A Robust Image Hashing Method Based on Zernike Moments
Yan Qing Zhao, Shuozhong Wang, Guorui Feng, Zhenjun Tang · 2010
Image hashing maps an image to a short binary sequence representing the image’s characteristics. 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 corrected phases of Zernike moments. Similarity between hashes is measured with the Hamming distance. Experimental results show that the scheme is robust against most content-preserving attacks. Hashes between pairs of different images have low collision probability. The Zernike moment based image hash can be used to detect forged images containing inserted foreign areas.