复杂背景下的对象特征提取
|
摘要
本文以犯罪现场遗留足迹为对象,阐述了图像处理和模式识别的相关知识,实现复杂背景下的对象特征提取。足迹是刑侦工作中经常用到的生物特征,针对足迹照片存在噪声干扰大,边缘不清晰,人工识别受主观因素影响等问题,提出了基于二维最大熵的类间方差、基于模糊聚类和形态学滤波的足迹特征识别方法。利用二维最大熵的类间方差算法或模糊聚类算法将图像进行阈值分割,得到鞋底各部分受力情况的粗略估计;同时结合形态学滤波和阈值面积消除法抑制噪声,并自适应地确定特征识别门限值;最后在原始图像上标识出特征区。该方法运算简单,能充分利用图像的梯度和灰度信息,有效消除噪声,提高特征区域边缘检测的准确性,为刑侦工作的足迹自动识别提供了新途径。
Taking the tread in alibi as object, this thesis introduces some knowledge about image processing and pattern recognition, and extracts characteristic feature in complex background. Tread feature recognition is one of the most important biometrics in criminal investigation work. A scheme was developed to correctly reproduce distinct, continuous edges and decrease manual intervene based on the maximum variance between clusters (Otsu) method and the algorithms of fuzzy C-means clustering. In this paper, an improved Otsu algorithm is proposed, which is based on the two-dimensional bound histogram. First the Otsu method and the algorithms of fuzzy C-means clustering is used to segment the heavy pressure surface form the image, then the morphological filter and area threshold removing method are applied to filter the small area and the noise, with an adaptive method to select the area extraction threshold. Experimental results show that the scheme reproduces accurate, smooth edges due to the use of the gradient and gray information, providing a new way for tread feature automatic recognition.
Taking the tread in alibi as object, this thesis introduces some knowledge about image processing and pattern recognition, and extracts characteristic feature in complex background. Tread feature recognition is one of the most important biometrics in criminal investigation work. A scheme was developed to correctly reproduce distinct, continuous edges and decrease manual intervene based on the maximum variance between clusters (Otsu) method and the algorithms of fuzzy C-means clustering. In this paper, an improved Otsu algorithm is proposed, which is based on the two-dimensional bound histogram. First the Otsu method and the algorithms of fuzzy C-means clustering is used to segment the heavy pressure surface form the image, then the morphological filter and area threshold removing method are applied to filter the small area and the noise, with an adaptive method to select the area extraction threshold. Experimental results show that the scheme reproduces accurate, smooth edges due to the use of the gradient and gray information, providing a new way for tread feature automatic recognition.
引文
[1] 陈宇,范影乐,庞全.复杂背景下的细胞图像分割技术研究.计算机工程与应用,2005,42～59
[2] 杨磊,杨杰,郑忠龙.海空复杂背景中基于自适应局部能量阈值的红外小目标检测.红外与毫米波学报.2006,25(1):40～45
[3] 管庶安,邓红耀.极端复杂背景下的牌照快速定位新方法.计算机工程与设计.2006,27(7):1170～1172
[4] 王永栋.立体足迹造型与识别系统技术及在法庭诉讼中的证据作用.中国人民公安大学学报.2005,(1):40～41
[5] 孙冬梅,裘正定.生物特征识别技术综述电子学报.2001,12(29):1742～1748.
[6] 朱平.对足迹检验鉴定理论的思考.刑事技术.2005,(5):52
[7] 傅晓海,俞文,雷中坚.对足迹鉴定科学性的反思.中国司法鉴定. 2004,(1):35～37
[8] 兰绍江.我国足迹检验技术的回顾与展望.警察学研究.1994,(2):48～53
[9] 王清举,韩均良,郑德才,等.足迹步法定量化检验.北京:中国人民公安大学出版社,1992,36～38
[10] 宁军丽,王海荣.动力形态特征在鞋印检验中的应用.警察技术.2004,(2):35～37
[11] 翟鲁平.浅谈犯罪现场足迹步法与鞋底磨损特征的分析与检验.内蒙古电大学刊.2005,(4):35～37
[12] Weidong Wang,Xijian Ping,Yihong Ding.Footprint Heavy Pressure Surface Pick-up and Description.Proceeding of the Third Intermational Conference on Image and Graphics.IEEE Trans,2004,11:112～121.
