Research Article Open Access

CHAOTIC NEURAL NETWORK BASED HASHING ALGORITHM FOR IMAGE AUTHENTICATION

Abstract

A robust hashing method is developed for detecting forgery in images including removal, insertion, replacement of objects, abnormal color modifications and for locating the forged area. The hash sequence is formed by concatenating both the global and local features of the image. The global features are based on Zernike moments representing the luminance and chrominance characteristics of the image. The local features are based on position and texture information of the salient regions in the image. Secret keys are generated from the biometric image. Keys are protected by passing it through the chaotic neural network. These keys are used in feature extraction and hash construction. The generated hash is sensitive to tampering and hence it is used for image authentication. The hash of test image is compared with the hash of a reference image. When the hash distance is greater than a threshold t1 and less than t2, the received image is judged as a fake. By decomposing the hashes the type of image forgery and location of forged areas can be determined.

Dr.M.Ramakrishnan, R.Sujatha, S.B.Sony Thangam

To read the full article Download Full Article | Visit Full Article