Ear Biometrics Using 2D and 3D Images
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Force field feature extraction for ear biometrics
Computer Vision and Image Understanding
Using ear biometrics for personal recognition
IWBRS'05 Proceedings of the 2005 international conference on Advances in Biometric Person Authentication
Hi-index | 0.00 |
Personal identification based on the ear structure is a new biometrics. In this paper, a new ear recognition method is proposed. For the purpose of segmentation, we apply the Canny edge detector to the ear image. Then the longest path in the edge image is extracted and selected as the outer boundary of the ear. By selecting the top, bottom, and left point of the detected boundary, we form a triangle with the selected points as its vertices. Further we calculate the barycenter of the triangle and select it as a reference point in all images. Then the ear region is extracted from the entire image using a predefined window centered at the reference point. For the recognition approach, we improve a previous method based on PCA by using 2D wavelet in three different directions and extracting three different coefficient matrices. Experimental results show the effectiveness of our proposed method.