Proceeding of IEEE the 11th International Conference on Computer Vision,2007,1-8.
[32]Cai HP, Mikolajczyk K, Matas, J. Learning linear discriminant projections for dimensionality reduction of image descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33 (2):338-352.
[33]Mougiakakou SG, Valavanis IK, Nikita A, et al. Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifier [J]. Artificial Intelligence in Medicine,2007,41(1):25-37.
[34]Zhang XJ, Fujita HS, Qin TF, et al. CAD on liver using CT and MRI [J]. Medical Imaging and Informatics, Lecture Notes in Computer Science,2008,4987: 367-376.
[35]Napel SA, Beaulieu CF, Rodriguez C, et al. Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity:Method and Preliminary Results [J]. Radiology,2010,256(1):243-252.
[36]Ngo CW, Jiang YG, Wei XY, et al. Experimenting VIREO-374: Bag-of-Visual-Words and Visual-Based Ontology for Semantic Video Indexing and Search [C]. Proceedings of TRECVID, November,2007.
[37]Sobel JL, Pearson ML, Gross K, et al. Information content and clarity of radiologists'reports for chest radiography [J]. Academic Radiology,1996,3 (9): 709-717.
[38]Stoutjesdijk MJ, Futterer JJ, Boetes C, et al. Variability in the description of morphologic and contrast enhancement characteristics of breast lesions on magnetic resonance imaging [J]. Investigative Radiology,2005,40 (6):355-362.
[2]LeBozec C, Jaulent M-C, Zapletal E, et al. Unified modeling language and design of a case-based retrieval system in medical imaging [C]. in:Proceedings of the Annual Symposium of the American Society for Medical Informatics (AMIA), Nashville, TN, USA,1998.
[3]Bui AAT, Taira RK, Dionision JDN, et al. Evidence-based radiology [J]. Academic Radiology,2002,9(6):662-669.
[4]Giild MO, Kohnen M, Keysers D, et al. Quality of DICOM header information for image categorization [J]. In:International Symposium on Medical Imaging, Vol. 4685 of SPIE Proceedings, San Diego, CA, USA,2002:280-287.
[5]Smeulders AW, Worring M, Santini S, et al. Content-based image retrieval at the end of the early years [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2000,22(12):1349-1380.
[6]Datta R, Joshi D, Li J, Wang JZ. Image Retrieval:Ideas, Influences, and Trends of the New Age [C]. ACM Computing Surveys,2008,40(65).
[7]Datta R, Joshi D, Li J, Wang JZ. Content-Based Image Retrieval-Approaches and Trends of the New Age [C]. Proceedings of the 7th International Workshop on Multimedia Information Retrieval, in conjunction with ACM International Conference on Multimedia, Singapore, ACM, November 2005,253-262.
[8]Yang ZJ, Kuo C-CJ. Survey on Image Content Analysis, Indexing, and Retrieval Techniques and Status Report of MPEG-7 [J]. Tamkang Journal of Science and Engineering,1999,2(3):101-118.
[9]Swain M, Ballard D. Color indexing [J]. Int'l Journal of Computer Vision,1991, 7(1):11-32.
[10]Stricker M, Orengo M. Similarity of color images [J]. In SPIE Storage and Retrieval of Image and Video Databases,1995,2420:381-392.
[11]Smith JR, Li C-S. Image classification and querying using composite region templates [J]. Computer Vision and Image Understanding, Special Issue on Content-Based Access of Image and Video Libraries,1999,75(1/2):165-174.
[12]Pratt WK. Digital Image Processing [M],2nd edition. John Wiley & Sons Publication,1991.
[13]Aksoy S, Haralick RM. Textural features for image database retrieval [C]. In: IEEE CVPR'98 Workshop on Content-Based Access of Image and Video Libraries,1998: 45.
[14]Tamura H, Mori S, Yamawaki T. Texture features corresponding to visual perception [J]. IEEE Trans, on Sys. Man and Cyb,1978,8(6):460-473.
[15]Manjunath B, Wu P, Newsam S, et al. A texture descriptor for browsing and similarity retrieval [J]. Journal of Signal Processing:Image Communication,2000, 16(1-2):33-43.
