Web Based Audio-Video Information Summarization Algorithm (AVISA) for Videos and Audios
The rapid development of audio as well as video data needs vigorous, proficient, and scalable systems to permit for indexing as well as retrieval. These systems should be easily reached from insubstantial, convenient as well as usable interfaces to aid users in management, search of video as well as audio content. As a result there is an enormous need of audio and video retrieval systems, since users change from text based retrieval systems to content based retrieval systems. In this research, provide a novel video as well as audio summarization to organization of audio as well as videos that robotically process video producing a Video Table of Contents (VToC), when offering easy-to-use interfaces for confirmation, rectification and increase of the mechanically taken out video structure. The presented Audio-Video Information Summarization Algorithm (AVISA) encompasses three main steps. The primary step is accountable for automatic organization of videos. It mainly concentrates on the taking out of Video Key Frame Indexing, Color, Texture, audio features, and son on utilized for AVISA. The second steps maintain the structure as a VToC in eXtensible Markup Language (XML) format, and provides the VToC on the Web with eXtensible Stylesheet Language (XSL). The final one gives user’s choices to customize a video into its summary with the help of Fuzzy C Means (FCM) based clustering. On summarization, the model data of the videos is categorized to its identical videos by utilizing a least distance. The performance of this system is assessed by means of utilizing videos for the period of the summarization.
Author's Name: N.Srinivas and Dr. M.V.Ramana Murthy
Volume: Volume 14
Issues: Issue 3
Keywords: Video Table of Contents (V-ToC), Audio-Video Information Summarization Algorithm (AVISA), summarization, clustering, Fuzzy C Means (FCM) and features.