A comparative study of perceptual hashing algorithms: Application on fingerprint images

Abstract
Perceptual image hashing has been broadly used in the literature to authenticate images or to identify similar contents for image copy detection. It can be used to improve the security of fingerprint-based identification systems, especially to guarantee the authenticity of fingerprint images. In this paper, a comparative study of the most used techniques in the field of perceptual hashing is provided, aiming at evaluating their performance when applied to fingerprint images. The study includes five techniques, namely: A-Hash, D-Hash, P-Hash, WHash and SVD-Hash. The performance has been assessed in terms of perceptual robustness, discrimination capability and authentication characteristics, through extensive experiments. The obtained results are promising and show that overall both the A-Hash and P-Hash performed well when compared to other evaluated techniques.
Description
Keywords
Perceptual hashing; fingerprint images; robust hashing.
Citation