An Automated Analysis and Indexing Framework for Lecture Video Portal

This paper presents an automated framework for lecture video indexing in the tele-teaching context. The major issues involved in our approach are content-based lecture video analysis and integration of proposed analysis engine into a lecture video portal. In video visual analysis, we apply automated video segmentation, video OCR (Optical Character Recognition) technologies for extracting lecture structural and textual metadata. Concerning ASR (Automated Speech Recognition) analysis, we have optimized the workflow for the creation of a German speech corpus from raw lecture audio data. This enables us to minimize the time and effort required for extending the speech corpus and thus improving the recognition rate. Both, OCR and ASR results have been applied for the further video indexing. In order to integrate the analysis engine into the lecture video portal, we have developed an architecture for the corresponding tasks such as, e.g., data transmission, analysis management, and result visualization etc. The accuracy of each individual analysis method has been evaluated by using publicly available test data sets.