FLIP-INVARIANT VIDEO COPY DETECTION USING SPARSE-CODED FEATURES

Abstract

Now a days, a number of videos are available in video databases, social networking sites and other web servers. Large size of these video database make it difficult to trace the video content. To ensure the copy-right of the videos in video database, a video copy detection system is needed. A Video copy detection system stores the video features that characterize a video along with the video in the database. Existing copy detection systems store the video features as simple codewords. A simple and compact representation of video features makes the system more efficient. Moreover, the memory constraint problem can also be solved. This paper propose a sparse-coding technique that can represent the video features as sparse-codes. Proposed video copy detection system using sparse-codes works as follows: keyframes of the videos in the database are extracted using abrupttransition detection algorithm. Salient regions of keyframes are detected by Harris-Laplacian detector and its local features are described by Flip-Invariant SIFT(F-SIFT) descriptor. F-SIFT enriches SIFT with flip invariance property by preserving its feature distinctiveness. F-SIFT is invariant to operations like flip, rotation, scale etc. A 128-Dimensional F-SIFT descriptor is extracted from each salient region. Extracted descriptors are converted to sparse-codes by the proposed sparse-coding technique. Each keyframe is represented by the sparse feature vector. Sparse vectors of all the keyframes of a video forms the sparse code of the video. Sparse-codes of the input video are compared with the sparse-codes stored in video database to identify the near duplicate videos. Experimental results demonstrate that proposed sparse-coding technique reduces the memory constraint problem. It also improves the detection accuracy.