Invariant moment features for fingerprint recognition
Liangwei Chen, Chaorong Li · 2013
A method of invariant moment features for fingerprint recognition is proposed based on the global structure of fingerprint. The invariant moment features are calculated on the region of interest (ROI). The ROI is cropped from fingerprint image based on the reference point. Because the invariant moments are invariant under rotation the proposed method calculates the fingerprint features without pre-alignment. The experiments results show the proposed method can extracted discriminative fingerprint feature.