复杂背景下器件多余物成像检测的若干关键技术研究
|
摘要
元器件的完整性是机器正常运行的重要保障,因此,对于元器件上多余物的检测方法的研究也是非常重要的。目前,关于器件上的多余物还主要依靠人工或者半人工来检测,判别的主观性较大,而且技术人员容易疲劳,导致检测效率不高。针对这一问题,本文提出了一种基于模式识别的视觉成像理论的多余物检测方法。
经过对元器件图像的分析,发现多余物目标体积较小,并且形状姿态不一,所处位置不定,而元器件的背景图像却相对稳定,因此,提出了一种基于元器件背景的显著区域识别与配准的方法来完成参考图像和实时图像的配准,从而实现多余物目标的检测。
本文的主要研究工作就是对复杂背景下多余物目标的定位,针对这一目的做了以下几个方面的研究工作:(1)图像分割;(2)区域特征提取;(3)显著特征选择;(4)显著区域识别;(5)显著区域配准;(6)多余物目标定位。一般的目标识别方法多数是针对目标的图像特性来设计的,而本文主要是通过识别背景区域来达到识别多余物目标的目的。通过对分割后图像的处理,找出最显著的背景区域,然后以它为准则实现参考图像和实时图像的配准,最终识别出多余物目标。本文对四类元器件共300幅图像进行了测试,实验证明,基于显著区域识别与配准的复杂背景下多余物自动检测的方法是可行的,其平均检测概率可达到0.85以上。
In the industrial society, the integrality of devices is the important guarantee of the working efficiency of machines. Thus, it is essential to develop methods to detect the redundancy in devices. Currently, most of the redundancy detection for device depends on human check or human-machine check, which make the result has much subjectivity. Besides, in the human check, the technician is prone to be tired, which might lead to the drop of the working efficiency. Aiming at this problem, we advance a new redundancy detection method, which based on the pattern recognition and vision theory.
After the careful analysis for the image of device, we find the different features of redundancy and the background of image. Redundancy usually have small size, different shapes and flexible positions. on the contrary, the background of image usually has several different regions, and the shape, size, position of regions are relatively steady. In view of these features, we propose to use the recognition and registration of the marked region in the background to complete the registration between reference image and real-time image.
The primary work of this paper is to fix the position of redundancy in the device. For attaining this purpose, we did work in several aspects as below: (1) image segmentation; (2) the feature extraction in the region; (3) the selection of the marked features; (4) the recognition of the marked region; (5) the registration of the marked region; (6) the detection of redundancy. Most of the target recognition methods are designed as the feature of target, in contrast, this paper make the redundancy recognition from the recognition of the region in background. After the pre-processing and segmentation of the images, according to the extracted features from regions, we find the most marked regions and then, make the registration between the marked regions. At last, detect the redundancy in devices. This paper made test in four kinds of devices, which have 300 images. Experiments proved that the feasibility of this method and the detection probability can reach above 0.85.
经过对元器件图像的分析,发现多余物目标体积较小,并且形状姿态不一,所处位置不定,而元器件的背景图像却相对稳定,因此,提出了一种基于元器件背景的显著区域识别与配准的方法来完成参考图像和实时图像的配准,从而实现多余物目标的检测。
本文的主要研究工作就是对复杂背景下多余物目标的定位,针对这一目的做了以下几个方面的研究工作:(1)图像分割;(2)区域特征提取;(3)显著特征选择;(4)显著区域识别;(5)显著区域配准;(6)多余物目标定位。一般的目标识别方法多数是针对目标的图像特性来设计的,而本文主要是通过识别背景区域来达到识别多余物目标的目的。通过对分割后图像的处理,找出最显著的背景区域,然后以它为准则实现参考图像和实时图像的配准,最终识别出多余物目标。本文对四类元器件共300幅图像进行了测试,实验证明,基于显著区域识别与配准的复杂背景下多余物自动检测的方法是可行的,其平均检测概率可达到0.85以上。
In the industrial society, the integrality of devices is the important guarantee of the working efficiency of machines. Thus, it is essential to develop methods to detect the redundancy in devices. Currently, most of the redundancy detection for device depends on human check or human-machine check, which make the result has much subjectivity. Besides, in the human check, the technician is prone to be tired, which might lead to the drop of the working efficiency. Aiming at this problem, we advance a new redundancy detection method, which based on the pattern recognition and vision theory.
