A Novel Approach for Image Authentication by Robust Hashing Using Zernike Moments and Local Features

Image hashing maps an image to a short binary sequence representing the image characters. This paper proposes a new image hashing method using Zernike moments that are an effective means for extracting robust features from an image. The method is based on rotation invariance of magnitudes and correct phases of Zernike moments and detecting image forgery including removal, insertion, and replacement of objects, and abnormal color modification, and for locating the forged area. We use Zernike moments of the luminance/chrominance components to reflect the image’s global characteristics, and extract local texture features from salient regions in the image to represent contents in the corresponding areas. Distance metrics indicating the degree of similarity between two hashes and defined to measure the hash performance. Two thresholds are used to decide whether a given image is an original/normal-processed or maliciously doctored version of a reference image, or is simply a different image. The method can be used to replacement of objects or abnormal modification of colors. Probability of collision between hashes of different images approaches zero. Experimental results are presented to show effectiveness of the method.