Abstract
The study of image-based retrieval when the database consists of videos becomes a very challenging task. This variation of visual search is important for a broad range of applications that require indexing video databases based on their visual contents. Our paper presents the search of a database based on broadcasting news. The main agenda of this paper is to retrieve the data of a particular shot of a video and compare it with a part of broadcast news and check its occurrence in the broadcast news video. Outnumbering different algorithms we have come up with an efficient way of retrieving the data. In this paper, we have first extracted the frames for a particular segment of video and converted each frame to binary form and detected the edges of each frame using the edge detection method, and stored the no of edges detected into arrays for the video shot as well as the broadcast news. For the rectification, we have checked the edge similarity between the detected edge of the particular video shot and broadcast news. To refine our algorithm of edge similarity, we have also performed SSIM to achieve the most desired results. Moreover, as the commercial frames may occur more than once in broadcast news we can have an analysis of the no of times of occurrence of commercials shot in broadcast news.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