After the careful analysis for the image of device, we find the different features of redundancy and the background of image. Redundancy usually have small size, different shapes and flexible positions. on the contrary, the background of image usually has several different regions, and the shape, size, position of regions are relatively steady. In view of these features, we propose to use the recognition and registration of the marked region in the background to complete the registration between reference image and real-time image.
The primary work of this paper is to fix the position of redundancy in the device. For attaining this purpose, we did work in several aspects as below: (1) image segmentation; (2) the feature extraction in the region; (3) the selection of the marked features; (4) the recognition of the marked region; (5) the registration of the marked region; (6) the detection of redundancy. Most of the target recognition methods are designed as the feature of target, in contrast, this paper make the redundancy recognition from the recognition of the region in background. After the pre-processing and segmentation of the images, according to the extracted features from regions, we find the most marked regions and then, make the registration between the marked regions. At last, detect the redundancy in devices. This paper made test in four kinds of devices, which have 300 images. Experiments proved that the feasibility of this method and the detection probability can reach above 0.85.
引文
[1]何东建.数字图像处理.2003年7月第1版
[2]王淑娟,高宏亮,翟国富.航天继电器多余物自动检测算法的研究.宇航学报,2008,Vol.29,No.1 January
[3]傅世敏.视觉选择性注意的机制及其在视觉信息处理中的作用:[博士学位论文].中国科学技术大学,1998
[4] CHRISTOPHER J.C. BURGES. A Tutorial on Support Vector Machines for Pattern Recognition. Kluwer Academic Publishers. Boston. Manufactured in The Netherlands
[5]张国华,杜迎,华丞等.捕捉集成电路中多余物方法的研究.电子产品可靠性与环境试验,2006,Vol.24,No.2 Apr
[6] Chris Harris,Mike Stephens. A combined corner and edge detector. Alvey Vision Conference. 1988: 147- 152
[7] Smith SM,BRADYM. SUSAN-a new approach to low level image processing[J]. International Journal of Computer. 1997, 23 (1) : 45- 78
[8]刘贵喜,王蕾.基于区域选择和特征点匹配的图像配准算法.光电子.激光,第18卷第8期
[9]李博,杨丹,张小洪.一种新的基于梯度方向直方图的图像配准方法.计算机应用研究,第24卷第3期
[10]吕金建,文贡坚,李德仁等.一种基于角点特征的图像自动配准方法.遥感技术与应用,第22卷第3期
[11]张辉,王淑娟,王立忠等.航天继电器多余物检测方法的综合分析与讨论.机电元件,Vol.23 No.2
[12]王淑娟,张辉,王世成.航天继电器多余物检测技术的探讨.低压电器,2004,No.9
[13] Bins,Bruce A. Draper Feature Selection from Huge Feature Sets[EB/OL]
[14] Manoranjan Dash,Huan Liu. Feature Selection for Classification[J]. Intelligent Data Analysis,1997,1(3):131-156
[15] D Koller,M Sahami. Toward Optimal Feature Selection[A], Proc. 13th International Conference on Machine Learning, 1996.284-292
[16]高贵,匡纲要,李德仁.高分辨率SAR图像分割及目标特征提取.宇航学报,2006年3月
[17] Rafael C. Gonzalez,Richard E. Woods.数字图像处理(第二版).电子工业出版社
[18]孙即祥.现代模式识别.国防科技大学出版社
[19] Chao J,Shao K,Jang L. Uncertain information fusion using belief measure and its application to signal classification[J]. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems,1996(12):151-157
[20]陈桂友,徐胜男,李振华.等刚体变换下基于轮廓的多传感器图像配准算法.系统工程与电子技术,第29卷第7期
[21]牛力丕,毛士艺,陈炜.基于Hausdorff距离的图像配准研究.电子与信息学报,第29卷第1期
[22]陈振学,汪国有,马于涛等.基于均值反差滤波的红外小目标检测算法.武汉大学学报,第32卷第6期
[23]张南,刘军杰,刘志军.基于支撑向量机的模式识别方法研究.舰船科学技术, 2006年10月,第28卷第5期
[24] Treisman A..A feature integration theory of attention. Cognitive Psychology. January 1980, 12:97-136.
