Ear biometric has the basic characteristics，such as universality, distinctiveness，stability and collectibility.The non-disturbed recognition can be easily realized by ear biometric or fusion of ear and face biometrics. As a novel biometric identification, ear recognition is a very active research project in the field of pattern
recognition. However, ear recognition result is usually affected by the head posture of image，illumination vanations，occlusion and other factors, which makes the process of recognition more complicated and challenging, In this paper, a novel ear recognition approach based on histogram of oriented gradient feature extraction is studied. The ear recognition scheme by combining histogram of oriented gradient features with sulrregion fuzzy fusion is presented. The ear image is divided into a number of sulrregions, histograms of oriented gradient features of different sulrregions are extracted separately, and the fuzzy membership matching fusion strategy is introduced to obtain the last classification label. Furthmore, the issue on ear recognition under local occlusion based on histogram
of oriented gradient is discussed in detail.The recognition contribution rate for each sulrregion is defined and analyzed，and the accumulated occlusion is investigated，which can give a reference for determining the effective identify regional block.The maximum occluded rank and effective identify regional block can effentivcly identify the human ear images. Therefore, the standard of the ear images whether retained or discarded can be determined.Experimental results show that ear recognition approach based on histogram of oriented gradient features is practicable and effective.
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1]Chen C K，Yu YM，Shi J. A fast sparse repre- sentation based classification. Journal of Nan- jing University(Natural Sciences)，2012，48
(1) : 70-76.(陈才扣，喻以明，史俊.一种速的基于稀疏表示分类器.南京大学学报(自然科学)，2012, 48(1); 70-76).
[2]Yan P, Bowyer K W. Biometric recognition using 3D ear shape, IEEE Transactions on Pat-tern Analysis and Machine Intelligence, 2007，8(29):1297~1308.
[3]Hurley D, Nixon M, Carter J. Force field fca ture extraction for ear biometrics. Computer Vi lion and image Understanding, 2004，98: 491一512.
[4]Choras M.Ear biometrics based on geometrical feature extraction. Electronic Letters on Com puter Vision and Image Analysis, 2005,5(3):84~95.
[5]Mu Z C, Xi D C，Xu Z G, et al. Ear feature extraction combining the shape feature of outer ear with the structure feature of inner ear. Jour-
nal of University of Science and Technology Bei- jing, 2006, 28(5): 497-500.(穆志纯，席德春，徐正光等.外耳形状特征和内耳结构特征
结合的人耳特征提取.北京科技大学学报，2006，28(5):497一500).
[6]Yuan W Q, Tian Y，Zou D. Ear geometric fea- ture extraction and recognition based on multi- scale canny. Journal of Optoelectronics Laser,
2008, 19(11):1554一1557.(苑玮琦，田莹，邹达.基于多尺度Canny算子的人耳几何特征提取与识别.光电子激光，2008, 19(11); 1554一1557).
[7]Nanni L，Lumini A. A multi-matcher for ear authentication. Pattern Recognition Letters,2007,28:2219~2226.
[8]Feng J，Mu Z C，Duan S F, et al. Ear recogni- tion based on local binary pattern and kernel fisher discriminant analysis. Journal of Informa-
tion and Computational Science, 2008，5(2): 887一894.
[9]Wang Y，Mu Z C, Fu D M, et al. Ear recogni- tion based on wavelet transform and uniform texture descriptors. Acta Electronica Sinica,
2010, 38(1); 239-243.(土瑜，穆志纯，付冬梅等.基于小波变换和规范型纹理描述子的人耳识别.电子学报，2010, 38(1); 239- 243).
[10]Wang X Y，Guo J Y. Human ear recognition based on statistic features of local information. Computer Engineering and Applications, 2012，
48(9) : 141-144.(王晓云，郭金玉.基于局部信息统计的人耳识别方法.计算机工程与应用，2012，48 (9):141一144).
[11]Dun W J，Mu Z C. An ICA-based car recogni- tion method through nonlinear adaptive feature fusion. Journal of Computer一Aided Design and
Computer Graphics，2009，21(3):382一388. (敦文杰，穆志纯.基于ICA的非线性自适应特征融合的人耳识别.计算机辅助设计与图形学学报，2009, 21(3): 382-388).
[12]Yuan L，Mu Z C. Ear recognition under partial occlusion based on sub-classificr fusion. Chinese Journal of Scientific Instrument, 2011，32(1):
186-193.(袁立，穆志纯.基于子分类器融合的部分遮挡人耳识别.仪器仪表学报，2011, 32(1):186一193).
[13]Lowe D G. Distinctive image features from scale-invariant key-points. international Journal of Computer Vision, 2004，6(2):91一110.
[14]Dalal N,Triggs B. Histograms of oriented gra- dients for human detection. Proceedings of IEEE Computer Vision and Pattern Recogni-
tion. San Diego, USA，200，1:88一893.
[15]Mu Z C. Ear recognition laboratory at Universi- ty of Science and Technology. Beijing; USTB car image database. http;// www. ustb. edu. cni
resb/subject/subject, htm, 2011一01一10.
[16]Yuan L，Mu Z C, Xu Z G, et al. Personal rec- ognition with car biometrics. Pattern Recogni- tion and Artificial intelligence, 2005，18(3):
310-315.(袁立，穆志纯，徐正光等.基于人耳生物特征的身份识别.模式识别与人工智能，2005，18(3):310一315.
{{custom_fnGroup.title_en}}
Footnotes
{{custom_fn.content}}
PDF(353186 KB)
