基于改进选择性视觉注意模型的语义图像分割研究
|
摘要
自动语义图像分割是计算机视觉领域中一个非常具有挑战性的课题，它是迈向图像理解的关键步骤。然而，用户对图像的理解或检索无法用图像处理算法提取的底层图像特征来完全表达。因此，图像分割与检索等技术面临的严峻问题之一是底层图像特征与高层语义之间存在的巨大语义鸿沟。
选择性视觉注意模型（SVAM）是为拟合人类视觉注意机制而提出的可计算模型，它能获得图像中最容易引起人们注意的显著区域，从而能更好地进行语义图像分割。另一方面，作为第3代人工神经网络主要代表的脉冲耦合神经网络（PCNN）在图像分割方面也有良好的性能。为了进一步提高语义图像分割的准确性，本文研究SVAM+PCNN整合模型的自动语义图像分割模型或方法。主要研究内容和结论如下：
（1）针对PCNN分割输出为二值图像，而选择性视觉注意模型显著性检测输出为灰度显著图，二者难以直接进行公平比较的问题，采用二者最终彩色图像分割结果灰度化方法，然后对二者的灰度图像分割结果进行受试者工作特征（ROC）曲线分析，来达到二者语义图像分割结果公平比较、分析的目的。实验结果表明，改进ROC分析方法能够有效评价与分析不同类型的图像分割模型或方法。针对整合模型与其组成模型之间性能评价的常用数字化指标差异不大时，缺少评价改进效果或显著性差异的评判标准问题，本文提出把统计学上的均方差指标、双侧Student’s t-test假设检验方法引入模型间的显著性差异分析上。实验结果表明，该指标和方法能够有效评价图像分割模型或方法。
（2）针对STB/Itti选择性视觉注意模型提取出的感兴趣区域过小，难以有效进行语义图像分割的问题，提出STB/Itti+PCNN整合模型。该整合模型以STB/Itti模型提取出的颜色与方向特征融合图作为PCNN的输入图像，以增强PCNN的全局耦合功能与抗噪性；用STB/Itti模型的显著图确定出PCNN应点火神经元范围，PCNN无需多次迭代寻找该范围；并且用PCNN取代STB/Itti模型中的WTA神经网络来进行图像分割结果输出。另外，针对缺乏迭代过程的PCNN其图像分割能力会有所下降的问题，用STB/Itti模型的特征融合图输入和局部迭代归一化合并策略来保持或增强PCNN的图像分割能力。实验结果表明，STB/Itti+PCNN整合模型能够有效进行语义图像分割，平均AUC值比STB/Itti模型提高了127.94%，与STB/Itti模型的显著性差异概率在0.99以上，且具有很强的抵抗噪声污染和几何变换攻击的能力。
（3）为了科学评价语义图像分割效果，在本研究语义图像分割实验及分析文献的基础上，提出8项最佳语义图像分割标准：1）基于一定的生物视觉机制；2）不需任何已知样本训练与可调参数；3）首先关注的是最大的显著区域；4）平滑地囊括显著目标整体；5）分割出的显著目标具良好的形状特征；6）能抵抗噪声污染和几何变换攻击；7）实时地输出全分辨率图像分割结果图；8）可硬件实现。并用这些标准来指导本研究的语义图像分割模型的设计、建立与实现。
（4）为获得最佳语义图像分割结果，本文按照从粗分割到细分割的思想，提出能获得最佳语义图像分割效果的GBVS+PCNN整合模型。在对9种现有SVAM进行视觉效果、性能指标及平均耗时研究对比后，选择GBVS进行语义图像的粗分割，用GBVS提取出的亮度特征图作为PCNN的特殊输入图像，并用该PCNN来扩展GBVS进行语义图像的细分割；最后，用提出的基于“AUC值大小”判决准则的显著区域判别算法，自动完成最终语义图像分割结果的输出。实验结果表明，GBVS+PCNN整合模型能满足前7项最佳语义图像分割标准；该整合模型的PCNN扩展部分则满足全部最佳语义图像分割标准。运用双侧Student’s t-test方法，得出该整合模型与GBVS之间的显著性差异概率在0.99以上。
（5）针对PQFT模型提取出的显著图中冗余低频信息过多，导致不能很好界定显著目标物位置的问题，本文通过PCNN模型自动设置的链接系数来确定出每个像素的周边区域，提出一种拟合生物视觉神经元的中央兴奋-周边抑制机制的精简C-S运算方法，用该运算方法计算出的CIE Lab颜色空间上三通道差值图像作为PQFT的4元数输入图像的虚部系数，从而得到改进PQFT模型：IPQFT，以有效减少显著图中的冗余低频信息。另外，针对基于“AUC值大小”判决准则的显著区域自动判别算法在其整合模型中的平均耗时占到5%过多的问题，提出与其功能相似的基于“尺寸变化与否”判决准则的显著区域判别算法，在MATLBAB环境下使显著区域判别算法对测试图像的平均耗时从102.0ms降到了16.1ms。
（6）针对可硬件实现的实时语义图像分割实际应用需求，提出IPQFT+PCNN整合模型。用IPQFT进行语义图像的粗分割；用PCNN对IPQFT扩展并进行语义图像的细分割；用基于“尺寸变化与否”判决准则的显著区域判别算法来自动完成最终语义图像分割。实验结果表明，在MATLBAB环境下IPQFT+PCNN整合模型处理一幅测试图像的平均耗时为238.2ms，达到了实时性的要求；由于IPQFT中的主要算法傅里叶变换及PCNN均可硬件实现，二者的整合模型也便于硬件实现；另外，该整合模型具有抗噪性、几何不变性等健壮的鲁棒性，同时还具有并行、自动、智能等特点。
（7）针对语义图像分割模型或方法的性能数字化指标综合评价方法尚不完善问题，遵照最佳语义图像分割标准，提出一种不同类型SVAM的综合评分决策表的方法，以丰富SVAM的评价方法与指标体系。从综合得分情况看，本文提出的3种整合模型在语义图像分割方面均优于本研究中现有的9种SVAM，能够显著提高语义图像分割的准确性。
Automatic semantic image segmentation is a challenge task in the computer vision field,which is the key step to image understanding. However, users cannot understand or retrievean image by using raw image features extracted by image processing algorithms. Therefore,one of serious problems confronted by image segmentation and retrieval is the huge semanticgap between raw image features and image semantic acquisition.
Selective visual attention model (SVAM) is the computational model provided formimicking the attention mechanism of human visual system, which can obtain the mostsalient region that attracts people greatly in an image. So, SVAM is able to implementsemantic image segmentation efficiently. On the other hand, as the main representative in thethird generation of artificial neural network, pulse-coupled neural network (PCNN) has thegood performance in image segmentation. In order to further improve the accuracy ofsemantic image segmentation, this dissertation devotes itself to automatic semantic imagesegmentation models or methods based on integration models of SVAM+PCNN. The majorresearch contents and conclusions of this dissertation are summarized as follows.
(1) The output of the PCNN is a binary image, while the salient region detection result ofthe SVAM is a gray-scale image. Then, it is difficult to compare their performance of imagesegmentation directly and fairly. To solve this problem, this paper improves the receiveroperating characteristic (ROC) curve analysis method based on the same platform of theirgray scale image results transformed from their color image segmentation results.Experimental results show that the improved ROC analysis could evaluate different kinds ofimage segmentation models or methods efficiently. Another problem is how to prove that anintegration model is significantly different from its component models. To solve this problem,this paper introduces the mean square deviation in statistics and the statistic method ofStudent’s t-test to the evaluation of different models. Experimental results indicate that thisindex and method can efficiently evaluate image segmentation models or methods.
(2) Considering that the region of interest (ROI) extracted by saliency toolbox (STB)/Ittimodel is not large enough for semantic image segmentation, the integration model ofSTB/Itti+PCNN is proposed. This integration model took fusion image of color andorientation maps extracted by the STB/Itti model as the input image of PCNN, so that the strong image segmentation capability and the property of anti-noise of PCNN could beenhanced; Saliency map generated by STB/Itti was employed to identify the optimal iterationnumber of PCNN at once, and the PCNN did not require many iterations; the PCNN thendisplaced the WTA of STB/Itti to output the semantic image segmentation results.Furhermore, the image segmentation capability of the PCNN lacking iterations will be weak,so two strategies were adopted in order to keep its strong image segmentation capability:Special input image mentioned above was chosen to enhance the global coupled modulationfunction; The feature combination of “iterative local localized interactions” in STB/Itti wasadopted to assist the PCNN in performing the function of pulse synchronization.Experimental results show that the integration model of STB/Itti+PCNN can efficientlysegment images semantically, with mean AUC value increased by127.94%; there issignificant difference at above0.99probability level between STB/Itti+PCNN model andSTB/Itti model, and STB/Itti+PCNN model is robust against noises and geometric attacks.
(3) To evaluate the semantic image segmentation results scientifically, eight criteria ofthe best semantic image segmentation are proposed as follows based on the results of thisresearch and some related literatures.1) Based on biological visual mechanism to some extent;2) Does not require any training, trials or tunable parameters;3) Emphasize on the largestsalient object;4) Uniformly highlight the whole salient regions;5) Establish well-definedboundaries of salient objects;6) Disregard high frequencies arising from noise and geometricattacks;7) Efficiently output full resolution image segmentation results;8) Can beimplemented by hardware easily. Meanwhile, we use these eight criteria to guide the design,building and implementation of the semantic image segmentation models in our research.
(4) To obtain the best semantic image segmentation results, the GBVS+PCNN model isproposed according to the theory from coarse segmentation to fine segmentation. Afterresearching on and comparing with visual effects, performance indices and averagetime-consuming of nine current SVAMs, the GBVS model was chosen to implement thecoarse segmentation, and the intensity feature map extracted by GBVS was used as the inputimage of PCNN which extended GBVS to implement the fine segmentation; Finally, a salientregion identified algorithm based on “AUC Value” was proposed for automatic output of thefinal semantic image segmentation results. Experimental results show that the GBVS+PCNNmodel can meet seven of the eight criteria of the best semantic image segmentation, while thePCNN part of this integration model can conform to all of the eight criteria. By using pairedStudent’s t-test method, we have got the probability level of significant difference betweenGBVS+PCNN model and GBVS model, standing at above0.99.
(5) Saliency map generated by PQFT model cannot locate the salient object of an imagewell, because there is too much redundant low-frequency information. To mimic the center excited-surrounding inhibited mechanism of biological visual neurons, a simplified C-Salgorithm is proposed based on the surrounding region identified by the linking coefficient setautomatically by PCNN. Three subtraction maps of CIE Lab color space channels calculatedby the C-S algorithm were taken as the coefficients of imaginary part of PQFT quaternionimage, through which the improved PQFT, named IPQFT, is proposed. IPQFT could greatlyreduce the redundant low-frequency information in its saliency map. Additionaly, to solve theproblem that the algorithm for automatically identifying the salient region based on “AUCValue” costs5%of average time-consuming in its integration model, a similar algorithmbased on “Size Change” is proposed, which makes the average time-consuming decreasedfrom102.0ms to only16.1ms in MATLAB environment.