[25]夏庆观,路红,陈桂.基于小波神经网络的零件图像特征提取和识别.仪器仪表学报, 2005年8月,第26卷第8期
[26]何斌,马天予,王运坚等.数字图像处理.人民邮电出版社,2002年
[27] R.Desimone,J.Duncan. Neural Mechanism of Selective Visual Attention. Annual Review Neuroscience. 1995,18:193-222
[28]夏德深,傅德胜.现代图像处理技术与应用.东南大学出版社
[29]王娟,慈林林,姚康泽.特征选择方法综述.计算机工程与科学,2005年第27卷第12期
[30]李军梅,胡以华,陈修桥.模式识别的特征优化专家系统研究.电光与控制, 2006年1月,第13卷第1期
[31] B. Srinivasa Reddy,B. N. Chatterji. An FFT-Based Technique for Translation, Rotation, and Scale-Invariant Image Registration. IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 5, NO. 8, AUGUST 1996
[32] Marti A. Hearst. Support vector machines. TRENDS & CONTROVERSIES
[33] Sanjeev R. Kulkarni. Learning Pattern Classification—A Survey. IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 44, NO. 6, OCTOBER 1998
[34] HARDIE RC, BARNARD KJ. High resolution image reconstruction from a sequence of rotated and translated frames and its application to an infrared imaging system[J]. Optical Engineering, 1998, 37 (1) :2472260.
[35] HENG L. K., HWA E. M., KOK H. S.. High accuracy registration of translated and rotated images using hierarchical method. proceedings of IEEE International Conference on Acoustics. Speech and Signal Processing, 1999 [C]. [S.l.] : [s.n.] , 2000: 221122214
[36] Chiou Ting Hsu, Rob A. Beuker. Multiresolution Feature Based Image Registration [A]. Proceedings of SPIE[C]. Perth : [s.n.],2000
[37]雷凯,刘艳滢,王延杰等.基于特征点的对数极坐标变换图像配准算法.光学技术,第32卷第3期
[38]张绪省,朱贻盛,程明等.小波变换在检测继电器内小颗粒中的应用.宇航学报,1997,18 (2) :62- 671
[39] Otsu. A Threshold Selection Method from Gray-Level Histogram. IEEE Trans on SMC-9, 1979:62-66.
[40]潘泉,于昕,程咏梅等.信息融合理论的基本方法与进展.自动化学报,第29卷第4期
[41]杨宾峰,宁欣.主成份分析在数字图像特征提取中的应用.微计算机信息,2007年第23卷第2-3期
[2]王淑娟,高宏亮,翟国富.航天继电器多余物自动检测算法的研究.宇航学报,2008,Vol.29,No.1 January
[3]傅世敏.视觉选择性注意的机制及其在视觉信息处理中的作用:[博士学位论文].中国科学技术大学,1998
[4] CHRISTOPHER J.C. BURGES. A Tutorial on Support Vector Machines for Pattern Recognition. Kluwer Academic Publishers. Boston. Manufactured in The Netherlands
[5]张国华,杜迎,华丞等.捕捉集成电路中多余物方法的研究.电子产品可靠性与环境试验,2006,Vol.24,No.2 Apr
[6] Chris Harris,Mike Stephens. A combined corner and edge detector. Alvey Vision Conference. 1988: 147- 152
[7] Smith SM,BRADYM. SUSAN-a new approach to low level image processing[J]. International Journal of Computer. 1997, 23 (1) : 45- 78
[8]刘贵喜,王蕾.基于区域选择和特征点匹配的图像配准算法.光电子.激光,第18卷第8期
[9]李博,杨丹,张小洪.一种新的基于梯度方向直方图的图像配准方法.计算机应用研究,第24卷第3期
[10]吕金建,文贡坚,李德仁等.一种基于角点特征的图像自动配准方法.遥感技术与应用,第22卷第3期
[11]张辉,王淑娟,王立忠等.航天继电器多余物检测方法的综合分析与讨论.机电元件,Vol.23 No.2
[12]王淑娟,张辉,王世成.航天继电器多余物检测技术的探讨.低压电器,2004,No.9
[13] Bins,Bruce A. Draper Feature Selection from Huge Feature Sets[EB/OL]
