A safe and secured iris template using steganography and cryptography

Abstract

This study combines Cryptography (Twofish and Triple data decryption (3DES)) algorithms and Steganography (Least Significant Bits) to solve the problem of attacking or hacking biometric template for a malicious act, which has become a huge problem in the iris recognition system. Twofish and Triple data encryption are good and secured cryptography algorithms which are used to change readable secret data (plain image) into an unreadable format (cipher image) while least significant bits (LSB) is a steganography algorithm which embeds ciphertext/image directly into a cover image to produce an image known as stego image. In this work, Hough transform, Daugman rubber-sheet model and Log Gabor filter were used for iris image segmentation, normalization and feature extraction and the iris template generated was encrypted using 3DES and Twofish algorithms. The cipher image was then embedded into a cover image to produce stego image using LSB. The result of this work slightly changes the master file after embedding the secret image (stego file) that cannot be identified by the physical eyes and only a JPEG image was used as the master or cover file. The two levels of security technique provide high embedded capacity and eminence stego images that will able to withstand attackers.