A multi-videos retrieval using adaptive key feature set of shot

In this paper, we provided adaptive key feature sets to describe the content of every shot in video. Return the most similar results to build a multi-video retrieval function. By using K-mean cluster and the gradient histogram of local binary pattern, we respectively transferred video into color and texture features. According to calculated the features distance between continuous frames to detect the shot boundaries of the video. Thus, different shot can be detected. After videos were cut into representative shots, filter and cluster the shots by video analysis function, so that each shot can be more representative. Finally, we could find out the similar results by calculating the distance between query video and video database. In the experimental results, we detected the correct shot boundary. In video retrieval, it can be divided into two ways - the image query videos and the video query videos. The query results showed the similar shot of the target clips.