[14] Manoranjan Dash,Huan Liu. Feature Selection for Classification[J]. Intelligent Data Analysis,1997,1(3):131-156
[15] D Koller,M Sahami. Toward Optimal Feature Selection[A], Proc. 13th International Conference on Machine Learning, 1996.284-292
[16]高贵,匡纲要,李德仁.高分辨率SAR图像分割及目标特征提取.宇航学报,2006年3月
[17] Rafael C. Gonzalez,Richard E. Woods.数字图像处理(第二版).电子工业出版社
[18]孙即祥.现代模式识别.国防科技大学出版社
[19] Chao J,Shao K,Jang L. Uncertain information fusion using belief measure and its application to signal classification[J]. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems,1996(12):151-157
[20]陈桂友,徐胜男,李振华.等刚体变换下基于轮廓的多传感器图像配准算法.系统工程与电子技术,第29卷第7期
[21]牛力丕,毛士艺,陈炜.基于Hausdorff距离的图像配准研究.电子与信息学报,第29卷第1期
[22]陈振学,汪国有,马于涛等.基于均值反差滤波的红外小目标检测算法.武汉大学学报,第32卷第6期
[23]张南,刘军杰,刘志军.基于支撑向量机的模式识别方法研究.舰船科学技术, 2006年10月,第28卷第5期
[24] Treisman A..A feature integration theory of attention. Cognitive Psychology. January 1980, 12:97-136.
[25]夏庆观,路红,陈桂.基于小波神经网络的零件图像特征提取和识别.仪器仪表学报, 2005年8月,第26卷第8期
[26]何斌,马天予,王运坚等.数字图像处理.人民邮电出版社,2002年
[27] R.Desimone,J.Duncan. Neural Mechanism of Selective Visual Attention. Annual Review Neuroscience. 1995,18:193-222
[28]夏德深,傅德胜.现代图像处理技术与应用.东南大学出版社
[29]王娟,慈林林,姚康泽.特征选择方法综述.计算机工程与科学,2005年第27卷第12期
[30]李军梅,胡以华,陈修桥.模式识别的特征优化专家系统研究.电光与控制, 2006年1月,第13卷第1期
[31] B. Srinivasa Reddy,B. N. Chatterji. An FFT-Based Technique for Translation, Rotation, and Scale-Invariant Image Registration. IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 5, NO. 8, AUGUST 1996
[32] Marti A. Hearst. Support vector machines. TRENDS & CONTROVERSIES
[33] Sanjeev R. Kulkarni. Learning Pattern Classification—A Survey. IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 44, NO. 6, OCTOBER 1998
[34] HARDIE RC, BARNARD KJ. High resolution image reconstruction from a sequence of rotated and translated frames and its application to an infrared imaging system[J]. Optical Engineering, 1998, 37 (1) :2472260.
[35] HENG L. K., HWA E. M., KOK H. S.. High accuracy registration of translated and rotated images using hierarchical method. proceedings of IEEE International Conference on Acoustics. Speech and Signal Processing, 1999 [C]. [S.l.] : [s.n.] , 2000: 221122214
[36] Chiou Ting Hsu, Rob A. Beuker. Multiresolution Feature Based Image Registration [A]. Proceedings of SPIE[C]. Perth : [s.n.],2000
[37]雷凯,刘艳滢,王延杰等.基于特征点的对数极坐标变换图像配准算法.光学技术,第32卷第3期
[38]张绪省,朱贻盛,程明等.小波变换在检测继电器内小颗粒中的应用.宇航学报,1997,18 (2) :62- 671
[39] Otsu. A Threshold Selection Method from Gray-Level Histogram. IEEE Trans on SMC-9, 1979:62-66.
[40]潘泉,于昕,程咏梅等.信息融合理论的基本方法与进展.自动化学报,第29卷第4期
[41]杨宾峰,宁欣.主成份分析在数字图像特征提取中的应用.微计算机信息,2007年第23卷第2-3期
© 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 |