FPGA Verification of the Video Retrieval System using MPEG-7 Visual Descriptors

Multimedia is rapidly spreading due to the increasing number of application fields and Internet technologies. The development of a retrieval system is urgently needed to retrieve the demanded information by users. Image information is widely used for the contentbased retrieval of moving pictures. It is mainly used to segment a video by scene. The process that divides video into shots is called “video segmentation”. For the video segmentation, detecting cuts which are turn point of scene is called “cut detection”. In this paper, for the video segmentation, we use two MPEG-7 visual descriptors; HMMD (HueMax-Min-Diff) color model and the EHD (Edge Histogram Descriptor). The goal of this paper is to implement the retrieval system as hardware. It is designed by Verilog HDL. We perform the FPGA verification, and implement the retrieval system for the moving picture.