Template Matching Approach for Pose Problem in Face Verification
In this paper we propose a template matching approach to address the pose problem in face verification, which neither synthesizes the face image, nor builds a model of the face image. Template matching is performed using edginess-based representation of face images. The edginess-based representation of face images is computed using one-dimensional (1-D) processing of images. An approach is proposed based on autoassociative neural network (AANN) models to verify the identity of a person using score obtained from template matching.
KeywordsFace Recognition Face Image Template Match True Class Equal Error Rate
Unable to display preview. Download preview PDF.
- 5.Sao, A.K.: Significance of image representation for face recognition. Master’s thesis, Department of Computer Science and Engineering, Indian Institute of Technology, Madras (2003)Google Scholar
- 7.Black, J., Gargesha, M., Kahol, K., Kuchi, P., Panchanathan, S.: A framework for performance evaluation of face recogniton algorithm. In: Internet Multimedia System, Boston (2002)Google Scholar
- 8.Little, G., Krishna, S., Black, J., Panchanathan, S.: A methodology for evaluating robustness of face recognition algoritms with respect to change in pose and illumination angle. In: ICASSP, Philadelhia (2005)Google Scholar
- 9.Kumar, B.V.K.V., Savvides, M., Venkataramani, K., Xie, C.: Spatial frequency domain image processing for biometric recognition. In: IEEE Int. Conf. Image Processing, New York, pp. 53–56 (2002)Google Scholar