[13] 张毓晋编译.图像工程(上册)-图像处理(第 2 版).北京:清华大学出版社,2006,5～7
[14] 李沁.基于分形几何的图象识别方法研究:[硕士学位论文].保定:华北电力大学,2006
[15] 肖菁,王琰,平西建,等.Bezier 曲面和 Nurbs 曲面拟合在三维足迹表面重建中的应用.西安:第九届中国图象图形学术会议论文集,1998,280～282.
[16] 王琰.三维离散数据的曲面拟合研究:[硕士学位论文].郑州:解放军信息工程学院,1997
[17] 郭惠敏.基于超二次曲面的三维体元建模方法研究:[硕士学位论文].郑州:解放军信息工程学院,1996
[18] 郭惠敏,平西建,邵美珍.超二次曲面三维模型的参数恢复方法探讨.武汉:第八届中国图象图形学术会议论文集.1996,431～435
[19] 田越.基于曲线形状分析的三维表面识别:[硕士学位论文].郑州:解放军信息工程学院,1997
[20] 田越,平西建.基于曲线形状分析的三维表面识别.中国图象图形学报.1999,4(8):689～692
[21] Yue Tian, Xijian Ping, Yingjie Wang.3D Surface Recognition Based on Fuzzy Algorithm. Asian Fuzzy Systems Symposium 2000-International Symposium on Theory and Applications of soft Computing(AFSS 2000 Japan),2000,838～841
[22] 肖菁.基于法向量分布曲线的三维物体识别方法:[硕士学位论文].郑州:解放军信息工程学院,1999
[23] 柳葆芳,肖菁,平西建,等.三维表面的曲面描述与相似性判别.中国图象图形学报(A 版),2001,6(2):30～31
[24] 张涛,平西建,柳葆芳,邵美珍.一种深度图象中的表面曲率估计算法.数据采集与处理,2001,16(1):47～51
[25] Refael C Gonzalez,Richard E Woods 著,阮秋琦,阮宇智等译,数字图像处理(第二版),北京:电子工业出版社,2003,56～58
[26] 刘涛,VC 编程实现灰度图像与彩色图像的相互转换,天机网,软件频道,2001,11,1
[27] 何斌,马天予,王运坚等编著,Visual C++数字图像处理(第二版),北京:人民邮电出版社,2002,12:7～8
[28] Matalas I, Benjamin R, Kitney R. An edge detection technique using the facet model and parameterized relaxation labeling.IEEE PAMI,1997,19(4):328～341
[29] Bezdek J C.Pattern Recognition with Fuzzy Objective Function Algorithm . New York:Plenum Press,1981:196～199
[30] 裴继红,基于模糊信息处理的图像分割方法研究:[博士学位论文] .西安电子科技大学,2002
[31] 韩思奇,王蕾.图像分割的阈值法综述.系统工程与电子技术.2002,6(24):91～102
[32] Doyle W.Operation Useful for Similarity-Invariant Pattern Recognition.J. Asssoc.Computer Mach.1962,9:259～567
[33] lee S,Chung S.A Comparative Performance Study of Several Global Thresholding Techniques for Segmentation[J].Computer Vision,Graphics, and Image Processing.1990,52:171～190
[34] Tsai W H.Moment-Preserving Thresholding:A New Approach.Computer Vision,Graphics,and Image Processing.1985,29:377～393
[35] Kittler J,Llingworlh J.Minimum Error Thresholding.Pattern Recognition.1986,19:41～47
[36] Rosenfeld A,De La Tone P.Histgram Concavity Analysis as an Aid in Threshold Selection.IEEE Trans.on Systems,Man and Cybernetics,1983,23l～235
[37] Pun T .A New Method for Gray-Level Picture Thresholding Using the Entroy of the Histogram[J].Signal Processing,1980,2:223～237