[16]Ahmadian, Faramarzi E, Sayadian. Image Indexing and Retrieval Using Gabor Wavelet and Legendre Moments [C]. Proceedings of the 25th Annual International Conference of the IEEE EMBS Cancun, Mexico September,2003:17-21.
[17]Chang T, Kuok CCJ. Texture analysis and classification with tree-structured wavelet transform [J]. IEEE Trans,on Image Processing,1993,2(4):429-440.
[18]Simoncelli EP, Portilla J. Texture characterization via joint statistics of wavelet coefficient magnitudes [C]. In:IEEE International Conference on Image Processing,1998:62-66.
[19]Nevel AV. Texture synthesis via matching first and second order statistics of a wavelet frame decomposition [C]. In:IEEE International Conference on Image Processing,1998:72-76.
[20]Hu MK. Visual pattern recognition by moment invariants [J]. IEEE Transaction on Information Theory,1962,8(1):179-187.
[21]Shen L, Rangayyan RM, Desautels JEL. Detection and Classification of Mammographic Calcification [J]. International Journal of Pattern Recognition and Artificial Intelligence,1993,7(6):1403-1416.
[22]Persoon E, Fu KS. Shape discrimination using Fourier descriptors [J], IEEE Trans. System Man Cybernet,1977, SMC-7 (3):170-179.
[23]Zhang DS, Lu G. A comparison of shape retrieval using Fourier descriptors and short-time Fourier descriptors [C]. In:Proceedings of the Second IEEE Conference on Multimedia (PCM01), Beijing, China, October 24-26,2001:855-860.
[24]Jain AK, Vailaya A. Image retrieval using color and shape [J]. Pattern Recognition, 1996,29(8):1233-1244.
[25]Brandt S, Laaksonen J, Oja E. Statistical shape features in content-based image retrieval [C]. In: Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain,2000,2:1062-1065.
[26]Tieng QM, Boles WW. Recognition of 2D object contours using the wavelet transform zero-crossing representation [J]. IEEE Trans. Pattern Anal. Mach. Intell, 1997,19(8):910-916.
[27]Chuang GC-H, Kuo C-CJ. Wavelet descriptor of planar curves:theory and applications [J]. IEEE Trans.on Image Processing,1996,5(1):56-70.
[28]CHAN TF, VESE L. Active contour without edges [J]. IEEE Transon Image Processing,2001,10(2):266-277.
[29]Lim YW, Lee SU. On the Color Image Segmentation Algorithm Based on the Thresholding and the Fuzzy c means Techniques [J]. Pattern Recognition,1990, 23(9):935-51.
[30]Dempster A, Laird N, Rubin D. Maximun Likehood from incomplete data via the EM algorithm [J]. J Royal Stat Soc,1977,39(1):1-38.
[31]章毓晋.图像工程(中)图像分析[M].北京：清华大学出版社,2005：102-103.
[32]Lucchese L, Mitra SK. Color image segmentation: a state-of-the-art survey [C]. Proceedings of the Indian National Science Academy (INSA-A), New Delhi,2001, 67(2):207-221.
[33]Zhang YY, Michael B, Stephen S. Segmentation of brain images through a hidden Markov random field model and the expectation maximization algorithm [J]. IEEE TMI,2001,20(1):45-57.
[34]Niblack W, Barber R, Equitz W, et al. QBIC project:querying images by content, using color, texture, and shape [J]. Proc. SPIE,1993,1908:173-187.
[35]Sebe N, Lew M, Huijsmans DP. Toward improved ranking metrics [J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2000,22(10):l 132-1143.
[36]Rui Y, Huang TS, Ortega M, et al. Relevance feedback:A power tool in interactive content-based image retrieval [J]. IEEE Transactions on Circuit s and Systems for Video Technology,1998,8(5):644-655.
[37]Selaroff S, Taycher L, Cascia ML. Imagerover: A content-based image browser for the World Wide Web [C]. In: proceedings of IEEE Work shop on Content-Based Access of Image and Video Libraries, San Juan, Puerto Rico, June 1997:2-9.