(6) To meet the practical application requirements of real-time semantic imagesegmentation method which can be implemented by hardware easily, the integration model ofIPQFT+PCNN is proposed. Just like GBVS+PCNN model, IPQFT was applied for coarsesegmentation; the PCNN extended IPQFT and was used for fine segmentation; the algorithmfor identifying the salient region based on “Size Change” was applied to output automaticallythe final semantic image segmentation results. Experimental results show that the averagetime consumed by IPQFT+PCNN model to process a testing image is about238.2ms inMATLAB environment, which achieves the real-time requirement; because the Fouriertransform and PCNN algorithms of the integration model can all be implemented by hardware,then the IPQFT+PCNN model can also be implemented by integrated circuit easily. Moreover,the IPQFT+PCNN model is robust to noises and geometric attacks, and it is parallel,automatic, and intelligent as well.
(7) Comprehensive evaluation on performance indices of semantic image segmentationmodels or methods is still not perfect. According to the eight criteria of the best semanticimage segmentation, a total score of decision table is proposed to evaluate different kinds ofimage segmentation models or methods, which enriches the current evaluation methods orindices of SVAMs. According to the total scores of the decision table, the three integrationmodels proposed by this dissertation outperform the other nine current SVAMs in semanticimage segmentation, and can output semantic image segmentation results more accurately.
选择性视觉注意模型（SVAM）是为拟合人类视觉注意机制而提出的可计算模型，它能获得图像中最容易引起人们注意的显著区域，从而能更好地进行语义图像分割。另一方面，作为第3代人工神经网络主要代表的脉冲耦合神经网络（PCNN）在图像分割方面也有良好的性能。为了进一步提高语义图像分割的准确性，本文研究SVAM+PCNN整合模型的自动语义图像分割模型或方法。主要研究内容和结论如下：
（1）针对PCNN分割输出为二值图像，而选择性视觉注意模型显著性检测输出为灰度显著图，二者难以直接进行公平比较的问题，采用二者最终彩色图像分割结果灰度化方法，然后对二者的灰度图像分割结果进行受试者工作特征（ROC）曲线分析，来达到二者语义图像分割结果公平比较、分析的目的。实验结果表明，改进ROC分析方法能够有效评价与分析不同类型的图像分割模型或方法。针对整合模型与其组成模型之间性能评价的常用数字化指标差异不大时，缺少评价改进效果或显著性差异的评判标准问题，本文提出把统计学上的均方差指标、双侧Student’s t-test假设检验方法引入模型间的显著性差异分析上。实验结果表明，该指标和方法能够有效评价图像分割模型或方法。
（2）针对STB/Itti选择性视觉注意模型提取出的感兴趣区域过小，难以有效进行语义图像分割的问题，提出STB/Itti+PCNN整合模型。该整合模型以STB/Itti模型提取出的颜色与方向特征融合图作为PCNN的输入图像，以增强PCNN的全局耦合功能与抗噪性；用STB/Itti模型的显著图确定出PCNN应点火神经元范围，PCNN无需多次迭代寻找该范围；并且用PCNN取代STB/Itti模型中的WTA神经网络来进行图像分割结果输出。另外，针对缺乏迭代过程的PCNN其图像分割能力会有所下降的问题，用STB/Itti模型的特征融合图输入和局部迭代归一化合并策略来保持或增强PCNN的图像分割能力。实验结果表明，STB/Itti+PCNN整合模型能够有效进行语义图像分割，平均AUC值比STB/Itti模型提高了127.94%，与STB/Itti模型的显著性差异概率在0.99以上，且具有很强的抵抗噪声污染和几何变换攻击的能力。
（3）为了科学评价语义图像分割效果，在本研究语义图像分割实验及分析文献的基础上，提出8项最佳语义图像分割标准：1）基于一定的生物视觉机制；2）不需任何已知样本训练与可调参数；3）首先关注的是最大的显著区域；4）平滑地囊括显著目标整体；5）分割出的显著目标具良好的形状特征；6）能抵抗噪声污染和几何变换攻击；7）实时地输出全分辨率图像分割结果图；8）可硬件实现。并用这些标准来指导本研究的语义图像分割模型的设计、建立与实现。
（4）为获得最佳语义图像分割结果，本文按照从粗分割到细分割的思想，提出能获得最佳语义图像分割效果的GBVS+PCNN整合模型。在对9种现有SVAM进行视觉效果、性能指标及平均耗时研究对比后，选择GBVS进行语义图像的粗分割，用GBVS提取出的亮度特征图作为PCNN的特殊输入图像，并用该PCNN来扩展GBVS进行语义图像的细分割；最后，用提出的基于“AUC值大小”判决准则的显著区域判别算法，自动完成最终语义图像分割结果的输出。实验结果表明，GBVS+PCNN整合模型能满足前7项最佳语义图像分割标准；该整合模型的PCNN扩展部分则满足全部最佳语义图像分割标准。运用双侧Student’s t-test方法，得出该整合模型与GBVS之间的显著性差异概率在0.99以上。
（5）针对PQFT模型提取出的显著图中冗余低频信息过多，导致不能很好界定显著目标物位置的问题，本文通过PCNN模型自动设置的链接系数来确定出每个像素的周边区域，提出一种拟合生物视觉神经元的中央兴奋-周边抑制机制的精简C-S运算方法，用该运算方法计算出的CIE Lab颜色空间上三通道差值图像作为PQFT的4元数输入图像的虚部系数，从而得到改进PQFT模型：IPQFT，以有效减少显著图中的冗余低频信息。另外，针对基于“AUC值大小”判决准则的显著区域自动判别算法在其整合模型中的平均耗时占到5%过多的问题，提出与其功能相似的基于“尺寸变化与否”判决准则的显著区域判别算法，在MATLBAB环境下使显著区域判别算法对测试图像的平均耗时从102.0ms降到了16.1ms。
（6）针对可硬件实现的实时语义图像分割实际应用需求，提出IPQFT+PCNN整合模型。用IPQFT进行语义图像的粗分割；用PCNN对IPQFT扩展并进行语义图像的细分割；用基于“尺寸变化与否”判决准则的显著区域判别算法来自动完成最终语义图像分割。实验结果表明，在MATLBAB环境下IPQFT+PCNN整合模型处理一幅测试图像的平均耗时为238.2ms，达到了实时性的要求；由于IPQFT中的主要算法傅里叶变换及PCNN均可硬件实现，二者的整合模型也便于硬件实现；另外，该整合模型具有抗噪性、几何不变性等健壮的鲁棒性，同时还具有并行、自动、智能等特点。
（7）针对语义图像分割模型或方法的性能数字化指标综合评价方法尚不完善问题，遵照最佳语义图像分割标准，提出一种不同类型SVAM的综合评分决策表的方法，以丰富SVAM的评价方法与指标体系。从综合得分情况看，本文提出的3种整合模型在语义图像分割方面均优于本研究中现有的9种SVAM，能够显著提高语义图像分割的准确性。
Automatic semantic image segmentation is a challenge task in the computer vision field,which is the key step to image understanding. However, users cannot understand or retrievean image by using raw image features extracted by image processing algorithms. Therefore,one of serious problems confronted by image segmentation and retrieval is the huge semanticgap between raw image features and image semantic acquisition.
Selective visual attention model (SVAM) is the computational model provided formimicking the attention mechanism of human visual system, which can obtain the mostsalient region that attracts people greatly in an image. So, SVAM is able to implementsemantic image segmentation efficiently. On the other hand, as the main representative in thethird generation of artificial neural network, pulse-coupled neural network (PCNN) has thegood performance in image segmentation. In order to further improve the accuracy ofsemantic image segmentation, this dissertation devotes itself to automatic semantic imagesegmentation models or methods based on integration models of SVAM+PCNN. The majorresearch contents and conclusions of this dissertation are summarized as follows.
(1) The output of the PCNN is a binary image, while the salient region detection result ofthe SVAM is a gray-scale image. Then, it is difficult to compare their performance of imagesegmentation directly and fairly. To solve this problem, this paper improves the receiveroperating characteristic (ROC) curve analysis method based on the same platform of theirgray scale image results transformed from their color image segmentation results.Experimental results show that the improved ROC analysis could evaluate different kinds ofimage segmentation models or methods efficiently. Another problem is how to prove that anintegration model is significantly different from its component models. To solve this problem,this paper introduces the mean square deviation in statistics and the statistic method ofStudent’s t-test to the evaluation of different models. Experimental results indicate that thisindex and method can efficiently evaluate image segmentation models or methods.
(2) Considering that the region of interest (ROI) extracted by saliency toolbox (STB)/Ittimodel is not large enough for semantic image segmentation, the integration model ofSTB/Itti+PCNN is proposed. This integration model took fusion image of color andorientation maps extracted by the STB/Itti model as the input image of PCNN, so that the strong image segmentation capability and the property of anti-noise of PCNN could beenhanced; Saliency map generated by STB/Itti was employed to identify the optimal iterationnumber of PCNN at once, and the PCNN did not require many iterations; the PCNN thendisplaced the WTA of STB/Itti to output the semantic image segmentation results.Furhermore, the image segmentation capability of the PCNN lacking iterations will be weak,so two strategies were adopted in order to keep its strong image segmentation capability:Special input image mentioned above was chosen to enhance the global coupled modulationfunction; The feature combination of “iterative local localized interactions” in STB/Itti wasadopted to assist the PCNN in performing the function of pulse synchronization.Experimental results show that the integration model of STB/Itti+PCNN can efficientlysegment images semantically, with mean AUC value increased by127.94%; there issignificant difference at above0.99probability level between STB/Itti+PCNN model andSTB/Itti model, and STB/Itti+PCNN model is robust against noises and geometric attacks.
(3) To evaluate the semantic image segmentation results scientifically, eight criteria ofthe best semantic image segmentation are proposed as follows based on the results of thisresearch and some related literatures.1) Based on biological visual mechanism to some extent;2) Does not require any training, trials or tunable parameters;3) Emphasize on the largestsalient object;4) Uniformly highlight the whole salient regions;5) Establish well-definedboundaries of salient objects;6) Disregard high frequencies arising from noise and geometricattacks;7) Efficiently output full resolution image segmentation results;8) Can beimplemented by hardware easily. Meanwhile, we use these eight criteria to guide the design,building and implementation of the semantic image segmentation models in our research.
(4) To obtain the best semantic image segmentation results, the GBVS+PCNN model isproposed according to the theory from coarse segmentation to fine segmentation. Afterresearching on and comparing with visual effects, performance indices and averagetime-consuming of nine current SVAMs, the GBVS model was chosen to implement thecoarse segmentation, and the intensity feature map extracted by GBVS was used as the inputimage of PCNN which extended GBVS to implement the fine segmentation; Finally, a salientregion identified algorithm based on “AUC Value” was proposed for automatic output of thefinal semantic image segmentation results. Experimental results show that the GBVS+PCNNmodel can meet seven of the eight criteria of the best semantic image segmentation, while thePCNN part of this integration model can conform to all of the eight criteria. By using pairedStudent’s t-test method, we have got the probability level of significant difference betweenGBVS+PCNN model and GBVS model, standing at above0.99.
