基于GLCM和FastICA的鞋底识别
摘要
针对传统鞋底识别中的几何参数法和纹理分析法的局限,引入快速独立分量分析(FastICA)方法,将其应用于鞋底识别领域,并结合鞋底图像的几何特征及基于灰度共生矩阵(GLCM)的纹理特征,提出了综合使用多种特征的鞋底识别新方法,一定程度上克服了单一特征的局限。实验表明,该方法比单一特征的识别方法有更高的识别率。
出处
《福建电脑》
2011年第9期92-95,共4页
Journal of Fujian Computer
参考文献9
-
1N. SAWYER. SHOE-FIT' A Computerized Shoe Print Database [C]. Proc. European Convention on Security and Detec- tion, 1995,86-89.
-
2A. GIROD. Computer Classification of the Shoeprint of Bur- glar Soles[J]. Forensic Science Int'l, 1996, 82: 59-65.
-
3W. ASHLEY. What Shoe Was That? The Use of Computer- ized Image Database to Assist in Identification [J]. Forensic Science Int'1,1996, 82: 67-79.
-
4SU H, BOUR.IDANE A, CROOKES D. Image quality mea- sures for hierarchical decomposition of a shoeprint image [J]. Forensic Science International, 2006, 163: 125-131.
-
5管燕,李存华,仲兆满.一种基于综合特征的鞋底图像识别方法[J].西南民族大学学报(自然科学版),2007,33(5):1189-1194. 被引量:2
-
6NIBLACK W, BARBER P..The QBIC project: querying image by content using color, texture and shape [M].SPIE,1993:173- 187.
-
7Haralick R M , Shanmugam K.Texture features for image clas- sification.IEEE Trans.on Sys,Man,and Cyb, 1973, SMC , 3(6) : 610-621.
-
8A. Hyvarinen and E.Oja. Independent Component Analysis: Algorithms and application. Neural Networks. 2000,3(4~5):411~430P.
-
9Hyv?rinen A,Oja E.A fast fixed-point algorithm for indepen- dent component analysis[J].Neural Computation, 1997,9 (7) : 1483- 1492.
二级参考文献9
-
1黄贤武 王加俊 李家华.数字图像处理与压缩编码技术[M].成都:电子科技大学出版社,2002..
-
2吴志军.鞋底花纹比对与分析系统的设计与实现[D].大连:大连海事大学,2004.
-
3A.GIROD.Computer Classification of the Shoeprint of Burglar Soles[J].Forensic Science Int'l,1996,82:59-65.
-
4N.SAWYER.SHOE-FIT' A Computerized Shoe Print Database[C].Proc.European Convention on Security and Detection,1995,86-89.
-
5W.ASHLEY.What Shoe Was That? The Use of Computerized Image Database to Assist in Identification[J].Forensic Science Int'l,1996,82:67-79.
-
6SU H,BOURIDANE A,CROOKES D.Image quality measures for hierarchical decomposition of a shoeprint image[J].Forensic Science International,2006,163:125-131.
-
7NIBLACK W,BARBER R.The QBIC project:querying image by content using color,texture and shape[M].SPIE,1993:173-187.
-
8OHANIAN P.P.,DUBES R.C.Performance evaluation for four classes of texture features[J].Pattern Recognition.1992,25(8):819-833.
-
9HARALICK R,SHANMUGAM K,DINSTEIN I.Textural features for image classification[J].IEEE Trans Syst,Mancybern.1973,3(6):610-623.
-
1管燕,李存华,仲兆满,滕腾.一种基于视觉特征的鞋底图像识别方法[J].河南科技大学学报(自然科学版),2008,29(3):56-59. 被引量:2
-
2丁维福,姜威,张亮亮.结合Gabor变换和FastICA的人脸表情识别方法[J].计算机工程与应用,2011,47(24):178-181. 被引量:6
-
3方民权,周海芳,张卫民,申小龙.GPU上高光谱快速ICA降维并行算法[J].国防科技大学学报,2015,37(4):65-70. 被引量:1
-
4李丙春.基于独立成分分析的人脸图像特征提取与识别[J].新疆师范大学学报(自然科学版),2014,33(4):79-84.
-
5杜晔,张亚丹,黎妹红,张大伟.基于改进FastICA算法的入侵检测样本数据优化方法[J].通信学报,2016,37(1):42-48. 被引量:14
-
6管燕,李存华,仲兆满.一种基于综合特征的鞋底图像识别方法[J].西南民族大学学报(自然科学版),2007,33(5):1189-1194. 被引量:2
-
7乔继红.应用独立成分分析的太阳能电池图像去噪[J].制造业自动化,2014,36(23):5-7.
-
8张晋东,秦贵和,崔月.基于FastICA和SVM的EEG信号分类系统[J].计算机研究与发展,2008,45(z1):255-258. 被引量:1
-
9杨青,王栗,刘彧诚,刘念.FICA-IPNN集合型滚动轴承故障诊断方法[J].电机与控制学报,2014,18(3):73-78. 被引量:4
-
10方民权,张卫民,周海芳.集成众核上快速独立成分分析降维并行算法[J].计算机研究与发展,2016,53(5):1136-1146. 被引量:5