Textual Metadata Retrieval of Lecture Videos Using Optical Character Recognition

The increase of video lecture data on World Wide Web is rapid therefore an efficient method of data retrieval is needed. So the system providing a method for data retrieval from the lecture video is implemented which will extract the text data. Automatic video segmentation and then key frame detection is applied first. Optical Character Recognition (OCR) Technology is applied to extract the textual metadata. The extracted text data is saved in the form of templates for future reference. The 80 % of accuracy in recognizing the letters from lecture videos is achieved and the extracted information is saved so that the quality of learning is improved.