(5) Saliency map generated by PQFT model cannot locate the salient object of an imagewell, because there is too much redundant low-frequency information. To mimic the center excited-surrounding inhibited mechanism of biological visual neurons, a simplified C-Salgorithm is proposed based on the surrounding region identified by the linking coefficient setautomatically by PCNN. Three subtraction maps of CIE Lab color space channels calculatedby the C-S algorithm were taken as the coefficients of imaginary part of PQFT quaternionimage, through which the improved PQFT, named IPQFT, is proposed. IPQFT could greatlyreduce the redundant low-frequency information in its saliency map. Additionaly, to solve theproblem that the algorithm for automatically identifying the salient region based on “AUCValue” costs5%of average time-consuming in its integration model, a similar algorithmbased on “Size Change” is proposed, which makes the average time-consuming decreasedfrom102.0ms to only16.1ms in MATLAB environment.
(6) To meet the practical application requirements of real-time semantic imagesegmentation method which can be implemented by hardware easily, the integration model ofIPQFT+PCNN is proposed. Just like GBVS+PCNN model, IPQFT was applied for coarsesegmentation; the PCNN extended IPQFT and was used for fine segmentation; the algorithmfor identifying the salient region based on “Size Change” was applied to output automaticallythe final semantic image segmentation results. Experimental results show that the averagetime consumed by IPQFT+PCNN model to process a testing image is about238.2ms inMATLAB environment, which achieves the real-time requirement; because the Fouriertransform and PCNN algorithms of the integration model can all be implemented by hardware,then the IPQFT+PCNN model can also be implemented by integrated circuit easily. Moreover,the IPQFT+PCNN model is robust to noises and geometric attacks, and it is parallel,automatic, and intelligent as well.
(7) Comprehensive evaluation on performance indices of semantic image segmentationmodels or methods is still not perfect. According to the eight criteria of the best semanticimage segmentation, a total score of decision table is proposed to evaluate different kinds ofimage segmentation models or methods, which enriches the current evaluation methods orindices of SVAMs. According to the total scores of the decision table, the three integrationmodels proposed by this dissertation outperform the other nine current SVAMs in semanticimage segmentation, and can output semantic image segmentation results more accurately.
引文
方慧娟,罗继亮,黄彩虹,李平.2011.脉冲神经网络的快速仿真方法.吉林大学学报(工学版),41(1):227~230
飞思科技产品研发中心.2003. MATLAB6.5辅助图像处理.北京:电子工业出版社
高静静.2008.基于视觉注意模型的感兴趣区检测技术研究.[硕士学位论文].北京:北京工业大学
顾晓东.2005.单位脉冲耦合神经网络中若干理念及应用问题的研究.[博士后学位论文].上海：复旦大学
过晨雷.2008.注意力选择机制的研究:算法设计以及系统实现.[硕士学位论文].上海：复旦大学
韩力群.2006.人工神经网络教程.北京:北京邮电大学出版社:22~46
郝明非.2007.彩色图像超复数整体拼接及其质量评估的研究.[硕士学位论文].上海:复旦大学
何东健,耿楠,张义宽.2003.数字图像处理.西安:西安电子科技大学出版社:159~202
何伟,蒋加伏,齐琦.2009.基于粗糙集理论和神经网络的图像分割方法.计算机工程与应用,45(1):188~190
贺俊.2009.基于视觉注意机制的物体显著性研究.[硕士学位论文].上海:上海交通大学
纪永刚.2006.基于微波图像的辽东弯海冰典型要素信息提取.[博士学位论文].北京:中国科学院研究生院
贾云得.2000.机器视觉.北京:科学出版社:15~26
江淑红.2008.彩色图像超复数整体处理理论及应用研究.[博士学位论文].上海:复旦大学
金良海.2008.彩色图像滤波与基于四元数的彩色图像处理方法.[博士学位论文].武汉:华中科技大学
康彬.2011.基于Nios II软核的PCNN图像分割系统设计.[硕士学位论文].兰州:兰州大学
李甲.2010.基于学习的视觉显著计算.[博士学位论文].北京:中国科学院研究生院
刘勍,马义德,钱志柏.2005.一种基于交叉熵的改进型PCNN图像自动分割新方法.中国图象图形学报,10(5):579~584
刘勍,许录平,马义德,等.2010b.一种超模糊熵ULPCNN图像自动分割新方法.西安电子科技大学学报,37(5):817~824
刘勍,许录平,马义德,苏哲.2010a.基于互信息改进型脉冲耦合神经网络多值图像分割.光子学报,39(5):923~927
刘勍,应隽,马小姝.2011.三代人工神经网络发展及其哲学思考.第13届中国系统仿真技术及其应用学术年会论文集,13:1183~1186
刘勍.2011.基于脉冲耦合神经网络的图像处理若干问题研究.[博士学位论文].西安:西安电子科技大学
刘晓玲.2004.视觉神经生理学.北京：人民卫生出版社
陆科.2008.基于PCNN的图像分割算法研究.[硕士学位论文].沈阳:东北大学
罗四维.2004.大规模人工神经网络理论基础.北京:清华大学出版社,北方交通大学出版社:5~175
罗四维.2006.视觉感知系统信息处理理论.北京:电子工业出版社:1~86
罗彤.2008.视觉感知启发的图像分割系统研究.[博士学位论文].杭州:浙江大学
马奇.2009.视觉注意和行为认知模型及其应用.[硕士学位论文].上海:复旦大学
马义德,戴若兰,李廉,吴承虎.2002a.生物细胞图像分割技术的进展.生物医学工程学杂志,19(3):487~492
马义德,戴若兰,李廉.2002b.一种基于脉冲耦合神经网络和图像熵的自动图像分割方法.通信学报,23(1):46~51
马义德,李廉,绽琨,王兆滨.2008.脉冲耦合神经网络与数字图像处理.北京:科学出版社:1~270
马义德,齐春亮.2006.基于遗传算法的脉冲耦合神经网络自动系统研究.系统仿真学报,18(3):722~724
聂仁灿,周冬明,赵东风.2008.基于Unit-Linking PCNN和图像熵的图像分割新方法.系统仿真学报,20(1):222~227
任延涛,韩玉昌,隋雪.2006.视觉搜索过程中的眼跳及其机制.心理科学进展,14(3):340~345
邵俊明.2008.基于感兴趣区域的图像语义获取方法研究.[硕士学位论文].杨凌:西北农林科技大学
沈兰荪,张菁,李晓光.2008.图像检索与压缩域处理技术的研究.北京:人民邮电出版社:1~113
石美红,张军英,朱欣娟,张晓滨.2002.基于PCNN的图像高斯噪声滤波的方法.计算机应用,26(2):1~4
王成.2010.基于脉冲耦合神经网络的感兴趣区图像检测方法及应用.[博士学位论文].广州:华南理工大学
王新.2010. PCNN混沌特性与硬件实现研究.[硕士学位论文].兰州:兰州大学
卫立波.2010.基于图谱的视觉注意模型的研究.[硕士学位论文].重庆:重庆大学
魏伟一.2011.非均匀光照图像的灰度校正与分割技术研究.[博士学位论文].兰州:兰州理工大学
夏辉,穆希辉,马振书,兰箭,杜峰坡.2007.基于最大交叉熵的PCNN简化模型在图像分割中的应用.军械工程学院学报,19(1):58~61
刑燕.2009.四元数及其在图形图像处理中的应用研究.[博士学位论文].合肥:合肥工业大学
徐晓军,李建华,王孙安,郭咏虹.2004.基于最优家族遗传算法的改进二维熵图像分割.西安交通大学学报,38(11):1182~1185
许新征,丁世飞,史忠植,贾伟宽.2010.图像分割的新理论和新方法.电子学报,38(2A):76~82
杨惠娟.2010.遥感图像超复数融合及其评价方法研究.[博士学位论文].上海:复旦大学
姚畅.2009.眼底图像分割方法的研究及其应用.[博士学位论文].北京:北方交通大学
叶佳.2007.彩色图像的超复数整体检索和客观质量评估的研究.[硕士学位论文].上海:复旦大学
余映.2010.视觉注意计算模型设计及其应用研究.[博士学位论文].上海:复旦大学
张菁.2008.基于视觉感知的个性化图像检索的初步研究.[博士学位论文].北京:北京工业大学
张永梅.2011.基于生物视觉机制的图像感兴趣区域提取研究.[硕士学位论文].杨凌:西北农林科技大学
张煜东,吴乐南.2008.基于二维Tsallis熵的改进PCNN图像分割.东南大学学报,38(4):579~583
章毓晋.2007.图像工程:图像分析.第二版.北京:清华大学出版社:75~91
赵磊,贾振红,覃锡忠,杨杰,庞韶宁.2012.基于灰色关联分析与RBF的图像分割算法.计算机工程,38(1):225~226
郑征.2006.相容粒度空间模型及其应用研究.[博士学位论文].北京:中国科学院计算技术研究所
Achanta R, Estrada F, Wils P, Süsstrunk S.2009. Frequency tuned Salient Region Detection.Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition,1-4:1597~1604.