[38]Zhou XS, Huang TS. Relevance Feedback in Image Retrieval:A Comprehensive Review [J]. Multimedia Systems,2003,8:536-544.
[39]吴洪,卢汉清,马颂德.基于内容图像检索中相关反馈技术的回顾[J].计算机学报,2005,28(12)：1969-1979.
[40]张晨光.基于内容的肝脏CT图像检索的研究[D],上海交通大学,2005,PP.1.
[41]Mougiakakou SG, Valavanis IK, Nikita A, et al. Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifier[J]. Artificial Intelligence in Medicine,2007,41(1):25-37,
[42]Zhang XJ, Fujita HS, Qin TF, et al. CAD on liver using CT and MRI, Medical Imaging and Informatics [J]. Lecture Notes in Computer Science,2008,4987: 367-376.
[43]Napel SA, Beaulieu CF, Rodriguez C, et al. Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity: Method and Preliminary Results, Radiology [J].2010,256(l):243-252.
[1]Shyu C, Kak A, Kosaka A, et al. ASSERT: A physician-in-the-loop content based image retrieval system for HRCT image databases [J]. Computer Vision and Image Understanding,1999,75(1):111-132.
[2]Mattie ME, Staib L, Stratmann E, et al. PathMaster:Content-based cell image retrieval using automated feature extraction [J]. Journal of the American Medical Informatics Association,2000,7:404-415.
[3]Wang JZ. Pathfinder: multiresolution region-based searching of pathology images using IRM [J]. Journal of the American Medical Informatics Association,2000,7: 883-887.
[4]Miiller H, Rosset A, Vallee, J-P et al. Comparing features sets for content-based image retrieval in a medical-case database [C]. In:SPIE Conference on Medical Imaging, San Diego, CA, USA,2004:99-109.
[5]Lehmann TM, Guld MO, Keysers D, et al. Similarity of medical images computed from global feature vectors for content-based retrieval [J]. Lecture Notes in Artificial Intelligence,2004,3214:989-995.
[6]Lehmann, TM, Giild MO, Thies C, et al. IRMA—Content-based image retrieval in medical applications [J]. Methods Inf Med,2004,43:354-361.
[7]Antani S, Lee DJ, Long LR, et al. Evaluation of shape similarity measurement methods for spine X-ray images [J]. Journal of Visual Communication and Image Representation,2004,15(3):285-302.
[8]Antani S, Xu X, Long LR, et al. Partial shape matching for CBIR of spine X-ray images [C]. In:Proceedings of IS&T/SPIE Electronic Imaging-Storage and Retrieval Methods and Applications for Multimedia,2004:1-8.
[9]Veropoulos K, Campbell C, Learnmonth G. Image processing and neural computing used in the diagnosis of tuberculosis [C]. In:Proceedings of the Colloquium on Intelligent Methods in Healthcare and Medical Applications (IMHMA), York, England,1998:8/1-8/4.
[10]Brodley C, Kak A, Shyu C, et al. Content-based retrieval from medical image databases: A synergy of human interaction, machine learning and computer vision [C]. In:Proceedings of the 10th National Conference on Artificial Intelligence, Orlando, FL, USA,1999:760-767.
[11]Bueno JM, Chino F, Traina AJM, et al. How to add content-based image retrieval capacity into a PACS [C]. In: Proceedings of the IEEE Symposium on Computer-Based Medical Systems (CBMS 2002), Maribor, Slovenia,2002: 321-326.
[12]Xian GM.An identification method of malignant and benign liver tumors from ultrasonography based on GLCM texture features and fuzzy SVM [J]. Expert Systems with Applications,2010,37(10):6737-6741.
[13]Beretti S, Del Bimbo A, Pala P. Content-based retrieval of 3D cellular structures [C]. In:Proceedings of the second International Conference on Multimedia and Exposition (ICME'2001), IEEE Computer Society, IEEE Computer Society, Tokyo, Japan,2001:1096-1099.
[14]Sastry CS, Ravindranath M, Pujari AK, et al. A modified Gabor function for content based image retrieval [J]. Pattern Recognition Letters,2007,28(2): 293-300.