[38] Kapur J,Sahop P,Wong A.A New Method for Grey-Level Picture Thresholding using the Entropy of the Histogram.Computer Vision Graphics,and Image Processing,1985,29:210～239
[39] Kapur J N.Maximum Entropy Models in Science and Engineering.Wiley Eastern,New Delhi,1989,231～235
[40] Mason D,Lauder I J,Rutoritz D,eta1.Measurement of C-Bands in Human Chromosoms.IEEE Trans.on Pattern Anal.Mach. Intell.1975,7:155～164
[41] Wu A Y,Rosenfeld A.Threshold Selection Using Quadtree.IEEE Trans.on Pattern Ana1.Mach.Intel1.1982,4:90～94
[42] Ahuja N,Rosenfeld A.A Note on the Use of Second-Order Gray-Level Satistics for Threshold Selection.IEEE Tram.On Systerns,Man and Cybernetics,1978,8:895～899
[43] Abutaleb A S . Automatic Thresholding of Gray-Level Picture Using Two-Dimensional Entropies.Pattern Recognition,1989,47:22～32
[44] Pal N R,Pal S K.A Review on Image Segmentation Techniques.Pattern Recognition,1993,26(9):1277～1294
[45] Brink A.Thresholding of Digital Image Using two Dimensional Entropies Pattern Recognition.1992,25:803～808
[46] 郭建星.一种改进的基于最大类间方差的分割方法,仪器仪表学报,2005,26(8):665～666
[47] Bharnu B, Lee S, Ming J.Alaptive Image Segmentation Using a Genetic Algorithm.IEEE Trans.on Systerm ,Man and Cvbernetica,1995,5(12):1543～1565
[48] 夏良正.数字图像处理.南京:东南大学出版社.1999,9:228～229
[49] 高新波,谢维信,模糊聚类理论发展及应用的研究进展,科学通报,1999,44(21):2241～2250
[50] 唐常青,吕宏伯,黄铮,张方.数学形态学方法及其应用.北京:科学出版社.1990,56～59
[51] 崔屹.图像处理与分析-数学形态学方法及应用.北京:科学出版社,2000,68～72
[52] 杨晖,张继武.数学形态学在图像边缘检测中的应用研究.辽宁大学学报.2005,1:50～53
[53] 阮秋琦.数字图像处理学.北京:电子工业出版社.2001,136～138
[54] 雷艳敏,黄秋元.基于数学形态学的图像边缘检测.武汉理工大学学报.2000,27(5):25～27
[55] 付永庆,王咏胜.一种基于数学形态学的灰度图像边缘检测算法.哈尔滨工程大学学报.2005,26(5):685～687
[56] Louverdisg , Vardavoudiami , Andresdisi , etal . A new approach to morphological color image processing.PatternRecognition,2002,35:1733～1741
[57] Chent,Wuqh,Torkamanrr,etal.A pseudo top-hat mathematical morphological approach to edge diction in dark regions.Pattern Recognition,2002,35:199～210
[58] 刘健庄,栗文表.灰度图象的二维 otsu 自动阈值分割法.自动化学报,1991,19(1):101～105
[2] 杨磊,杨杰,郑忠龙.海空复杂背景中基于自适应局部能量阈值的红外小目标检测.红外与毫米波学报.2006,25(1):40～45
[3] 管庶安,邓红耀.极端复杂背景下的牌照快速定位新方法.计算机工程与设计.2006,27(7):1170～1172
[4] 王永栋.立体足迹造型与识别系统技术及在法庭诉讼中的证据作用.中国人民公安大学学报.2005,(1):40～41
[5] 孙冬梅,裘正定.生物特征识别技术综述电子学报.2001,12(29):1742～1748.