Achanta R, Süsstrunk S.2010. Saliency detection using maximum symmetric surround. Proceedingsof IEEE International Conference on Image Processing,10:2653~2656
Alpert S, Galun M, Basri R, Brandt A,2007. Image segmentation by probabilistic bottom-upaggregation and cue integration. Proceedings of the IEEE Conference on Computer Vision and PatternRecognition,2007:1~8
Athanasiadis T, Mylonas P, Avrithis Y, Kollias S.2007. Semantic image segmentation and objectlabeling. IEEE Transactions on Circuits and Systems for Video Technology,17(3):298~312
Balasubramanian V, Kimber D, Berry M.2001. Metabolically efficient information processing.Neural Computation,13(4):799~815
Berg H, Olsson R, Lindbladb T, Chilo J.2008. Automatic design of pulse coupled neurons for imagesegmentation. Neurocomputing,71(10-12):1980~1983
Bi Y W, Qiu T S, Li X B, Guo Y.2004. Automatic image segmentation based on a simplified pulsecoupled neural network. Lecture Notes in Computer Science,3174:199~211
Bruce N, Tsotsos J K.2006. Saliency Based on Information Maximization. Proceedings of Advancesin Neural Information Processing Systems,18,155~162
Bruce N, Tsotsos J K.2007a. An information theoretic model of saliency and visual search.Proceedings of WAPCV,171~183
Bruce N, Tsotsos J K.2007b. Attention based on information maximization. Journal of Vision,7(9):950~950
Carmi R, Itti L.2006a. The role of memory in guiding attention during natural vision. Journal ofVision,6(9):898~914
Carmi R, Itti L.2006b. Visual causes versus correlates of attentional selection in dynamic scenes.Vision Research,46(26):4333~4325
Celik T, Tjahjadi T.2010. Unsupervised colour image segmentation using dual-tree complex wavelettransform. Computer Vision and Image Understanding,114(7):813~826
Chaira T, Ray A K.2003. Segmentation using fuzzy divergence. Pattern Recognition Letters,24(12):1837~1844
Chen K, Wang D L, Liu X W.2000. Weight adaptation and oscillatory correlation for imagesegmentaion. IEEE Transactions on Neural Networks,11(5):1106~1123
Chen Y L, PARK S-K, Ma Y D, Ala R.2011. A new automatic parameter setting method of asimplified PCNN for image segmentation. IEEE Trans. Neural Networks,22(6):880~892
Cui X, Liu Q, Metaxas D.2009. Temporal spectral residual: fast motion saliency detection.Proceedings of ACM International Conference on Multimedia,617~620
Daugman J G.1985. Uncertainty relations for resolution in space, spatial frequency, and orientationoptimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A,2:1160~1169
Dekruger D, Hunt B R.1994. Image processing and neural networks for recognition of cartographicarea feature. Pattern Recognition,27(4):461~483
Dong Y Z, Zhou X D, Wang C J, Xie W G.2004. Application of soft mathematical morphology inimage segmentation of IR ship image. Proceedings of the International Conference on Signal ProcessingProceedings,7:729~732
Draper B, Lionelle A.2003. Evaluation of selective attention under similarity transforms. Procedingsof Workshop on Attention and Performance in Computer Vision,2003:31~38
Duncan J, Humphreys G W.1989. Visual search and stimulus similarity. Psychological Review,96(3):433~458
Duncan J.1989. Boundary conditions on parallel search in human vision. Perception,(18):457~469
Eckhorn R, Bauer R, Jordan W, Brosch M, Kruse W, Munk M, Reitboeck H J.1988. Coherentoscillations: a mechanism of feature linking in the visual cortex, multiple electrode and correlation analysesin the Cat. Biological Cybernetics,12(60):121~130
Eckhorn R, Frien A, Bauer R, Woelbern T, Kehr H.1993. High frequency (60-90Hz) oscillations inprimary visual cortex of awake monkey. NeuroReport,4(3):243~246
Eckhorn R, Reitboeck H J, Arndt M, Dicke P.1989. Feature linking via stimulus-evoked oscillations:experimental results from cat visual cortex and functional implications from a network model. Proceedingsof International Joint Conference on Neural Networks,6(1):723~730
Eckhorn R, Reitboeck H J, Arndt M, Dicke P.1990. Feature linking via synchronization amongdistributed assemblies: simulation of results from cat cortex. Neural Computation,2(3):293~307
Egly R, Driver J, Rafal R D.1994. Shifting visual attention between objects and locations: evidencefrom normal and parietal lesion subjects. Journal of Experimental Psychology General,123:161~177
Einh user W, Kruse W, Hoffmann K-P, K nig P.2006. Differences of monkey and human overtattention under natural conditions. Vision Research,46(8-9):1194~1209
Ekblad U, Kinser J M.2004a. The oretical foundation of the intersecting cortical model and its usefor change detection of aircraft, cars and nuclear explosion tests. Signal Processing,84:1131~1146
Ekblad U, Kinserh J M, Atmer J, Zetterlund N.2004c. Image information content and extractiontechniques. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers,Detectors and Associated Equipment,525(1-2):397~401
Ekbld U, Kinser J M, Atmer J, Zetterlund N.2004b. The intersecting cortical model in imageprocessing. Nuclear Instruments and Methods in Physics Research, Section A,525(1-2):392~396
Ell T, Sangwin S.2007. HyPereomplex Fourier transforms of color images. IEEE Transactions onImage Processing,16(1):22~35
Eriksen C W, James J D S.1986. Visual attention within and around the field of focal attention: azoom lens model. Perception and Psychophysics,40:225~240
Fay M P, Proschan M A.2010. Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesistests and multiple interpretations of decision rules. Statistics Surveys,4:1~39
Feng S H, Xu D, Yang X, Wu A M.2005. A Novel Region-based Image Retrieval Algorithm UsingSelective Visual Attention Model. Proceedings of ACIVS,235~242
FitzHugh R.1961. Impulses and physiological states in theoretical models of nerve membrane.Biophysics J, l:445~466
Frien A, Eckhorn R, Bauer R, Woelbern T, Kehr H.1994. Stimulus-specific fast oscillations at zerophase between visual areas V1and V2of awake monkey. NeuroReport,5(17):2273~2277
Fu H, Chi Z, Feng D.2006. Attention-driven Image Interpretation with Application to ImageRetrieval. Pattern Recognition,39(7):1604~1621
Fu J C, Chen C C, Chai J W, Wong S T C, Li I C.2010. Image segmentation by EM-based adaptivepulse coupled neural networks in brain magnetic resonance imaging. Computerized Medical Imaging andGraphics,34(4):308~320
Gao D, Mahadevan V, Vasconcelos N.2007. The discriminant center-surround hypothesis forbottom-up saliency. Proceedings of Advances in Neural Information Processing Systems,20:497~504
Gray C M, K nig P, Engel A K, Singer W.1989. Oscillatory responses in cat visual cortex exhibitinter-columnar synchronization which reflects global stimulus properties. Nature,338:334~337
Grigorescu C, Petkov N, Westenberg M A.2003. Contour detection based on nonclassical receptivefield inhibition. IEEE Trans on Image Processing,12(7):729~739
Guo C L, Ma Q, Zhang L M.2008. Spatio-temporal saliency detection using phase spectrum ofquaternion Fourier transform. Proceedings of Computer Vision and Pattern Recognition,1~8
Guo C L, Zhang L M.2010. A novel multiresolution spatiotemporal saliency detection model and itsapplications in image and video compression. IEEE Trans. Image Process.,19(1)185~198
Harel J, Koch C, Perona P.2006. Graph-based visual saliency. Proceedings of Advances in NeuralInformation Processing Systems,19:545~552
Hateren J V.1992. Real and optimal neural images in early vision. Nature,360(6399):68~70
He D J, Liu R S, Song H B.2011b. Closed salient edge extraction based on visual attentionmechanism. Applied Mechanics and Materials,2011(58-60)1972~1978
He D J, Liu S W, Liang X H, Cai C.2011a. Improved Saliency Toolbox/Itti Model for Region ofInterest Extraction. Optical Engineering,50(9):097202-1~097202-13
He D J, Shao J M, Gen N, Yang Q L.2007. A model for image categorization based on biologicalvisual mechanism. New Zealand Journal of Agricultural Research,50:781~787
Healey C G.2009. Perception in visualization.http://www.csc.ncsu.edu/faculty/healey/PP/index.html#McC_CG:87[2012-02-28]
Hodgkin A L, Huxley A E.1952. A quantitative description of membrane current and its applicationto conduction and excitation in nerve. Journal of Physiology,117:500~544
Hou X, Zhang L.2007. Saliency detection: A spectral residual approach. Proceedings of ComputerVision and Pattern Recognition,2007:1~8
Hou X, Zhang L.2008. Dynamic visual attention: searching for coding length increments.Proceedings of the Neural Information Processing Systems,21:681~688
Hou X.2011. Dynamic Visual Attention. http://www.klab.caltech.edu/~xhou/[2011-12-28]
Hu Y, Rajian D, Chia L T.2005. Adaptive local context suppression of multiple cues for salientvisual attention detection. Proceedings of IEEE International Conf Multimedia and Expo,2005:346-349
Huang T-H, Cheng K-Y, Chuang Y-Y.2009. A collaborative benchmark for region of interestdetection algorithms. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2009:296~303
Hubel D, Torsten N W.2004. Brain and visual perception. USA: Oxford University Press:1~217
Hurvich L M, Jameson D.1957. An opponent-process theory of color vision. Psychological Review,64(6):384~404
ILab.2002. iLab neuromorphic vision C++toolkit. http://ilab.usc.edu/toolkit/[2012-02-18]
Ishai A, Ungerleider L G, Martin A, Martin A, Schouten J L, Haxby J.1999. Distributedrepresentation of object in the human ventral visual pathway. Proceedings of the National Academy ofSciences,96:9379~9384
Itti L, Baldi P.2005. A principled approach to detecting surprising events in video. Proceedings ofIEEE Conference on Computer Vision and Pattern Recognition,1:631~637
Itti L, Baldi P.2006. Bayisian surprise attracts human attention. Proceedings of Neural InformationProcessing Systems,19:547~554
Itti L, Koch C, Niebur E.1998. A model of saliency-based visual attention for rapid scene analysis.IEEE Trans on Pattern Analysis and Machine Intelligence,20(11):1254~1259
Itti L, Koch C.2000. A saliency-based search mechanism for overt and covert shifts of visualattention. Vision Research,40(10-12):1489~1506
Itti L, Koch C.2001a. Feature combination strategies for saliency-based visual attention systems.Journal of Electronic Imaging,10(1):161~169
Itti L, Koch C.2001b. Computational modeling of visual attention. Nature Reviews Neuroscience,2(3):194~203
Itti L.2000. Models of bottom-up and top-down visual attention.[PhD Dissertation]. Pasadena:California Institute of Technology
Itti L.2001. Visual attention and target detection in cluttered natural scenes. Optical Engineering,40(9):1784~1793
Itti L.2004. Automatic forveation for video compression using a neurobiological model of visualattention. IEEE Transactions on Image Processing,13(10):1304~1318