[15]Tang LH, Hanka R, Ip HHS, et al. Extraction of semantic features of histological images for content-based retrieval of images [C]. In:Proceedings of the IEEE Symposium on Computer-Based Medical Systems (CBMS2000), Houston, TX, USA,2000.
[16]Han J, Ma KK. Rotation-invariant and scale-invariant Gabor features for texture image retrieval [J]. Image and Vision Computing,2007,25(9):1474-1481.
[17]Miiller H, Rosset A, Valleee JP, et al. Integrating content-based visual access methods into a medical case database [C]. In: Proceedings of the Medical Informatics Europe Conference (MIE 2003), St. Malo, France,2003:480-485.
[18]Kwak DM, Kim BS, Yoon OK, et al. Content-based ultrasound image retrieval using a coarse to fine approach [J]. Annals of the New York Academy of Sciences, 2002,980:212-224.
[19]Hu MK. Visual pattern recognition by moment invariants [J]. IEEE Transaction on Information Theory,1962,8(1):179-187
[20]Haralick R.M., Shanmugam K., Texture feature for image classification [J]. IEEE Trans. On System, Man and Cybernetics,1973, SMC-3(6):610-621.
[21]Reis MS, Bauer A. Using Wavelet Texture Analysis in Image-Based Classification and Statistical Process Control of Paper Surface Quality [J]. Computer Aided Chemical Engineering,2009,29:1209-1214.
[22]Osowski S, Nghia DD. Fourier and wavelet descriptors for shape recognition using neural networks—a comparative study [J]. Pattern Recognition,2002,35(9): 1949-1957.
[23]Persoon E, Fu KS. Shape discrimination using Fourier descriptors [J]. IEEE Trans. on PAMI,1986,8:388～397.
[24]Zhang DS, Lu GJ. Study and evaluation of different Fourier methods for image retrieval [J]. Image Vision Computing,2005,23:33-49.
[25]Shen L, Rangayyan RM, Desautels JEL. Detection and classification of mammographic calcification [J]. International Journal of Pattern Recognition and Artificial Intelligence,1993,7(6):1403-1416.
[26]安志勇.基于内容的图像检索关键技术研究[D].博士论文,2008：pp.24.
[27]Santini S, Jain R. Similanrity math [J]. IEEE Trans. On PAMI,1996,18(9): 946-958.
[28]Swain MJ, Ballar DH, Color indexing [C]. Intl.J. on Computer Vision,1991,7(1): 11-32.
[29]庄越挺,潘云鹤,吴飞,网上多媒体信息分析与检索[M].清华大学出版社,北京,2002,pp.42-43.
[30]Hafner J, Sawhney H, Equitz W, et al. Efficient color histogram indexing for quadratic form distance function [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,1995,17(7):729-736.
[31]Weinberger KQ, Blitzer J, Saul LK. Distance metric learning for large margin nearest neighbor classification [C]. In Proc. Adv. Neural Inf. Process. Syst.,2005, 1473-1480.
[32]Zhang DS. Image Retrieval Based on Shape [C], PhD Thesis, Monash University, March,2002.
[33]盛骤,谢式千,潘承毅,概率论与数理统计[M ].高等教育出版社,1989.
[34]Kullback S. Information theory and statistics [M]. Dover, New York, NY,1968.
[35]Puzicha J, Hufinann T, Buhmann J. Non-parametric similarity measure for unsupervised texture segmentation and image retrieval [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 1997, 267-272.
[36]Zhang DS, Lu GJ. Evaluation of similarity measurement for image retrieval [C]. IEEE Int. Conf. Neural Networks & Signal Processing, Nan Jing, China,2003, 928-931.
[37]Lee HY, Lee HK, Ha YH. Spatial color descriptor for image retrieval and video segmentation [J]. IEEE Trans. On Multimedia,2003,5(3):358-367.
[38]Arnold WM, Marcel W, Simone S, et al. Content-based image retrieval at the end of the early years [J]. IEEE Trans. On PAMI.2000,22(12):1349-1379.
