A New Approach for Fingerprint Matching Based on Singular Points Detection

摘要

In this paper, we introduce a new approach, using combined feature for fingerprint matching. Our proposed approach is the idea that this feature combines the information of every two singular points such as core and delta, of the image and takes the ridges structure between them into account. The combined feature is invariant with respect to the global transformations such as rotation and transformation. The proposed recognition is performed in three steps: singular points extraction, combined features extraction and matching. Experimental results on FVC2006 show efficiency and accuracy of the proposed method.