Perceptual hashing technique for tamper detection has been intensively investigated owing to the speed and memory efficiency.\nRecent researches have shown that leveraging supervised information could lead to learn a high-quality hashing code. However,\nmost existing methods generate hashing code by treating each region equally while ignoring the different perceptual saliency\nrelating to the semantic information. We argue that the integrity for salient objects is more critical and important to be verified,\nsince the semantic content is highly connected to them. In this paper, we propose a Multi-View Semi-supervised Hashing\nalgorithm with Perceptual Saliency (MV-SHPS),which explores supervised information andmultiple features into hashing learning\nsimultaneously. Our method calculates the image hashing distance by taking into account the perceptual saliency rather than\ndirectly considering the distance value between total images. Extensive experiments on benchmark datasets have validated the\neffectiveness of our proposed method.
Loading....