Fingerprint Image Watermarking Approach Using DTCWT without Corrupting Minutiae

This paper proposes a new digital watermarking technique for fingerprint images using the Dual-Tree Complex Wavelet Transform (DTCWT). The watermark is embedded into the real and imaginary parts of the DTCWT wavelet coefficients. This work focuses on the study of watermarking techniques for fingerprint images that are collected from different angles without corrupting minutiae points. We investigate the effect of the watermark on the fingerprint features after the watermark embedding process. VeriFinger V5.0 is used to determine the matching score between the template and the watermarked images. The users identity is linked with the fingerprint features to add more authentication factors to the authentication process. The SHA2 hash function is used to encode the user identification number by generating the hash value and convert it into a binary image to construct the watermark data. The original fingerprint image is not required to extract watermark data. The proposed method has been tested using the CASIA fingerprint image database with 500 fingerprint images from 100 persons.