Itti L.2008. CRCNS data sharing: eye movements during free-viewing of natural videos. Proceedingsof Collaborative Research in Computational Neuroscience Annual Meeting,2008
James W.1981. The Principles of Psychology. NewYork: Holt:1~98
Johnson J L, Padgett M L.1999. PCNN models and applications. IEEE Transactions on NeuralNetworks,10(3):480~498
Johnson J L, Pedgett M L, Friday W O.1996. Multiscale image factorization. Proceedings of IEEEInternational Conf on Neural networks,1996:690~693
Johnson J L.1994. Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensitysignal invariance for images. Applied Optics,33(26):6239~6253
Judd T, Ehinger K. Durand F, Torralba A. Learning to predict where humans look. Proceedings ofIEEE International Conference on Computer Vision,2009:2106~2113
Julész B, Bergen J R.1983. Textons, the fundamental elements in preattentive vision and theperception of textures. Bell System Technical Journal,62(6):1619~1645
Julész B.1981. A theory of preattentive texture discrimination based on first-order statistics oftextons. Biological Cybernetics,41:131~138
Julész B.1981. Textons, the elements of texture perception, and their interactions. Nature,290:91~97
Julész B.1984. A brief outline of the texton theory of human vision. Trends in Neuroscience,7(2):41~45
Kastner S, Ungerleider L G.2000. Mechanisms of visual attention in the human cortex. Annu RevNeurosci,23:315~341
Kinser J M.2001. Image signatures: classification and ontology. Proceedings of the4thInternationalConference on Computer Graphics and Imaging,1~6
Kreiter A K, Singer W.1992. Oscillatory neuronal responses in the visual cortex of the awakemacaque monkey. European J Neurosci,4:369~375
Kuntimad G, Ranganath H S.1999. Perfect image segmentation using pulse coupled neural networks.IEEE Trans. Neural Networks,10(3):591~598
Leung C C, Chen W F, Kwok P C K, Chan F H Y.2003. Brain tumor boundary detection in MRimage with generalized fuzzy operator. Proceedings of IEEE International Conference on ImageProcessing,2:1057~1060
Leventhal A G.1991. The Neural Basis of Visual Function, Vision and Visual Dysfunction. BocaRaton, FL: CRC Press
Li F, Peng J X, Zheng X J.2004. Object-Based and Semantic Image Segmentation Using MRF.EURASIP Journal on Applied Signal Processing,6:833~840
Li H, Bai Z Y.2008. A new PCNN-based method for segmentation of SAR images. Proceedings ofIntl. Conf. on Control, Automation, Robotics and Vision,10:1635~1639
Li J, Tian Y H, Huang T J, Gao W. A dataset and evalutation methodology for visual saliency invideo. Proceedings of IEEE International Conference on Multimedia and Expo,2009:442-445
Li J, Wang J Z.2003. Automatic linguistic indexing of pictures by a statistical modeling approach.IEEE Transactions on Pattern Analysis and Machine Intelligence,25(9):1075~1088
Li M, Wu Y, Zhang Q.2009. SAR image segmentation based on mixture context and wavelethidden-class-label Markov random field. Computers&Mathematics with Applications,57(6):961~969
Li S, Lee M C.2007. Efficient spatiotemporal-attention-driven shot matching. Proceedings of ACMInternational Conference on Multimedia,2007:178~187
Li Z R, Hayward R, Zhang J L, Liu Y E, Walker R.2009. Towards Automatic Tree Crown Detectionand Delineation in Spectral Feature Spaceusing PCNN and Morphological Reconstruction. Proceedings ofIEEE International Conference on Image Processing.2009:1705~1708
Lin Q W, Gui F.2008. Fractal dimension and neural network based image segmentation technique.Proceedings of SPIE Europe Photonics Europe,2008:70010L-70010L-8
Lindblad T, Kinser J M.2005a. Image Processing Using Pulse-Coupled Neural Networks. New York:Springer-Verlag:8~141
Lindblad T, Kinser J M.2005b.脉冲耦合神经网络图像处理.第二版.马义德,绽琨,王兆滨译.2008.北京:高等教育出版社:7~120
Liu S W, He D J; Liang X H.2012. An Improved Hybrid Model for Automatic Salient RegionDetection. IEEE Signal Processing Letters,19(4):207~210
Liu T, Sun J, Zheng N-N, Tang X O, Shum H-Y.2007. Learning to Detect A Salient Object.Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition,2007:1~8
Lowe D G.2004. Distinctive image features from scale-invariant keypoints. International Journal ofComputer Vision,60(2):91~110
Ma Y D, Liu Q, Qian Z B.2004. Automated image segmentation using improved PCNN model basedon cross-entropy. Proceedings of IEEE International Symposium on Intelligent Multimedia, Video andSpeech Processing,11(12):743~746
Maass W.1997. Networks of spiking neurons: the third generation of neural network models. NeuralNetworks,10(9):1659~1671
Marques O, Mayron L M, Borba G B, Gamba H R.2007. An Attention-driven Model for GroupingSimilar Images with Image Retrieval Applications. EURASIP Journal on Advances in Signal Processing,Special Issue on Image Perception,2007(1):116~116
Mayron L M.2008. Image Retrieval using Visual Attention.[PhD thesis]. Boca Raton: FloridaAtlantic University
Mcculloch W S, Pitts W.1943. A logical calculus of the ideas immanent in nervous activity. Bulletinof Mathematical Biophysics,5:115~133
Müller H J, Humphreys G W, Quinlan P T, Riddoch M J.1990. Combined-feature coding in the formdomain. In: Brogan D. Visual Search. Vol1. London: Taylor and Francis:47~55
Navalpakkam V, Itti L.2005. Modeling the influence of task on attention. Vision Research,45(2):205~231
Pagare R, Shinde A.2012. A study on image annotation techniques. International Journal ofComputer Applications,37(6):42~45
Pardo A.2002. Semantic image segmentation using morphological tools. Proceedings of IEEEInternational Conference on Image Processing,2:745~748
Petkov N, Kruizinga P.1997. Computational models of visual neurons specialised in the detection ofperiodic and aperiodic oriented visual stimuli: bar and grating cells. Biological Cybernetics,76(2):83~96
Postle B R, D'Esposito M.1999.“What-Then-Where” in visual working memory: an event-relatedfMRI study. J Cogn Neurosci,11(6):585~597
Quinlan P T, Humphreys G W.1987. Visual search for targets defined by combinations of color,shape, and size: an examination of task constraints on feature and conjuction searches. Perception&Psychophysics,41(5):455~472
Rao R, Ballard D.1999. Predictive coding in the visual cortex: a functional interpretation of someextraclassical receptive-field effects. Nature Neuroscience,2:79~87
Richards W, Seung H S, Pickard G.2006. Neural voting machines. Neural Networks,19(8):1161~1167
Rodieck R W, Stone J J.1965. Analysis of receptive fields of cat retina ganglion cells. Journal ofNeurophysiology,28:833~849
Rolls E T, Deco G.2006. Attention in natural scenes: neurophysiologic and computational bases.Neural Networks,19:1383~1394
Rosin P L.2009. A simple method for detecting salient regions. Pattern Recognition,42(11):2363~2371
Rout S, Srivastava S, Majumdar J.1998. Multi modal image segmentation using a modified Hopfieldneural network. Pattern Recognition,31(6):743~750
Rumelhart D E, Mcclelland J L.1986. Parallel distributed processing: explorations in themicrostructure of cognition. psychological and Biological Models. Boston: MIT Press
Russell B C, Torralba A, Murphy K P, Freeman W T.2008. Labelme: a database and web-based toolfor image annotation. International Journal of Computer Vision,77(1-3):157~173
Rybak I A, Gusakova V I, Golovan A V, Podladchikova L N, Shevtsova N A.1998. A model ofattention-guided visual perception and recognition. Vision Research,38:2387~2400
Sawilowsky S.2005. Misconceptions leading to choosing the t test over the Wilcoxon Mann-WhitneyU test for shift in location parameter. Journal of Modern Applied Statistical Methods,4(2):598~600
Schiller P H, Logothetis N k, Charles E R.1991. Parallel pathways in the visual system: their role inperception at isoluminance. Journal of Neuropsychologia,29:433~441
Serre T, Oliva A, Poggio T.2007b. A feed-forward architecture accounts for rapid categorization.Proceedings of the National Academy of Science,104(15):6424~6429
Serre T, Wolf L, Poggio T.2007a. Robust object recognition with cortex-like mechanisms. IEEETransactions on Pattern Analysis and Machine Intelligence,29(3):411~426
Shi J, Pan Z K, Wei W B.2009. An innovative variational level set model for multiphase imagesegmentation. Proceedings of the International Conference on Multimedia and Ubiquitous Engineering,3:41~44
Shi M H, Jiang S S, Wang H R, Xu B G.2007. A Simplified pulse-coupled neural network foradaptive segmentation of fabric defects. Machine Vision and Applications,20(2):131~138
Sofou A, Maragos P.2008. Generalized flooding and multicue PDE-based image segmentation. IEEETrans. on Image Processing,17(3):364~376
Sun Y R, Fisher R.2003. Object-based Visual Attention for Computer Vision. Artificial Intelligence,146(1):77~123
Tatler B W, Baddeley R J, Gilchrist I D.2005. Visual correlates of fixation selection: effects of scaleand time. Vision Research,45:643~659
Theeuwes J, Kooi F L.1994. Parallel search for a conjunction of contrast polarity and shape. VisionResearch,34(22):3013~3016
Treisman A, Gelade G.1980. A feature-integration theory of attention. Cognitive Psychology,12(1):97~136
Treisman A, Gormican S.1988. Feature analysis in early vision: evidence from search asymmetries.Psychological Review,95(1):15~48
Treisman A, Souther J.1986. Illusory words: the roles of attention and top-down constraints inconjoining letters to form words. Journal of Experimental Psychology: Human Perception&Performance,12:107~141
Treisman A.1985. Preattentive processing in vision. Computer Vision, Graphics and ImageProcessing,31:156~177
Treisman A.1991. Search, similarity, and integration of features between and within dimensions.Journal of Experimental Psychology: Human Perception&Performance,17(3):652~676
Tsotsos J K, Culhane S M, Wai W Y K, Lai Y, Davis N, Nuflo F.1995. Modeling visual-attention viaselective tuning. Artificial Intelligence,78(1-2):507-545
Vikram T N, Tscherepanow M, Wrede B. A random center surround bottom up visual attentionmodel useful for salient region detection. Proceedings of IEEE Workshop on Applications of ComputerVision,2011:166~173
Vilarino D L, Brea V M, Cabello D.1998. Discrete time CNN for image segmentation by activecontours. Pattern Recognition Letters,19(8):721~734
Wainwright M.1999. Visual adaptation as optimal information transmission. Vision Research,39(23):3960~3974
Walther D B, Koch C.2007. Attention in hierarchical models of object recognition. Progress in BrainResearch,165(3):57~78
Walther D, Koch C.2006. Modeling attention to salient proto-objecets. Neural NetWorks,19:1395~1407
