Fast Search for Large Video Database using Adjacent Pixel Intensity Difference Quantization Histogram

F. Lee, K. Kotani, Q. Chen, and T. Ohmi (Japan)


Video search, Histogram feature, Adjacent pixel intensity difference quantization, Active search


In this paper, we present a fast video search algorithm for large video database. This algorithm is based on the adjacent pixel intensity difference quantization (APIDQ) algorithm, which had been reliably applied to human face recognition previously. The proposed search algorithm has been evaluated by 6 hours of video to search for 200 video clips. Experimental results show the proposed algorithm can detect the similar video clip more accurately and about 7 times faster than conventional fast video search algorithm.

Important Links:

Go Back