Content Searching In Videos

Computer Engineering

The large number of video lectures within digital archives is making critical the indexing and retrieval process. Indeed, most of the systems base the indexing process on few generic text information (e.g., course title and teachers name) and this creates problems to students who are looking for very speci_c topics and hence want to browse video in details. Moreover, additional metadata could provide useful information to those users who access the educational materials by means of assistive technologies. In this paper, we propose an approach that allows students to take on-the-y notes while watching a video lecture and uses these notes to enrich video lectures with metadata that will be helpful to the indexing and re-trieval process. To extract the visual information, we apply video content analysis to detect slides and (OCR)Optical Character Recognition to obtain their text and (ASR) Automatic Speech Recognition is used to extract spoken text from the recorded audio. In this paper we present an approach for automated video indexing and video search in large lecture video archives. Firstly, we apply automatic video segmentation and key- frame detection. Then; we apply video Optical Character Recognition (OCR) technology on key-frames to extract textual metadata and Automatic Speech Recognition (ASR) on lecture audio tracks.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.