[6] 朱平.对足迹检验鉴定理论的思考.刑事技术.2005,(5):52
[7] 傅晓海,俞文,雷中坚.对足迹鉴定科学性的反思.中国司法鉴定. 2004,(1):35～37
[8] 兰绍江.我国足迹检验技术的回顾与展望.警察学研究.1994,(2):48～53
[9] 王清举,韩均良,郑德才,等.足迹步法定量化检验.北京:中国人民公安大学出版社,1992,36～38
[10] 宁军丽,王海荣.动力形态特征在鞋印检验中的应用.警察技术.2004,(2):35～37
[11] 翟鲁平.浅谈犯罪现场足迹步法与鞋底磨损特征的分析与检验.内蒙古电大学刊.2005,(4):35～37
[12] Weidong Wang,Xijian Ping,Yihong Ding.Footprint Heavy Pressure Surface Pick-up and Description.Proceeding of the Third Intermational Conference on Image and Graphics.IEEE Trans,2004,11:112～121.
[13] 张毓晋编译.图像工程(上册)-图像处理(第 2 版).北京:清华大学出版社,2006,5～7
[14] 李沁.基于分形几何的图象识别方法研究:[硕士学位论文].保定:华北电力大学,2006
[15] 肖菁,王琰,平西建,等.Bezier 曲面和 Nurbs 曲面拟合在三维足迹表面重建中的应用.西安:第九届中国图象图形学术会议论文集,1998,280～282.
[16] 王琰.三维离散数据的曲面拟合研究:[硕士学位论文].郑州:解放军信息工程学院,1997
[17] 郭惠敏.基于超二次曲面的三维体元建模方法研究:[硕士学位论文].郑州:解放军信息工程学院,1996
[18] 郭惠敏,平西建,邵美珍.超二次曲面三维模型的参数恢复方法探讨.武汉:第八届中国图象图形学术会议论文集.1996,431～435
[19] 田越.基于曲线形状分析的三维表面识别:[硕士学位论文].郑州:解放军信息工程学院,1997
[20] 田越,平西建.基于曲线形状分析的三维表面识别.中国图象图形学报.1999,4(8):689～692
[21] Yue Tian, Xijian Ping, Yingjie Wang.3D Surface Recognition Based on Fuzzy Algorithm. Asian Fuzzy Systems Symposium 2000-International Symposium on Theory and Applications of soft Computing(AFSS 2000 Japan),2000,838～841
[22] 肖菁.基于法向量分布曲线的三维物体识别方法:[硕士学位论文].郑州:解放军信息工程学院,1999
[23] 柳葆芳,肖菁,平西建,等.三维表面的曲面描述与相似性判别.中国图象图形学报(A 版),2001,6(2):30～31
[24] 张涛,平西建,柳葆芳,邵美珍.一种深度图象中的表面曲率估计算法.数据采集与处理,2001,16(1):47～51
[25] Refael C Gonzalez,Richard E Woods 著,阮秋琦,阮宇智等译,数字图像处理(第二版),北京:电子工业出版社,2003,56～58
[26] 刘涛,VC 编程实现灰度图像与彩色图像的相互转换,天机网,软件频道,2001,11,1
[27] 何斌,马天予,王运坚等编著,Visual C++数字图像处理(第二版),北京:人民邮电出版社,2002,12:7～8
[28] Matalas I, Benjamin R, Kitney R. An edge detection technique using the facet model and parameterized relaxation labeling.IEEE PAMI,1997,19(4):328～341
[29] Bezdek J C.Pattern Recognition with Fuzzy Objective Function Algorithm . New York:Plenum Press,1981:196～199
[30] 裴继红,基于模糊信息处理的图像分割方法研究:[博士学位论文] .西安电子科技大学,2002
[31] 韩思奇,王蕾.图像分割的阈值法综述.系统工程与电子技术.2002,6(24):91～102
[32] Doyle W.Operation Useful for Similarity-Invariant Pattern Recognition.J. Asssoc.Computer Mach.1962,9:259～567
[33] lee S,Chung S.A Comparative Performance Study of Several Global Thresholding Techniques for Segmentation[J].Computer Vision,Graphics, and Image Processing.1990,52:171～190
[34] Tsai W H.Moment-Preserving Thresholding:A New Approach.Computer Vision,Graphics,and Image Processing.1985,29:377～393