Walther D.2006a. Interactions of visual attention and object recognition: computational modeling,algorithms, and psychophysics.[PhD Dissertation]. Pasadena: California Institute of Technology
Walther D.2006b. SaliencyToolbox. http://www.saliencytoolbox.net/index.html [2009-09-25]
Wang D L, Terman D.1997. Image segmentation based on oscillatory correlation. NeuralComputation,9:805~836
Wang D L.1999. Object selection based on oscillatory correlation. Neural Network,12:579~592
Wang G, He G J.2010. Human visual system based processing for high resolution remote sensingimage segmentation. Proceedings of the International Conference on Signal Processing Systems,2:474~478
Wang H Q, Ji C Y, Gu B X, Tian G Z,2010. A simplified pulse-coupled neural network forcucumber image segmentation. Proceedings of International Conference on Computational andInformation Sciences,2010:1053~1057
Wang J Z, Li J, Wiederhold G.2001. SIMPLIcity: semantics-sensitive Integrated Matching forPicture LIbraries. IEEE Trans on Pattern Analysis and Machine Intelligence,23(9):947~963
Wang W, Wang Y Z, Huang Q M, Gao W.2008. Measuring visual saliency by site entropy rate.Proceedings of IEEE Conference on Computer Vision and Pattern Recongnition,2008:2368~2375
Wang Y, Adaii T, Kung S Y.1998. Quantification and segmentation of brain tissues from MR imagesa probabilistic neural networks approach. IEEE Transactions on Image Processing,7(8):1~12
Wang Z B, Ma Y D, Cheng F Y, Yang L Z.2010. Review of pulse-coupled neural networks. Imageand Vision Computing,28,5~13
Wang Z, Li B.2008. A two-stage approach to saliency detection in images. Proceedings of IEEEConference on Acoustics, Speech and Signal Processing,2008:965~968
Ware C.2000. Information visualization: perception for design. San Francisco: Morgan KaufmannPublishers:1~16
Wolfe J M, Cave K R, Franzel S L.1989. Guided Search: an alternative to the feature integrationmodel for visual search. Journal of Experimental Psychology: Human Perception&Performance,15(3):419~433
Wolfe J M, Cave K R.1989. Deploying visual attention: the Guided Search model. In Troscianko T,Blake A. AI and the Eye. Chichester: John Wiley&Sons, Inc:79~103
Wolfe J M, Franzel S L.1988. Binocularity and visual search. Perception&Psychophysics,44:81~93
Wolfe J M, Friedman-Hill S R, Stewart M I, O'Connell K M.1992. The role of categorization invisual search for orientation. Journal of Experimental Psychology: Human Perception&Performance,18(1):34~49
Wolfe J M, Horowitz T S.2004. What attributes guide the deployment of visual attention and how dothey do it? Nature Reviews Neuroscience,5(6),495~501
Wolfe J M, Klempen N, Dahlen K.2000. Postattentive vision. Journal of Experimental Psychology:Human Perception&Performance,26(2):693~716
Wolfe J M, Yu K P, Stewart M I, Shorter A D, Friedman-Hill S R, Cave K R.1990. Limitations onthe parallel guidance of visual search: color x color and orientation x orientation conjunctions. Journal ofExperimental Psychology: Human Perception&Performance,16(4):879~892
Wolfe J M.1994. Guided search2.0: a revised model of guided seareh. Psychonomic Bulletin&Review,1(2):202~238
Xiao Z H, Shi J, Chang Q.2009. Automatic image segmentation algorithm based on PCNN and fuzzymutual information. Proceedings of IEEE Ninth International Conference on Computer and InformationTechnology,2009:241~245
Zeki S.1993. A Vision of the Brain. Oxford: Oxford Univ Press:26~79
Zhai Y, Shah M.2006. Visual attention detection in video sequences using spatiotemoral cues.Proceedings of ACM International Conference on Multimedia,2006:815~824
Zhang J, Zhuo L, Shen L S.2008. Regions of interest extraction based on visual attention model andwatershed segmentation. IEEE International Conf on Neural Networks&Signal Processing,8(10):375~378
Zhou Q, Ma L, Celenk M, Chelberg D.2005. Content-based image retrieval based on ROI detectionand relevance feedback. Multimedia Tools and Applications,27(11):251~281
飞思科技产品研发中心.2003. MATLAB6.5辅助图像处理.北京:电子工业出版社
高静静.2008.基于视觉注意模型的感兴趣区检测技术研究.[硕士学位论文].北京:北京工业大学
顾晓东.2005.单位脉冲耦合神经网络中若干理念及应用问题的研究.[博士后学位论文].上海：复旦大学
过晨雷.2008.注意力选择机制的研究:算法设计以及系统实现.[硕士学位论文].上海：复旦大学
韩力群.2006.人工神经网络教程.北京:北京邮电大学出版社:22~46
郝明非.2007.彩色图像超复数整体拼接及其质量评估的研究.[硕士学位论文].上海:复旦大学
何东健,耿楠,张义宽.2003.数字图像处理.西安:西安电子科技大学出版社:159~202
何伟,蒋加伏,齐琦.2009.基于粗糙集理论和神经网络的图像分割方法.计算机工程与应用,45(1):188~190
贺俊.2009.基于视觉注意机制的物体显著性研究.[硕士学位论文].上海:上海交通大学
纪永刚.2006.基于微波图像的辽东弯海冰典型要素信息提取.[博士学位论文].北京:中国科学院研究生院
贾云得.2000.机器视觉.北京:科学出版社:15~26
江淑红.2008.彩色图像超复数整体处理理论及应用研究.[博士学位论文].上海:复旦大学
金良海.2008.彩色图像滤波与基于四元数的彩色图像处理方法.[博士学位论文].武汉:华中科技大学
康彬.2011.基于Nios II软核的PCNN图像分割系统设计.[硕士学位论文].兰州:兰州大学
李甲.2010.基于学习的视觉显著计算.[博士学位论文].北京:中国科学院研究生院
刘勍,马义德,钱志柏.2005.一种基于交叉熵的改进型PCNN图像自动分割新方法.中国图象图形学报,10(5):579~584
刘勍,许录平,马义德,等.2010b.一种超模糊熵ULPCNN图像自动分割新方法.西安电子科技大学学报,37(5):817~824
刘勍,许录平,马义德,苏哲.2010a.基于互信息改进型脉冲耦合神经网络多值图像分割.光子学报,39(5):923~927
刘勍,应隽,马小姝.2011.三代人工神经网络发展及其哲学思考.第13届中国系统仿真技术及其应用学术年会论文集,13:1183~1186
刘勍.2011.基于脉冲耦合神经网络的图像处理若干问题研究.[博士学位论文].西安:西安电子科技大学
刘晓玲.2004.视觉神经生理学.北京：人民卫生出版社
陆科.2008.基于PCNN的图像分割算法研究.[硕士学位论文].沈阳:东北大学
罗四维.2004.大规模人工神经网络理论基础.北京:清华大学出版社,北方交通大学出版社:5~175
罗四维.2006.视觉感知系统信息处理理论.北京:电子工业出版社:1~86
罗彤.2008.视觉感知启发的图像分割系统研究.[博士学位论文].杭州:浙江大学
马奇.2009.视觉注意和行为认知模型及其应用.[硕士学位论文].上海:复旦大学
马义德,戴若兰,李廉,吴承虎.2002a.生物细胞图像分割技术的进展.生物医学工程学杂志,19(3):487~492
马义德,戴若兰,李廉.2002b.一种基于脉冲耦合神经网络和图像熵的自动图像分割方法.通信学报,23(1):46~51
马义德,李廉,绽琨,王兆滨.2008.脉冲耦合神经网络与数字图像处理.北京:科学出版社:1~270
马义德,齐春亮.2006.基于遗传算法的脉冲耦合神经网络自动系统研究.系统仿真学报,18(3):722~724
聂仁灿,周冬明,赵东风.2008.基于Unit-Linking PCNN和图像熵的图像分割新方法.系统仿真学报,20(1):222~227
任延涛,韩玉昌,隋雪.2006.视觉搜索过程中的眼跳及其机制.心理科学进展,14(3):340~345
邵俊明.2008.基于感兴趣区域的图像语义获取方法研究.[硕士学位论文].杨凌:西北农林科技大学
沈兰荪,张菁,李晓光.2008.图像检索与压缩域处理技术的研究.北京:人民邮电出版社:1~113
石美红,张军英,朱欣娟,张晓滨.2002.基于PCNN的图像高斯噪声滤波的方法.计算机应用,26(2):1~4
王成.2010.基于脉冲耦合神经网络的感兴趣区图像检测方法及应用.[博士学位论文].广州:华南理工大学
王新.2010. PCNN混沌特性与硬件实现研究.[硕士学位论文].兰州:兰州大学
卫立波.2010.基于图谱的视觉注意模型的研究.[硕士学位论文].重庆:重庆大学
魏伟一.2011.非均匀光照图像的灰度校正与分割技术研究.[博士学位论文].兰州:兰州理工大学
夏辉,穆希辉,马振书,兰箭,杜峰坡.2007.基于最大交叉熵的PCNN简化模型在图像分割中的应用.军械工程学院学报,19(1):58~61
刑燕.2009.四元数及其在图形图像处理中的应用研究.[博士学位论文].合肥:合肥工业大学
徐晓军,李建华,王孙安,郭咏虹.2004.基于最优家族遗传算法的改进二维熵图像分割.西安交通大学学报,38(11):1182~1185
许新征,丁世飞,史忠植,贾伟宽.2010.图像分割的新理论和新方法.电子学报,38(2A):76~82
杨惠娟.2010.遥感图像超复数融合及其评价方法研究.[博士学位论文].上海:复旦大学
姚畅.2009.眼底图像分割方法的研究及其应用.[博士学位论文].北京:北方交通大学
叶佳.2007.彩色图像的超复数整体检索和客观质量评估的研究.[硕士学位论文].上海:复旦大学
余映.2010.视觉注意计算模型设计及其应用研究.[博士学位论文].上海:复旦大学
张菁.2008.基于视觉感知的个性化图像检索的初步研究.[博士学位论文].北京:北京工业大学
张永梅.2011.基于生物视觉机制的图像感兴趣区域提取研究.[硕士学位论文].杨凌:西北农林科技大学
张煜东,吴乐南.2008.基于二维Tsallis熵的改进PCNN图像分割.东南大学学报,38(4):579~583
章毓晋.2007.图像工程:图像分析.第二版.北京:清华大学出版社:75~91
赵磊,贾振红,覃锡忠,杨杰,庞韶宁.2012.基于灰色关联分析与RBF的图像分割算法.计算机工程,38(1):225~226
郑征.2006.相容粒度空间模型及其应用研究.[博士学位论文].北京:中国科学院计算技术研究所
Achanta R, Estrada F, Wils P, Süsstrunk S.2009. Frequency tuned Salient Region Detection.Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition,1-4:1597~1604.
Achanta R, Süsstrunk S.2010. Saliency detection using maximum symmetric surround. Proceedingsof IEEE International Conference on Image Processing,10:2653~2656
Alpert S, Galun M, Basri R, Brandt A,2007. Image segmentation by probabilistic bottom-upaggregation and cue integration. Proceedings of the IEEE Conference on Computer Vision and PatternRecognition,2007:1~8
Athanasiadis T, Mylonas P, Avrithis Y, Kollias S.2007. Semantic image segmentation and objectlabeling. IEEE Transactions on Circuits and Systems for Video Technology,17(3):298~312
Balasubramanian V, Kimber D, Berry M.2001. Metabolically efficient information processing.Neural Computation,13(4):799~815
Berg H, Olsson R, Lindbladb T, Chilo J.2008. Automatic design of pulse coupled neurons for imagesegmentation. Neurocomputing,71(10-12):1980~1983
Bi Y W, Qiu T S, Li X B, Guo Y.2004. Automatic image segmentation based on a simplified pulsecoupled neural network. Lecture Notes in Computer Science,3174:199~211
Bruce N, Tsotsos J K.2006. Saliency Based on Information Maximization. Proceedings of Advancesin Neural Information Processing Systems,18,155~162
Bruce N, Tsotsos J K.2007a. An information theoretic model of saliency and visual search.Proceedings of WAPCV,171~183
Bruce N, Tsotsos J K.2007b. Attention based on information maximization. Journal of Vision,7(9):950~950
Carmi R, Itti L.2006a. The role of memory in guiding attention during natural vision. Journal ofVision,6(9):898~914
Carmi R, Itti L.2006b. Visual causes versus correlates of attentional selection in dynamic scenes.Vision Research,46(26):4333~4325
Celik T, Tjahjadi T.2010. Unsupervised colour image segmentation using dual-tree complex wavelettransform. Computer Vision and Image Understanding,114(7):813~826
Chaira T, Ray A K.2003. Segmentation using fuzzy divergence. Pattern Recognition Letters,24(12):1837~1844
Chen K, Wang D L, Liu X W.2000. Weight adaptation and oscillatory correlation for imagesegmentaion. IEEE Transactions on Neural Networks,11(5):1106~1123
Chen Y L, PARK S-K, Ma Y D, Ala R.2011. A new automatic parameter setting method of asimplified PCNN for image segmentation. IEEE Trans. Neural Networks,22(6):880~892
Cui X, Liu Q, Metaxas D.2009. Temporal spectral residual: fast motion saliency detection.Proceedings of ACM International Conference on Multimedia,617~620
Daugman J G.1985. Uncertainty relations for resolution in space, spatial frequency, and orientationoptimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A,2:1160~1169
Dekruger D, Hunt B R.1994. Image processing and neural networks for recognition of cartographicarea feature. Pattern Recognition,27(4):461~483
Dong Y Z, Zhou X D, Wang C J, Xie W G.2004. Application of soft mathematical morphology inimage segmentation of IR ship image. Proceedings of the International Conference on Signal ProcessingProceedings,7:729~732
Draper B, Lionelle A.2003. Evaluation of selective attention under similarity transforms. Procedingsof Workshop on Attention and Performance in Computer Vision,2003:31~38
Duncan J, Humphreys G W.1989. Visual search and stimulus similarity. Psychological Review,96(3):433~458
Duncan J.1989. Boundary conditions on parallel search in human vision. Perception,(18):457~469
Eckhorn R, Bauer R, Jordan W, Brosch M, Kruse W, Munk M, Reitboeck H J.1988. Coherentoscillations: a mechanism of feature linking in the visual cortex, multiple electrode and correlation analysesin the Cat. Biological Cybernetics,12(60):121~130
Eckhorn R, Frien A, Bauer R, Woelbern T, Kehr H.1993. High frequency (60-90Hz) oscillations inprimary visual cortex of awake monkey. NeuroReport,4(3):243~246
Eckhorn R, Reitboeck H J, Arndt M, Dicke P.1989. Feature linking via stimulus-evoked oscillations:experimental results from cat visual cortex and functional implications from a network model. Proceedingsof International Joint Conference on Neural Networks,6(1):723~730
