A novel image copy detection scheme based on the local multi-resolution histogram descriptor

The conventional research on the image copy detection concentrates on extracting features which are robust enough to resist various kinds of image attacks. However, the global features are sensitive to geometric attacks, especially cropping and rotation, while the local features cannot substantially represent the image spatial information and structure context. Instead of simply extracting feature from local region or global image directly, we propose a novel image copy detection scheme based on Scale Invariant Feature Transform (SIFT) detector and multi-resolution histogram descriptor (MHD). In this novel algorithm, a series of robust, homogenous and large size circular patches are firstly constructed using the SIFT detector, and then the MHD is introduced to generate a discriminative feature vector for each patch. Experimental results obtained from the benchmark attacks demonstrate that the performance of the proposed approach is better than existing methods, especially on the test against geometric distortions.