A Color-texture Histogram from the HSV Color Space for Video Shot Detection

Color and texture are two important low-level features of a video frame. These features can be used either alone or in combination using appropriate weights for video shot detection. We propose a new soft-decision approach from the HSV color space for modeling combined human visual perception of color and texture in a single feature vector called COLTEX. It shows encouraging results in shot detection for content-based video retrieval applications. We have developed a web-based system for demonstrating our work and for performing user queries.