Locally Linear Embedding and Its Improved Algorithm for Multi-Pose Ear Recognition
XIE Zhao-Xia1, MU Zhi-Chun1, XIE Jian-Jun2
1.School of Information Engineering, University of Science and Technology Beijing, Beijing 100083 2.School of Mechatronics Engineering, Henan University of Science and Technology, Luoyang 471003
Abstract The current methods for ear recognition are discussed, and locally linear embedding (LLE) is employed to deal with multi-pose ear recognition. An improved locally linear embedding algorithm is presented. The improved LLE algorithm selects the neighbors according to the Hsim function, thus the instability of the neighbors in the higher dimensional space is well avoided. Experimental results demonstrate that LLE is feasible for multi-pose recognition and it has obvious advantages. Moreover, the improved LLE obtains a better recognition rate for multi-pose ear recognition.
[1] Mu Zhichun, Xi Dechun, Xu Zhengguang, et al. Ear Feature Extraction Combining the Shape Feature of Outer Ear with the Structure Feature of Inner Ear. Journal of University of Science and Technology Beijing, 2006, 28(5): 497-500 (in Chinese) (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): 497-500) [2] Middendorff C, Bowyer K W, Yan Ping. Multi-Modal Biometrics Involving the Human Ear // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 1-2 [3] Chen Hui, Bir B. Human Ear Recognition in 3D. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(4): 718-737 [4] Yan Ping, Bowyer K W. Biometric Recognition Using 3D Ear Shape. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(8): 1297-1308 [5] Yuan Li, Mu Zhichun, Zhang Yu, et al. Ear Recognition Using Improved Non-Negative Matrix Factorization // Proc of the 18th International Conference on Pattern Recognition. Hongkong, China, 2006, Ⅳ: 501-504 [6] Iannarelli A. Ear Identification. Fremont, USA: Paramount Publishing Company, 1989 [7] Moreno B, Aánchez , Vélez J. Use Outer Ear Images for Personal Identification in Security Applications // Proc of the IEEE 33rd Annual International Carnahan Conference on Security Technology. Madrid, Spain, 1999: 469-476 [8] Burge M, Burge W. Ear Biometrics in Computer Vision // Proc of the 15th International Conference of Pattern Recognition. Barcelona, Spain, 2000, Ⅱ: 822-826 [9] Hurley D J, Nixon M S, Carter J N. Force Field Feature Extraction for Ear Biometrics. Computer Vision and Image Understanding. 2005, 98(3): 491-512 [10] Wang Zhongli, Mu Zhichun, Wang Xiuyan, et al. Ear Recognition Based on Moment Invariants. Pattern Recognition and Artificial Intelligence, 2004, 17(4): 502-505 (in Chinese) (王忠礼,穆志纯,王修岩,等.基于不变矩匹配的人耳识别.模式识别与人工智能, 2004, 17(4): 502-505) [11] Yan Ping, Bowyer K W. Empirical Evaluation of Advanced Ear Biometrics // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, Ⅲ: 41 [12] Yand M H. Kernel Eigenfaces vs Kernel Fisherfaces: Face Recognition Using Kernel Methods // Proc of the 5th IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 215-220 [13] Zhang Junping, Shen Huanxing, Zhou Zhihua. Unified Locally Linear Embedding and Linear Discriminant Analysis Algorithm (ULLELDA) for Face Recognition // Proc of the 5th Chinese Conference on Biometric Recognition. Guangzhou, China, 2004: 296-304 [14] Yuan Li. Study on Some Key Issues in Ear Recognition. Ph.D Dissertation. Beijing, China: University of Science and Technology Beijing. Department of Automation, 2006 (in Chinese) (袁 立.人耳识别中若干关键问题的研究.博士学位论文.北京:北京科技大学.自动化系, 2006) [15] Seung H S, Daniel D L. The Manifold Ways of Perception. Science, 2000, 290(5500): 2268-2269 [16] Zhou Zhihua, Wang Jue. Machine Learning and Applications 2007. Beijing, China: Tsinghua University Press, 2007 (in Chinese) (周志华,王 珏.机器学习及其应用2007.北京:清华大学出版社, 2007) [17] Roweis S T, Saul L K. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science, 2000, 290(5500): 2323-2326 [18] Saul L K, Roweis S T. Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifolds. Journal of Machine Learning Research, 2003, 4(2): 119-155 [19] Yin Junsong, Hu Dewen, Zhou Zongtan. Growing Locally Linear Embedding for Manifold Learning. Journal of Pattern Recognition Research, 2007, 2(1): 1-16 [20] Varini C, Degenhard A, Nattkemper T W. ISOLLE: LLE with Geodesic Distance. Neurocomputing, 2006, 69(13/14/15): 1768-1771 [21] Yang Fengzhao. The Research on a Few Key Issues in High Dimensional Data Mining. Ph.D Dissertation. Shanghai, China: Fudan University. Department of Computer and Information Technology, 2003 (in Chinese) (杨风召.高维数据挖掘中若干关键问题的研究. 博士学位论文.上海: 复旦大学.计算机与信息技术系, 2003) [22] Yang Fengzhao, Zhu Yangyong. An Efficient Method for Similarity Search on Quantitative Transaction Data. Journal of Computer Research and Development, 2004, 41(2): 361-368 (in Chinese) (杨风召,朱扬勇.一种有效的量化交易数据相似性搜索方法. 计算机研究与发展, 2004, 41(2): 361-368)
2009, Vol. 22 