[39]Vogel J, Schiele B. Performance evaluation and optimization for content-based image retrieval [J]. Pattern Recognition,2006,39(5):897-909.
[1]Rui Y, Huang TS, Chang SF. Image retrieval:Current techniques, promising directions, and open issues [OL].http://research. microsoft, com/ users/ yongrui/ html/ publication. Html,1999
[2]Manjunath BS, Ohm JR., et al. Color and texture descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11(6):703～715.
[3]Borber M. MPEG-7 visual shape descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11 (6):716～719.
[4]Smith JR, Chang SF. Automated binary texture feature sets for image retrieval [A]. 1996, proc.ICASSP-96.
[5]Wouwer GV, Scheunders P, Dyck DV. Statistical texture characterization from discrete wavelet representations [J]. IEEE Trans. Image Proc.,1999,8(4):592-598.
[6]Do MN, Vetterli M. Rotation invariatnt texture characterization and retrieval using steerable wavelet-domain hidden markov-models [J]. IEEE Trans. On Multimedia. 2002,4:517-527 Dec.
[7]Do MN, Vetterli MN. Wavelet-based texture retrieval using generalized Gaussian density and kullback-leibler distance [J]. IEEE Transactions on Image Processing, 2002,11:146-158.
[8]Miiller H, Michoux N, Bandon D, et al. A review of content-based image retrieval systems in medical applications-clinical benefits and future directions [J]. International Journal of Medical Informatics,2004,73(1):1-23.
[9]Rahman MM, Bhattacharya P, DesaiA BC. Framework for medical image retrieval using machine learning and statistical similarity matching techniques with relevance feedback [J]. IEEE Transactions on Information Technology in Biomedicine,2007,11(1):58-69.
[10]Ohm JR, Bunjamin FB, Liebsch W, et al. A set of visual feature descriptors and their combination in a low-level description scheme [J]. Signal Process. Image Commun.2000,16:157-179.
[11]Tieng QM, Boles WW. Recognition of 2D object contours using the wavelet transform zero-crossing representation [J]. IEEE Trans. Pattern Anal. Mach. Intell, 1997.19 (8):910-916.
[12]Malik A, Zremic T. Classification of medical images using energy information obtained from wavelet transform for medical image retrieval [C]. In: Proceedings of 7th International Workshop on Enterprise networking and Computing in Healthcare Industry,2005:124-129.
[13]He WJ, Lai MJ. Construction of bivariate compactly supported biorthogonal box spline wavelet with arbitrarily high regularities [J]. Applied Comput. Harmonic Analysis,1999,6:53-74
[14]Z. He, X. You, Y. Y Tang, et al. Texture image retrieval using novel non-separable filter banks based on centrally symmetric matrices[J], in: Proceedings of 18th International Conference on Pattern Recognition, August 2006, pp.161-164.
[15]He ZY, You XG, Tang YY. Texture image retrieval based on non-tensor product wavelet filter banks [J]. Signal Processing,2009,89(8):1501-1510.
[16]Zhang DS, Lu G.J. Evaluation of similarity measurement for image retrieval [J], IEEE Int. Conf. Neural Networks & Signal Processing, Nan Jing, China,2003, 928-931.
[1]Smith JR, Chang SF. Automated binary texture feature sets for image retrieval [A]. 1996,proc.ICASSP-96.
[2]Wouwer GV, Scheunders P, Dyck DV. Statistical texture characterization from discrete wavelet representations [J]. IEEE Transactions on Image Processing,1999, 8(4):592-598.
[3]Do MN, Vetterli M. Rotation invariatnt texture characterization and retrieval using steerable wavelet-domain hidden markov-models [J]. IEEE Transactions On Multimedia.2002,4:517-527.
[4]Do MN, Vetterli M. Wavelet-based texture retrieval using generalized Gaussian density and kullback-leibler distance [J]. IEEE Transactions on Image Processing, 2002,11:146-158.
[5]He ZY, You XG, Tang YY. Texture image retrieval based on non-tensor product wavelet filter banks [J]. Signal Processing,2009,89(8):1501-1510.
