Sparse Representation Fusion of Fingerprint, Iris and Palmprint Biometric Features

Multimodal Biometric System using multiple sources of information for establishing the identity has been widely recognized. But the computational models for multimodal biometrics recognition have only recently received attention. In this paper multimodal biometric image such as fingerprint, palmprint, and iris are extracted individually and are fused together using a sparse fusion mechanism. A multimodal sparse representation method is proposed, which interprets the test data by a sparse linear combination of training data, while constraining the observations from different modalities of the test subject to share their sparse representations. The images are pre-processed for feature extraction. In this process Sobel, canny, Prewitt edge detection methods were applied. The image quality was measured using PSNR, NAE, and NCC metrics. Based on the results obtained, Sobel edge detection was used for feature extraction. Extracted features were subjected to sparse representation for the fusion of different modalities. The fused template can be used for watermarking and person identification application. CASIA database is chosen for the biometric images.