Retrieval oriented robust image hashing

In order to improve the validity and veracity of image retrieval, an image hashing algorithm based on fractional Fourier transform (FRFT) for content-based image retrieval (CBIR) application is proposed in this paper. By employing FRFT and normalized Hamming distance, a robust hashing sequence is obtained by preprocessing, feature generation and post processing. The orders of FRFT are used as the encryption keys. For illustration, several benchmark images are utilized to show the feasibility of the image hashing algorithm. Experimental results show that the proposed scheme is robust against common image processing such as JPEG compression, mid-filtering, and rotation. Therefore, the scheme proposed in this paper is suitable for CBIR application.