Content based video retrieval using integrated feature extraction and personalization of results

Traditional video retrieval methods fail to meet technical challenges due to large and rapid growth of multimedia data, demanding effective retrieval systems. In the last decade Content Based Video Retrieval (CBVR) has become more and more popular. The amount of lecture video data on the World Wide Web (WWW) is growing rapidly. Therefore, a more efficient method for video retrieval in WWW or within large video archives is urgently needed. This paper presents an implementation of automated video indexing and video search in large video database and also present personalized results. Proposed system works in three different phases, in the first phase video segmentation and key frame detection is performed to extract meaningful key frames. Secondly, OCR, HOG and ASR algorithms are applied over the keyframe to extract textual keyword. In the third phase, Color, Texture and Edge features are also extracted. Finally, search similarity measure is performed on the extracted features that are saved in SQL database and the output with personalised re-ranking results as per interest is presented to the users.