A robust hashing algorithm based on SURF for video copy detection

Abstract

To protect digital video from unauthorized use, video copy detection is an active research topic in the field of copyright control. For content-based copy detection, the key issue is to extract robust transformation-invariant feature. In this paper, a robust hashing algorithm based on speeded up robust feature (SURF) and ordinal measure (OM) is proposed for video copy detection. Since SURF is an invariant feature based on scale space theory, the local feature is extracted by SURF in a frame-by-frame manner. Every frame is divided into 4 × 4 blocks, and every block is traversed by Hilbert-order rasterization to count the number of SURF points. The Hash value is built by the difference of SURF points between adjacent blocks in Hilbert curve. Moreover, two special copy attacks, i.e., picture-in-picture and video flipping, are specifically discussed. Experimental results show the effectiveness of the proposed approach in both accuracy and efficiency.