[6]Yu M, Lu ZT, Feng QJ, et al. Liver CT image retrieval based on non-tensor product wavelet [C].2010 IEEE International Conference on Medical Image Analysis and Clinical Applications (MIACA),67-70.
[7]Furht B, Smoliar SW, Zhang H J. Video and image processing in multimedia systems [M]. Kluwer Academic Publishers,1995:226-70.
[8]Zhang DS, Lu GJ. Evaluation of similarity measurement for image retrieval [J]. Proceedings of the International Conference on Neural Networks and Signal Processing,2003,2:928-31.
[9]Nastar C, Mitschke M, Meihac C. Efficient Query Refinement for Image Retrieval [J]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Santa Barbara, California, IEEE Computer Society,1998, 547-52.
[1]Shyu C, Kak A, Kosaka A, et al. ASSERT: A physician-in-the-loop content based image retrieval system for HRCT image databases [J]. Computer Vision and Image Understanding,1999,75(1):111-132.
[2]Rosenfeld, Pfaltz J. L. Sequential operations in digital picture processing [J]. Journal of ACM,1996,13(4):471-494.
[3]Falconer K.J.Fractal Geometry:Mathematical Foundation and Application [M]. New York:Wiley,1990.
[4]冯晨.基于分形维数的中国海常见浮游植物细胞图像特征提取[D].博士论文,2006.pp：13.
[5]Xia Y, Feng DG, Zhao RC, et al. Multifractal signature estimation for textured image segmentation [J]. Pattern Recognition Letter,2010,31(2):163-169.
[6]Uemura K, Toyama H, Baba S, et al. Generation of fractal dimension images and its application to automatic edge detection in brain MRI [J]. Computerized Medical Imaging and Graphics,2000,24(2):73-85.
[7]Varma V, Garg R. Locally invariant fractal features for statistical texture classification [C]. Proc. IEEE International Conference on Computer Vision,2007: 1-8.
[8]Park PK, Lee CH, Lee S. Determination of cake porosity using image analysis in a coagulation-microfiltration system [J]. Journal of Membrane Science,2007,29(3): 66-72.
[9]Imai K, Ikeda M, Enchi Y, et al. Fractal-Feature Distance Analysis of Radiographic Image [J]. Academic Radiology,2007,14(2):137-143.
[10]Yu L, Zhang D, Wang KQ, et al. Coarse iris classification using box-counting to estimate fractal dimensions [J]. Pattern Recognition,2005,38(11):1791-1798.
[11]Myint SW, Lam N. A study of lacunarity-based texture analysis approaches to improve urban image classification. Computers [J]. Environment and Urban Systems,2005,29(5):501-523.
[12]Pentland AP. Fractal based description of natural scenes [J]. IEEE Trans. Pattern Anal. Mach, Intell,1984,6:661-674.
[13]Hastie T, Tibshirani R. Discriminant adaptive nearest neighbor classification [J]. IEEE Trans.Pattern Anal. Mach. Intell.,1996,18(6):607-616.
[14]Yu J, Amores J, Sebe N, et al. Distance learning for similarity estimation [J]. IEEE Trans. Pattern Anal. Mach. Intell.,2008,30(3):451-462.
[15]Jian B, Vemuri BC. Metric learning using Iwasawa decomposition [C]. In Proceeding IEEE International Conference of Computer Vision,2007,1-6.
[16]Xing EP, Ng AY, Jordan MI, et al. Distance metric learning, with application to clustering with side-information [C]. In Proc. Adv. Neural Inf. Process. Syst. MIT Press,2002.
[17]Bar-Hillel A, HertzT, Shental N, et al. Learning a Mahalanobis metric from equivalence constraints [J]. Journal of Machine Learning Research,2005, 6:937-965.
[18]Fukunage K. Introduction to Statistical Pattern Recognition [M].2nd edition. Boston:Academic Press,1990.
[19]Boyd S, Vandenberghe L. Convex optimization [M]. New York:Cambridge University Press,2006.
[20]Turk M, Pentland A. Eigenfaces for Recognition [J]. Journal of Cognitive Neuroscience,199,3(1):71-86.
