Clustering and Retrieval of Tele -Lecture Content

Ashwini Y. Kothawade, Prof. Dipak R. Patil

Abstract: Nowadays video lecturing is becoming popular due to its various advantages than classroom learning. Many institutes and organizations are using this method for learning. So there is an enormous amount of data available in video lecturing form. To extract the exact video and exact information through this collection of information from videos is a tedious task. In this paper we introduce the techniques for automatically retrieving the information from video files to collect it as a metadata for those files. For efficient retrieval of text from videos we use the OCR (Optical Character Recognition) tool to extract text from slides and ASR (Automatic Speech Recognition) tool for retrieval of speech information by the speaker. First of all we do segmentation and classification of video files for extracting the key frames. Then the OCR and ASR tool is used for collecting the information and it will be stored as a metadata for the file. At last, we provide the efficient browsing for these videos by using the clustering and ontology concept.

Keywords: OCR, ASR, Content retrieval, e-learning, tele-lecture, tesseract OCR, indexing to video lectures