Detection Technique for Image Forgery from Global and Local Features Using Hashes

A defective method or a robust hashing method is developed for detecting forgery which includes removal, insertion and replacement of objects and abnormal color modifications and locating the forged area, and tells the nature of forgery. This undesirable method is used both globally and locally. The local feature represents position and texture information of salient regions in the image, and its generates secret keys in the image. The global features are based on Zernike moments representing luminance and chrominance characteristics of the image as a whole. The hash test is compared with that of reference image. When the hash distance is different from the entrance values T1 and T2 the received image is judged as fake. T1 andT2 represent the threshold values. By decomposing the hashes the forgery and location can be determined. The experimental results are presented to producing favorable result effectiveness of the method.