[21]Belhumeur PN, Hespanda J, Kriegeman D. Eigenfaces vs. Fisherfaces:Recognition Using Class Specific Linear Projection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[22]Globerson A, Roweis S. Metric learning by collapsing classes [M]. Advances in neural information processing systems 18. Cambridge, MA:MIT Press,2006.
[23]Masashi S. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis [J]. J. Mach. Learn. Res.,2007,8:1027-1061.
[24]Weinberger KQ, Saul LK. Distance metric learning for large margin nearest neighbor classification [J]. The Journal of Machine learning Research,2009,10: 207-244.
[25]Shen CH, Welsh A, Wang L. PSDBoost:Matrix-generation linear programming for positive semidefinite matrices learning [C]. Proc. Adv. Neural Inf. Process. Syst., 2008,1473-1480.
[26]Shen CH, Kim J, Wang L, et al. Positive Semidefinite Metric Learning using Boosting-like Algorithms [J]. Journal of Learning Research,2012,1007-1036.
[27]Schapire RE. Theoretical views of boosting and applications [C]. In Proc. Int. Conf. Algorithmic Learn. Theory,1999,13-25.
[28]Goldberger J, Roweis S, Hinton G. Neighbourhood component analysis [C]. In Proc. Adv. Neural Inf. Process. Syst. MIT Press,2004.
[1]Armato SG, McNitt-Gray MF, Reeves AP, et al. The Lung Image Database Consortium (LIDC):an evaluation of radiologist variability in the identification of lung nodules on CT scans [J]. Academic Radiology,2007,14 (11):1409-1421.
[2]Barlow WE, Chi C, Carney PA, et al. Accuracy of screening mammography interpretation by characteristics of radiologists [J]. Journal of the National Cancer Institute,2004,96 (24):1840-1850.
[3]Robinson PJ. Radiology's Achilles'heel:error and variation in the interpretation of the Rontgen image [J]. The British Journal of Radiology,1997,70 (839):1085 1098.
[4]Yuan K, Tian Z, Zou J, et al. Brain CT image database building for computer-aided diagnosis using content-based image retrieval [J]. Information Processing and Management,2011,47(2):176-185.
[5]Huang YL, Chen JH, Shen WC. Computer-Aided Diagnosis of Liver Tumors in Non-enhanced CT Images [J]. Journal of Medical Physics,2004,9:141-150.
[6]Chen EL, Chung PC, Chen CL, et al. An automatic diagnostic system for CT liver image classification [J]. IEEE Transactions Biomedical Engineering,1998,45(6): 783-794.
[7]Greenspan H, Pinhas AT. Medical image categorization and retrieval for PACS using the GMM-KL framework [J]. IEEE Transactions on Information Technology in Biomedicine,2007,11(2):190-202.
[8]Iakovidis DK, Pelekis N, Kotsifakos EE, et al. A pattern similarity scheme for medical image retrieval [J]. IEEE Transactions on Information Technology in Biomedicine,2009,13(4):442-450.
[9]Rahman MM, Desai BC, Bhattacharya P. Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion [J]. Computerized Medical Imaging and Graphics,2008,32(2):95-108.
[10]Huang Y, Kuo S, Chang C, et al. Image retrieval with principal component analysis for breast cancer diagnosis on various ultrasonic systems [J]. Ultrasound Obstetrics & Gynecology,2005,26(5):558-566.
[11]Jennifer GD, Carla EB, Avi K, et al. Unsupervised feature selection applied to content-based retrieval of lung images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(3):373-378.
[12]Oliveira JD, Machado A, Chavez G, et al. MammoSys:A content-based image retrieval system using breast density patterns [J]. Computer Methods and Programs in Biomedicine,2010,99(3):289-297.
[13]Naqa IE, Yang Y, Galatsanos NP, et al. A similarity learning approach to content-based image retrieval:application to digital mammography [J]. IEEE Transactions on Medical Imaging,2004,23(10):1233-1244.
[14]Manjunath BS, Ohm JR, et al. Color and texture descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11 (6):703-715.