[35] Kittler J,Llingworlh J.Minimum Error Thresholding.Pattern Recognition.1986,19:41～47
[36] Rosenfeld A,De La Tone P.Histgram Concavity Analysis as an Aid in Threshold Selection.IEEE Trans.on Systems,Man and Cybernetics,1983,23l～235
[37] Pun T .A New Method for Gray-Level Picture Thresholding Using the Entroy of the Histogram[J].Signal Processing,1980,2:223～237
[38] Kapur J,Sahop P,Wong A.A New Method for Grey-Level Picture Thresholding using the Entropy of the Histogram.Computer Vision Graphics,and Image Processing,1985,29:210～239
[39] Kapur J N.Maximum Entropy Models in Science and Engineering.Wiley Eastern,New Delhi,1989,231～235
[40] Mason D,Lauder I J,Rutoritz D,eta1.Measurement of C-Bands in Human Chromosoms.IEEE Trans.on Pattern Anal.Mach. Intell.1975,7:155～164
[41] Wu A Y,Rosenfeld A.Threshold Selection Using Quadtree.IEEE Trans.on Pattern Ana1.Mach.Intel1.1982,4:90～94
[42] Ahuja N,Rosenfeld A.A Note on the Use of Second-Order Gray-Level Satistics for Threshold Selection.IEEE Tram.On Systerns,Man and Cybernetics,1978,8:895～899
[43] Abutaleb A S . Automatic Thresholding of Gray-Level Picture Using Two-Dimensional Entropies.Pattern Recognition,1989,47:22～32
[44] Pal N R,Pal S K.A Review on Image Segmentation Techniques.Pattern Recognition,1993,26(9):1277～1294
[45] Brink A.Thresholding of Digital Image Using two Dimensional Entropies Pattern Recognition.1992,25:803～808
[46] 郭建星.一种改进的基于最大类间方差的分割方法,仪器仪表学报,2005,26(8):665～666
[47] Bharnu B, Lee S, Ming J.Alaptive Image Segmentation Using a Genetic Algorithm.IEEE Trans.on Systerm ,Man and Cvbernetica,1995,5(12):1543～1565
[48] 夏良正.数字图像处理.南京:东南大学出版社.1999,9:228～229
[49] 高新波,谢维信,模糊聚类理论发展及应用的研究进展,科学通报,1999,44(21):2241～2250
[50] 唐常青,吕宏伯,黄铮,张方.数学形态学方法及其应用.北京:科学出版社.1990,56～59
[51] 崔屹.图像处理与分析-数学形态学方法及应用.北京:科学出版社,2000,68～72
[52] 杨晖,张继武.数学形态学在图像边缘检测中的应用研究.辽宁大学学报.2005,1:50～53
[53] 阮秋琦.数字图像处理学.北京:电子工业出版社.2001,136～138
[54] 雷艳敏,黄秋元.基于数学形态学的图像边缘检测.武汉理工大学学报.2000,27(5):25～27
[55] 付永庆,王咏胜.一种基于数学形态学的灰度图像边缘检测算法.哈尔滨工程大学学报.2005,26(5):685～687
[56] Louverdisg , Vardavoudiami , Andresdisi , etal . A new approach to morphological color image processing.PatternRecognition,2002,35:1733～1741
[57] Chent,Wuqh,Torkamanrr,etal.A pseudo top-hat mathematical morphological approach to edge diction in dark regions.Pattern Recognition,2002,35:199～210
[58] 刘健庄,栗文表.灰度图象的二维 otsu 自动阈值分割法.自动化学报,1991,19(1):101～105