In real time biometric based authentication environments, wavelet based functions are widely incorporated as one of the promising methods for feature extraction of biometric traits. In this paper, we propose a novel finger knuckle print (FKP) recognition technique based on Haar-Wavelet Transform (HWT). Haar -Wavelet transform is used to transform the original knuckle image into a subset of its feature space known as 'Eigen Knuckle'. The principle components and local space variations are extracted and represented in the form of Eigen vectors. Matching of a knuckle images for personal identification is done by means of a classifier using correlation. Matching scores obtained from various finger knuckles of the same person are fused by means of sum-weighting rule of matching score level fusion. From the exhaustive experiments conducted using two publically available database for FKP, viz. PolyU FKP database and IIT FKP database, it has been found that the proposed HWT based feature extraction algorithm produces high recognition rate when compared to the existing transform based methods of FKP recognition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.