Perceptual image hashing based on structural fractal features of image coding and ring partition

Perceptual image hashing finds increasing attention in several multimedia security applications. However, reaching the trade-off balance between the two most important properties of image hashing- robustness and discrimination, still remains the most restive challenge in hashing schemes. In this study, a robust image hashing technique is proposed by incorporating ring partition and fractal image coding. The scheme starts by normalizing the image to help in extracting its local features. Then the concept of ring partition is introduced in order to make our hash rotation invariant by dividing the image into 5 different rings to form a secondary image that possesses the invariant property. Further, image coding is introduced by extracting the structural fractal features to exploit dimensionality reduction and compression, hence, generating a robust hash. To ensure the system's security, encryption is performed on the generated fractal elements before the final hash construction. We conduct series of experiments to evaluate the performance of our scheme. The achieved result shows that our scheme is robust against several content-preserving attacks such as image rotation, JPEG compression, gamma correction, gaussian low pass filtering, image scaling, cropping, brightness adjustment and contrast adjustment. In addition, the receiver operating characteristics is used to show the discriminative capability and robustness of our scheme as compared to other state-of-art schemes in the literature.