An Approach of Using Free-hand Sketches for Content Based Video Retrieval
Gayathry · 2013
Abstract — In recent years there is an amazing growth in the amount of digital video data. However, as a database grows, the difficulty of finding relevant videos increases. The existing methods for video retrieval are not adequately efficient in terms of performance. With frequent adding and updating of videos in massive databases, it is often not practical to require manual entry of all attributes that might be needed for queries. Therefore we need a better search technique-Content-based video retrieval system. It provides increased flexibility and practical value. It is also useful in providing the ability to query on attributes such as texture or structure or edge of the object that are difficult to represent using keywords. In this paper, I propose a Content Based Video Retrieval (CBVR) system, driven by sketch queries. This system uses sketches for retrieving video clips. The paper is focusing on the gap between the low-level visual features and the high-level semantic meanings.