Eckhorn R, Reitboeck H J, Arndt M, Dicke P.1990. Feature linking via synchronization amongdistributed assemblies: simulation of results from cat cortex. Neural Computation,2(3):293~307
Egly R, Driver J, Rafal R D.1994. Shifting visual attention between objects and locations: evidencefrom normal and parietal lesion subjects. Journal of Experimental Psychology General,123:161~177
Einh user W, Kruse W, Hoffmann K-P, K nig P.2006. Differences of monkey and human overtattention under natural conditions. Vision Research,46(8-9):1194~1209
Ekblad U, Kinser J M.2004a. The oretical foundation of the intersecting cortical model and its usefor change detection of aircraft, cars and nuclear explosion tests. Signal Processing,84:1131~1146
Ekblad U, Kinserh J M, Atmer J, Zetterlund N.2004c. Image information content and extractiontechniques. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers,Detectors and Associated Equipment,525(1-2):397~401
Ekbld U, Kinser J M, Atmer J, Zetterlund N.2004b. The intersecting cortical model in imageprocessing. Nuclear Instruments and Methods in Physics Research, Section A,525(1-2):392~396
Ell T, Sangwin S.2007. HyPereomplex Fourier transforms of color images. IEEE Transactions onImage Processing,16(1):22~35
Eriksen C W, James J D S.1986. Visual attention within and around the field of focal attention: azoom lens model. Perception and Psychophysics,40:225~240
Fay M P, Proschan M A.2010. Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesistests and multiple interpretations of decision rules. Statistics Surveys,4:1~39
Feng S H, Xu D, Yang X, Wu A M.2005. A Novel Region-based Image Retrieval Algorithm UsingSelective Visual Attention Model. Proceedings of ACIVS,235~242
FitzHugh R.1961. Impulses and physiological states in theoretical models of nerve membrane.Biophysics J, l:445~466
Frien A, Eckhorn R, Bauer R, Woelbern T, Kehr H.1994. Stimulus-specific fast oscillations at zerophase between visual areas V1and V2of awake monkey. NeuroReport,5(17):2273~2277
Fu H, Chi Z, Feng D.2006. Attention-driven Image Interpretation with Application to ImageRetrieval. Pattern Recognition,39(7):1604~1621
Fu J C, Chen C C, Chai J W, Wong S T C, Li I C.2010. Image segmentation by EM-based adaptivepulse coupled neural networks in brain magnetic resonance imaging. Computerized Medical Imaging andGraphics,34(4):308~320
Gao D, Mahadevan V, Vasconcelos N.2007. The discriminant center-surround hypothesis forbottom-up saliency. Proceedings of Advances in Neural Information Processing Systems,20:497~504
Gray C M, K nig P, Engel A K, Singer W.1989. Oscillatory responses in cat visual cortex exhibitinter-columnar synchronization which reflects global stimulus properties. Nature,338:334~337
Grigorescu C, Petkov N, Westenberg M A.2003. Contour detection based on nonclassical receptivefield inhibition. IEEE Trans on Image Processing,12(7):729~739
Guo C L, Ma Q, Zhang L M.2008. Spatio-temporal saliency detection using phase spectrum ofquaternion Fourier transform. Proceedings of Computer Vision and Pattern Recognition,1~8
Guo C L, Zhang L M.2010. A novel multiresolution spatiotemporal saliency detection model and itsapplications in image and video compression. IEEE Trans. Image Process.,19(1)185~198
Harel J, Koch C, Perona P.2006. Graph-based visual saliency. Proceedings of Advances in NeuralInformation Processing Systems,19:545~552
Hateren J V.1992. Real and optimal neural images in early vision. Nature,360(6399):68~70
He D J, Liu R S, Song H B.2011b. Closed salient edge extraction based on visual attentionmechanism. Applied Mechanics and Materials,2011(58-60)1972~1978
He D J, Liu S W, Liang X H, Cai C.2011a. Improved Saliency Toolbox/Itti Model for Region ofInterest Extraction. Optical Engineering,50(9):097202-1~097202-13
He D J, Shao J M, Gen N, Yang Q L.2007. A model for image categorization based on biologicalvisual mechanism. New Zealand Journal of Agricultural Research,50:781~787
Healey C G.2009. Perception in visualization.http://www.csc.ncsu.edu/faculty/healey/PP/index.html#McC_CG:87[2012-02-28]
Hodgkin A L, Huxley A E.1952. A quantitative description of membrane current and its applicationto conduction and excitation in nerve. Journal of Physiology,117:500~544
Hou X, Zhang L.2007. Saliency detection: A spectral residual approach. Proceedings of ComputerVision and Pattern Recognition,2007:1~8
Hou X, Zhang L.2008. Dynamic visual attention: searching for coding length increments.Proceedings of the Neural Information Processing Systems,21:681~688
Hou X.2011. Dynamic Visual Attention. http://www.klab.caltech.edu/~xhou/[2011-12-28]
Hu Y, Rajian D, Chia L T.2005. Adaptive local context suppression of multiple cues for salientvisual attention detection. Proceedings of IEEE International Conf Multimedia and Expo,2005:346-349
Huang T-H, Cheng K-Y, Chuang Y-Y.2009. A collaborative benchmark for region of interestdetection algorithms. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2009:296~303
Hubel D, Torsten N W.2004. Brain and visual perception. USA: Oxford University Press:1~217
Hurvich L M, Jameson D.1957. An opponent-process theory of color vision. Psychological Review,64(6):384~404
ILab.2002. iLab neuromorphic vision C++toolkit. http://ilab.usc.edu/toolkit/[2012-02-18]
Ishai A, Ungerleider L G, Martin A, Martin A, Schouten J L, Haxby J.1999. Distributedrepresentation of object in the human ventral visual pathway. Proceedings of the National Academy ofSciences,96:9379~9384
Itti L, Baldi P.2005. A principled approach to detecting surprising events in video. Proceedings ofIEEE Conference on Computer Vision and Pattern Recognition,1:631~637
Itti L, Baldi P.2006. Bayisian surprise attracts human attention. Proceedings of Neural InformationProcessing Systems,19:547~554
Itti L, Koch C, Niebur E.1998. A model of saliency-based visual attention for rapid scene analysis.IEEE Trans on Pattern Analysis and Machine Intelligence,20(11):1254~1259
Itti L, Koch C.2000. A saliency-based search mechanism for overt and covert shifts of visualattention. Vision Research,40(10-12):1489~1506
Itti L, Koch C.2001a. Feature combination strategies for saliency-based visual attention systems.Journal of Electronic Imaging,10(1):161~169
Itti L, Koch C.2001b. Computational modeling of visual attention. Nature Reviews Neuroscience,2(3):194~203
Itti L.2000. Models of bottom-up and top-down visual attention.[PhD Dissertation]. Pasadena:California Institute of Technology
Itti L.2001. Visual attention and target detection in cluttered natural scenes. Optical Engineering,40(9):1784~1793
Itti L.2004. Automatic forveation for video compression using a neurobiological model of visualattention. IEEE Transactions on Image Processing,13(10):1304~1318
Itti L.2008. CRCNS data sharing: eye movements during free-viewing of natural videos. Proceedingsof Collaborative Research in Computational Neuroscience Annual Meeting,2008
James W.1981. The Principles of Psychology. NewYork: Holt:1~98
Johnson J L, Padgett M L.1999. PCNN models and applications. IEEE Transactions on NeuralNetworks,10(3):480~498
Johnson J L, Pedgett M L, Friday W O.1996. Multiscale image factorization. Proceedings of IEEEInternational Conf on Neural networks,1996:690~693
Johnson J L.1994. Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensitysignal invariance for images. Applied Optics,33(26):6239~6253
Judd T, Ehinger K. Durand F, Torralba A. Learning to predict where humans look. Proceedings ofIEEE International Conference on Computer Vision,2009:2106~2113
Julész B, Bergen J R.1983. Textons, the fundamental elements in preattentive vision and theperception of textures. Bell System Technical Journal,62(6):1619~1645
Julész B.1981. A theory of preattentive texture discrimination based on first-order statistics oftextons. Biological Cybernetics,41:131~138
Julész B.1981. Textons, the elements of texture perception, and their interactions. Nature,290:91~97
Julész B.1984. A brief outline of the texton theory of human vision. Trends in Neuroscience,7(2):41~45
Kastner S, Ungerleider L G.2000. Mechanisms of visual attention in the human cortex. Annu RevNeurosci,23:315~341
Kinser J M.2001. Image signatures: classification and ontology. Proceedings of the4thInternationalConference on Computer Graphics and Imaging,1~6
Kreiter A K, Singer W.1992. Oscillatory neuronal responses in the visual cortex of the awakemacaque monkey. European J Neurosci,4:369~375
Kuntimad G, Ranganath H S.1999. Perfect image segmentation using pulse coupled neural networks.IEEE Trans. Neural Networks,10(3):591~598
Leung C C, Chen W F, Kwok P C K, Chan F H Y.2003. Brain tumor boundary detection in MRimage with generalized fuzzy operator. Proceedings of IEEE International Conference on ImageProcessing,2:1057~1060
Leventhal A G.1991. The Neural Basis of Visual Function, Vision and Visual Dysfunction. BocaRaton, FL: CRC Press
Li F, Peng J X, Zheng X J.2004. Object-Based and Semantic Image Segmentation Using MRF.EURASIP Journal on Applied Signal Processing,6:833~840
Li H, Bai Z Y.2008. A new PCNN-based method for segmentation of SAR images. Proceedings ofIntl. Conf. on Control, Automation, Robotics and Vision,10:1635~1639
Li J, Tian Y H, Huang T J, Gao W. A dataset and evalutation methodology for visual saliency invideo. Proceedings of IEEE International Conference on Multimedia and Expo,2009:442-445
Li J, Wang J Z.2003. Automatic linguistic indexing of pictures by a statistical modeling approach.IEEE Transactions on Pattern Analysis and Machine Intelligence,25(9):1075~1088
Li M, Wu Y, Zhang Q.2009. SAR image segmentation based on mixture context and wavelethidden-class-label Markov random field. Computers&Mathematics with Applications,57(6):961~969
Li S, Lee M C.2007. Efficient spatiotemporal-attention-driven shot matching. Proceedings of ACMInternational Conference on Multimedia,2007:178~187
Li Z R, Hayward R, Zhang J L, Liu Y E, Walker R.2009. Towards Automatic Tree Crown Detectionand Delineation in Spectral Feature Spaceusing PCNN and Morphological Reconstruction. Proceedings ofIEEE International Conference on Image Processing.2009:1705~1708
Lin Q W, Gui F.2008. Fractal dimension and neural network based image segmentation technique.Proceedings of SPIE Europe Photonics Europe,2008:70010L-70010L-8
Lindblad T, Kinser J M.2005a. Image Processing Using Pulse-Coupled Neural Networks. New York:Springer-Verlag:8~141
Lindblad T, Kinser J M.2005b.脉冲耦合神经网络图像处理.第二版.马义德,绽琨,王兆滨译.2008.北京:高等教育出版社:7~120
Liu S W, He D J; Liang X H.2012. An Improved Hybrid Model for Automatic Salient RegionDetection. IEEE Signal Processing Letters,19(4):207~210
