Abstract: Shot segmentation is very important for video retrieval based on image content. In
order to improve the performance of shot segmentation, Harris operator is adopted to evaluate the
energy of image pix, and exclude pseudo feature points. By means of partition of frame in the
video into blocks and edge detection of the blocks, the minimal feature-point set is obtained and
the feature points are made relatively well-distributed. And then according to the feature points,
statistical quantity of frame in video is computed to construct feature vector to express the frame.
Based on above, along with gradual transition detection and flash detection of frame, a method of
shot segmentation is presented. Experiments of shot segmentation are efficient.

Key words: Harris operator, feature extraction, flash detection, gradual transition detection;
shot segmentation