[15]Borber M. MPEG-7 visual shape descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology,2001,11 (6):716-719.
[16]Farzanegan F. Keep AFIP [J]. Journal of the American College of Radiology,2006, 3 (12):961.
[17]Kreel L, Arnold MM, Lo YF. Radiological-pathological correlation of mass lesions in the liver [J] Australasian Radiology,1991,35 (3):225-232.
[18]Rosenfeld, Pfaltz JL. Sequential operations in digital picture processing [J]. Journal of ACM (JACM),1996,13(4):471-494.
[19]Li FF, Perona P. A bayesian hierarchical model for learning natural scene categories [C]. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05),2:524-531.
[20]Luo HL, H HW, Lai LL. Creating efficient visual codebook ensembles for object categorization [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans,2011,41(2):238-253.
[21]Gemert JC, Snoek CGM, Veenman CJ, et al. Comparing compact codebooks for visual categorization [J]. Computer Vision and Image Understanding,2011,114(4): 450-462.
[22]Perronnin F. Universal and adapted vocabularies for generic visual categorization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30 (7):1243-1256.
[23]Chapelle O, Wu M. Gradient descent optimization of smoothed information retrieval metrics [J]. Information Retrieval,2010,13(4):216-235.
[24]Qin T, Liu TY, Li H. A general approximation framework for direct optimization of information retrieval measures [J]. Information Retrieval,2010,13(4):375-397.
[25]Taylor M, Guiver J, Robertson S, et al. SoftRank:optimizing non-smooth rank metrics [C]. Proceeding of the International Conference on Web Search and Web Data Mining,2008.
[26]Chang H, Yeung DY. Kernel-based distance metric learning for content-based image retrieval [J]. Image and Vision Computing,2007,25(5):695-703.
[27]Friedman JH. Regularized Discriminant Analysis [J]. Journal of Amercian Statistical Association,1989,84(405):165-175.
[28]Ye J, Wang T. Regularized Discriminant Analysis for High Dimensional, Low Sample Size Data [C]. Proceeding of the 12th ACM SIGKDD Int'l Conference on Knowledge Discovery and Data Mining (KDD'06),2006,454-463.
[29]Cai D, He XF, Han JW. SRDA:An Efficient Algorithm for Large Scale Discriminant Analysis [J]. IEEE Transactions on Knowledge and Data Engineering, 2008,20(1):1-12.
[30]Hua G, Brown M, Winder S. Discriminant embedding for local image descriptors [C]. Proceeding of IEEE the 11th International Conference on Computer Vision, 2007,1-8.
[31]Mikolajczyk K, Matas J. Improving descriptors for fast tree matching by optimal linear projection [C]. Proceeding of IEEE the 11th International Conference on Computer Vision,2007,1-8.
[32]Cai HP, Mikolajczyk K, Matas, J. Learning linear discriminant projections for dimensionality reduction of image descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33 (2):338-352.
[33]Mougiakakou SG, Valavanis IK, Nikita A, et al. Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifier [J]. Artificial Intelligence in Medicine,2007,41(1):25-37.
[34]Zhang XJ, Fujita HS, Qin TF, et al. CAD on liver using CT and MRI [J]. Medical Imaging and Informatics, Lecture Notes in Computer Science,2008,4987: 367-376.
[35]Napel SA, Beaulieu CF, Rodriguez C, et al. Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity:Method and Preliminary Results [J]. Radiology,2010,256(1):243-252.
[36]Ngo CW, Jiang YG, Wei XY, et al. Experimenting VIREO-374: Bag-of-Visual-Words and Visual-Based Ontology for Semantic Video Indexing and Search [C]. Proceedings of TRECVID, November,2007.
[37]Sobel JL, Pearson ML, Gross K, et al. Information content and clarity of radiologists'reports for chest radiography [J]. Academic Radiology,1996,3 (9): 709-717.
[38]Stoutjesdijk MJ, Futterer JJ, Boetes C, et al. Variability in the description of morphologic and contrast enhancement characteristics of breast lesions on magnetic resonance imaging [J]. Investigative Radiology,2005,40 (6):355-362.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |