Videogram uses its proprietary technology to index video and extract data from each frame automatically. The automatically extracted data includes metadata of the video , speech (sound), scene data using machine learning vision algorithms, objects in frame (Machine Vision Learning), color, motion, & image similarity. A patented statistical model is used to extract area of interest from all the frames of the video. The output of this model is then used to pack the frames into pictorial summary (similar to a comic book). Videogram is the only platform in the world that does this.