Video clip retrieval using local phase quantization

The steady rise in use of smart phones equipped with latest features and access to media capturing and editing devices has caused the growth in multimedia content. Videos are a part of multimedia. To harness the information and data present in videos a robust and accurate content based video retrieval system is required. This paper presents a similar video clip retrieval system using texture feature called local phase quantization(LPQ) descriptor. This texture descriptor is formed by taking the histogram of codewords. This codeword is formed by quantizing the phase information computed within a window around each pixel in the image. The use of phase information makes LPQ descriptor robust to illumination and blur variations. Robustness and suitability of the proposed approach is demonstrated by carrying out experiments using videos from TRECVID 2007 dataset.