Abstract A 2D+3D multimodal ear recognition method is proposed. Firstly,ear detection method based on Adaboost algorithm is used to detect ear part on the 2D images,then the corresponding ear part is located and extracted in the 3D range image. For 2D ear recognition,Kernel Fisher Discriminant Analysis is applied for feature extraction and Nearest Neighbor classifier is applied for ear recognition. For 3D ear recognition,3D Local Binary Pattern descriptor is applied for feature extraction on range image,geometric constraint and location constraint are used to perform the matching process between a test ear and a registered protocol ear,and ear recognition performance is evaluated by the number of the matching points. Finally,Bayes decision rule is used for the decision level fusion of 2D and 3D ear recognition classifiers. The experimental results on the UND ear dataset show the effectiveness of the proposed method. In lighting variation scenario,the proposed 2D+3D fusion method outperforms unimodal ear recognition method with 2D images or range images.
[1] Yuan Li,Mu Zhichun. Ear Recognition Based on Local Information Fusion. Pattern Recognition Letters,2012,33(2): 182-190 [2] Yuan Li,Mu Zhichun,Yang Fan. A Review of Recent Advances in Ear Recognition // Proc of the 6th Chinese Conference on Biometric Recognition. Beijing,China,2011: 252-259 [3] Abaza A,Ross A,Hebert C,et al. A Survey on Ear Biometrics. ACM Transactions on Embedded Computing Systems,2010,9(4): 1-33 [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] Guo Mingduo,Mu Zhichun,Yuan Li. Multimodal Ear Recognition Based on 2D+3D Feature Fusion // Proc of the 7th Chinese Conference on Biometric Recognition. Guangzhou,China,2012: 227-234 [6] Xia Xiao. Research on Illumination in Ear Recognition. Master Dissertation. Beijing,China: University of Science and Technology Beijing,2009) (夏 筱.人耳识别中的光照问题研究.硕士学位论文.北京:北京科技大学,2009) [7] Chen Hui,Bhanu B. Human Ear Recognition in 3D. IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29(4): 718-737 [8] Chen Hui,Bhanu B. Efficient Recognition of Highly Similar 3D Objects in Range Images. IEEE Trans on Pattern Analysis and Machine Intelligence,2009,31(1): 172-179 [9] Kakadiaris I A,Passalis G,Toderici G,et al. Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model Approach. IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29(4): 640- 649 [10] Chen Leilei,Wang Bin,Zhang Liming. Fast 3D Ear Extraction and Recognition. Journal of Computer-aided Design and Computer Graphics,2009, 21(10): 1438-1445 (in Chinese) (陈雷蕾,王 斌,张立明.快速三维人耳提取与识别.计算机辅助设计与图形学学报,2009,21(10): 1438-1445) [11] Yan Ping,Bowyer K W. Multi-Biometrics 2D and 3D Ear Recognition // Proc of the 5th International Conference on Audio and Video Based Biometric Person Authentication. Hilton Rye Town,USA,2005: 503-512 [12] Yuan Li,Zhang Feng. Ear Detection Based on Improved Adaboost Algorithm // Proc of the International Conference on Machine Learning and Cybernetics. Baoding,China,2009,IV: 2414-2417 [13] Huang Yonggang,Wang Yunhong,Tan Tieniu. Combining Statistics of Geometrical and Correlative Features for 3D Face Recognition // Proc of the British Machine Vision Conference. Edinburgh,UK,2006: 879-888 [14] Yuan Li,Mu Zhichun,Zeng Hui. Multimodal Recognition Using Face and Ear. Journal of University of Science and Technology Beijing,2007,29(S2): 190-193 (in Chinese) (袁 立,穆志纯,曾 慧.基于人脸和人耳的多模态生物特征识别.北京科技大学学报,2007,29(S2): 190-193) [15] Ross A A,Nandakumar K,Jain A K. Handbook of Multibiometrics. New York,USA: Springer-Verlag,2006
图5 核Fisher鉴别分析算法流程图 Fig.5 Diagram of the Kernel Fisher Discriminant Analysis algorithm
2013, Vol. 26 