Liu T, Sun J, Zheng N-N, Tang X O, Shum H-Y.2007. Learning to Detect A Salient Object.Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition,2007:1~8
Lowe D G.2004. Distinctive image features from scale-invariant keypoints. International Journal ofComputer Vision,60(2):91~110
Ma Y D, Liu Q, Qian Z B.2004. Automated image segmentation using improved PCNN model basedon cross-entropy. Proceedings of IEEE International Symposium on Intelligent Multimedia, Video andSpeech Processing,11(12):743~746
Maass W.1997. Networks of spiking neurons: the third generation of neural network models. NeuralNetworks,10(9):1659~1671
Marques O, Mayron L M, Borba G B, Gamba H R.2007. An Attention-driven Model for GroupingSimilar Images with Image Retrieval Applications. EURASIP Journal on Advances in Signal Processing,Special Issue on Image Perception,2007(1):116~116
Mayron L M.2008. Image Retrieval using Visual Attention.[PhD thesis]. Boca Raton: FloridaAtlantic University
Mcculloch W S, Pitts W.1943. A logical calculus of the ideas immanent in nervous activity. Bulletinof Mathematical Biophysics,5:115~133
Müller H J, Humphreys G W, Quinlan P T, Riddoch M J.1990. Combined-feature coding in the formdomain. In: Brogan D. Visual Search. Vol1. London: Taylor and Francis:47~55
Navalpakkam V, Itti L.2005. Modeling the influence of task on attention. Vision Research,45(2):205~231
Pagare R, Shinde A.2012. A study on image annotation techniques. International Journal ofComputer Applications,37(6):42~45
Pardo A.2002. Semantic image segmentation using morphological tools. Proceedings of IEEEInternational Conference on Image Processing,2:745~748
Petkov N, Kruizinga P.1997. Computational models of visual neurons specialised in the detection ofperiodic and aperiodic oriented visual stimuli: bar and grating cells. Biological Cybernetics,76(2):83~96
Postle B R, D'Esposito M.1999.“What-Then-Where” in visual working memory: an event-relatedfMRI study. J Cogn Neurosci,11(6):585~597
Quinlan P T, Humphreys G W.1987. Visual search for targets defined by combinations of color,shape, and size: an examination of task constraints on feature and conjuction searches. Perception&Psychophysics,41(5):455~472
Rao R, Ballard D.1999. Predictive coding in the visual cortex: a functional interpretation of someextraclassical receptive-field effects. Nature Neuroscience,2:79~87
Richards W, Seung H S, Pickard G.2006. Neural voting machines. Neural Networks,19(8):1161~1167
Rodieck R W, Stone J J.1965. Analysis of receptive fields of cat retina ganglion cells. Journal ofNeurophysiology,28:833~849
Rolls E T, Deco G.2006. Attention in natural scenes: neurophysiologic and computational bases.Neural Networks,19:1383~1394
Rosin P L.2009. A simple method for detecting salient regions. Pattern Recognition,42(11):2363~2371
Rout S, Srivastava S, Majumdar J.1998. Multi modal image segmentation using a modified Hopfieldneural network. Pattern Recognition,31(6):743~750
Rumelhart D E, Mcclelland J L.1986. Parallel distributed processing: explorations in themicrostructure of cognition. psychological and Biological Models. Boston: MIT Press
Russell B C, Torralba A, Murphy K P, Freeman W T.2008. Labelme: a database and web-based toolfor image annotation. International Journal of Computer Vision,77(1-3):157~173
Rybak I A, Gusakova V I, Golovan A V, Podladchikova L N, Shevtsova N A.1998. A model ofattention-guided visual perception and recognition. Vision Research,38:2387~2400
Sawilowsky S.2005. Misconceptions leading to choosing the t test over the Wilcoxon Mann-WhitneyU test for shift in location parameter. Journal of Modern Applied Statistical Methods,4(2):598~600
Schiller P H, Logothetis N k, Charles E R.1991. Parallel pathways in the visual system: their role inperception at isoluminance. Journal of Neuropsychologia,29:433~441
Serre T, Oliva A, Poggio T.2007b. A feed-forward architecture accounts for rapid categorization.Proceedings of the National Academy of Science,104(15):6424~6429
Serre T, Wolf L, Poggio T.2007a. Robust object recognition with cortex-like mechanisms. IEEETransactions on Pattern Analysis and Machine Intelligence,29(3):411~426
Shi J, Pan Z K, Wei W B.2009. An innovative variational level set model for multiphase imagesegmentation. Proceedings of the International Conference on Multimedia and Ubiquitous Engineering,3:41~44
Shi M H, Jiang S S, Wang H R, Xu B G.2007. A Simplified pulse-coupled neural network foradaptive segmentation of fabric defects. Machine Vision and Applications,20(2):131~138
Sofou A, Maragos P.2008. Generalized flooding and multicue PDE-based image segmentation. IEEETrans. on Image Processing,17(3):364~376
Sun Y R, Fisher R.2003. Object-based Visual Attention for Computer Vision. Artificial Intelligence,146(1):77~123
Tatler B W, Baddeley R J, Gilchrist I D.2005. Visual correlates of fixation selection: effects of scaleand time. Vision Research,45:643~659
Theeuwes J, Kooi F L.1994. Parallel search for a conjunction of contrast polarity and shape. VisionResearch,34(22):3013~3016
Treisman A, Gelade G.1980. A feature-integration theory of attention. Cognitive Psychology,12(1):97~136
Treisman A, Gormican S.1988. Feature analysis in early vision: evidence from search asymmetries.Psychological Review,95(1):15~48
Treisman A, Souther J.1986. Illusory words: the roles of attention and top-down constraints inconjoining letters to form words. Journal of Experimental Psychology: Human Perception&Performance,12:107~141
Treisman A.1985. Preattentive processing in vision. Computer Vision, Graphics and ImageProcessing,31:156~177
Treisman A.1991. Search, similarity, and integration of features between and within dimensions.Journal of Experimental Psychology: Human Perception&Performance,17(3):652~676
Tsotsos J K, Culhane S M, Wai W Y K, Lai Y, Davis N, Nuflo F.1995. Modeling visual-attention viaselective tuning. Artificial Intelligence,78(1-2):507-545
Vikram T N, Tscherepanow M, Wrede B. A random center surround bottom up visual attentionmodel useful for salient region detection. Proceedings of IEEE Workshop on Applications of ComputerVision,2011:166~173
Vilarino D L, Brea V M, Cabello D.1998. Discrete time CNN for image segmentation by activecontours. Pattern Recognition Letters,19(8):721~734
Wainwright M.1999. Visual adaptation as optimal information transmission. Vision Research,39(23):3960~3974
Walther D B, Koch C.2007. Attention in hierarchical models of object recognition. Progress in BrainResearch,165(3):57~78
Walther D, Koch C.2006. Modeling attention to salient proto-objecets. Neural NetWorks,19:1395~1407
Walther D.2006a. Interactions of visual attention and object recognition: computational modeling,algorithms, and psychophysics.[PhD Dissertation]. Pasadena: California Institute of Technology
Walther D.2006b. SaliencyToolbox. http://www.saliencytoolbox.net/index.html [2009-09-25]
Wang D L, Terman D.1997. Image segmentation based on oscillatory correlation. NeuralComputation,9:805~836
Wang D L.1999. Object selection based on oscillatory correlation. Neural Network,12:579~592
Wang G, He G J.2010. Human visual system based processing for high resolution remote sensingimage segmentation. Proceedings of the International Conference on Signal Processing Systems,2:474~478
Wang H Q, Ji C Y, Gu B X, Tian G Z,2010. A simplified pulse-coupled neural network forcucumber image segmentation. Proceedings of International Conference on Computational andInformation Sciences,2010:1053~1057
Wang J Z, Li J, Wiederhold G.2001. SIMPLIcity: semantics-sensitive Integrated Matching forPicture LIbraries. IEEE Trans on Pattern Analysis and Machine Intelligence,23(9):947~963
Wang W, Wang Y Z, Huang Q M, Gao W.2008. Measuring visual saliency by site entropy rate.Proceedings of IEEE Conference on Computer Vision and Pattern Recongnition,2008:2368~2375
Wang Y, Adaii T, Kung S Y.1998. Quantification and segmentation of brain tissues from MR imagesa probabilistic neural networks approach. IEEE Transactions on Image Processing,7(8):1~12
Wang Z B, Ma Y D, Cheng F Y, Yang L Z.2010. Review of pulse-coupled neural networks. Imageand Vision Computing,28,5~13
Wang Z, Li B.2008. A two-stage approach to saliency detection in images. Proceedings of IEEEConference on Acoustics, Speech and Signal Processing,2008:965~968
Ware C.2000. Information visualization: perception for design. San Francisco: Morgan KaufmannPublishers:1~16
Wolfe J M, Cave K R, Franzel S L.1989. Guided Search: an alternative to the feature integrationmodel for visual search. Journal of Experimental Psychology: Human Perception&Performance,15(3):419~433
Wolfe J M, Cave K R.1989. Deploying visual attention: the Guided Search model. In Troscianko T,Blake A. AI and the Eye. Chichester: John Wiley&Sons, Inc:79~103
Wolfe J M, Franzel S L.1988. Binocularity and visual search. Perception&Psychophysics,44:81~93
Wolfe J M, Friedman-Hill S R, Stewart M I, O'Connell K M.1992. The role of categorization invisual search for orientation. Journal of Experimental Psychology: Human Perception&Performance,18(1):34~49
Wolfe J M, Horowitz T S.2004. What attributes guide the deployment of visual attention and how dothey do it? Nature Reviews Neuroscience,5(6),495~501
Wolfe J M, Klempen N, Dahlen K.2000. Postattentive vision. Journal of Experimental Psychology:Human Perception&Performance,26(2):693~716
Wolfe J M, Yu K P, Stewart M I, Shorter A D, Friedman-Hill S R, Cave K R.1990. Limitations onthe parallel guidance of visual search: color x color and orientation x orientation conjunctions. Journal ofExperimental Psychology: Human Perception&Performance,16(4):879~892
Wolfe J M.1994. Guided search2.0: a revised model of guided seareh. Psychonomic Bulletin&Review,1(2):202~238
Xiao Z H, Shi J, Chang Q.2009. Automatic image segmentation algorithm based on PCNN and fuzzymutual information. Proceedings of IEEE Ninth International Conference on Computer and InformationTechnology,2009:241~245
Zeki S.1993. A Vision of the Brain. Oxford: Oxford Univ Press:26~79
Zhai Y, Shah M.2006. Visual attention detection in video sequences using spatiotemoral cues.Proceedings of ACM International Conference on Multimedia,2006:815~824
Zhang J, Zhuo L, Shen L S.2008. Regions of interest extraction based on visual attention model andwatershed segmentation. IEEE International Conf on Neural Networks&Signal Processing,8(10):375~378
Zhou Q, Ma L, Celenk M, Chelberg D.2005. Content-based image retrieval based on ROI detectionand relevance feedback. Multimedia Tools and Applications,27(11):251~281