Abstract: Recently advanced development in multimedia technology allows the capturing and storing of video data with highly expensive computers. Further, the new opportunities offered by the information technology have made a vast collection of video data publicly available. But still, without proper search techniques these all data are hardly usable. Users are not well satisfied with the video retrieval systems which provide analogue VCR functionality. For example, a user analyses a football video will ask for specific events likewise goals. Content-based search and retrieval of video data becomes a challenging and important problem now a day. So, the needs for tools that can be used to manipulate the video content as in traditional databases manage numeric and text content is significant. Therefore, a more efficient way towards video retrieval in World Wide Web or within large lecture video archives is urgently required. This research presents an approach for automated video content retrieving over large lecture video archives. First of all, It apply automatic video segmentation and key-frame detection to offer a visual guideline for the video content navigation. Subsequently, It extract textual metadata by applying video Optical Character Recognition (OCR) technology algorithm on key-frames and Automatic Speech Recognition on lecture audio tracks content of the video. Proposed algorithm Multimedia question information retrieval is to provide a multimedia data such as image and video for extracted words in OCR method. The multimedia search diversification method helps to collect the appropriate answer based on words. It provides relevant information i.e. text, audio, video to the user for more effectiveness.

Keywords: Questing Answering, multimedia search, reranking, video segmentation, video browsing, video retrieval, video structure analysis, OCR, API.