Today, nearly above 400million of population uses internet. Internet is mostly used for search engines like google, where an individual search for information. Roughly 100million hours of videos are uploaded over internet daily (Viz. YouTube, Netflix, Dailymotion, Vimeo, Veoh, Metacafe, etc.) due to this tremendous amount of data is generated. Semantic/context based search is use which matches fast but only with correct tags. Each and every video is assigned with tags, the desired video is retrieved if and only if correct tags are used. Due to involvement of large number of frames in videos, it is difficult to extract desired video using context based matching. The proposed system is developed to extract desired video from huge data base. Algorithm consists of content based shot detection method and features are extracted for each data set of videos. Further, the frames dissimilarities are analyzed by different parameters like entropy, probability, color, etc. User can search desired video by using image as an input to the system. Proposed system successfully achieved 100% accuracy in content based search. This algorithm also reduces the search time than the existing one that is roughly 0.3ms/video, which is much faster and reliable. Expectation oof system is algorithm fits for content based video search and also gives alternative to context based search (e.g. Netflix, YouTube).

Video retrieval content based matching frames feature vector entropy probability