Video Key Frame Extraction using Entropy value as Global and Local Feature
This addresses video annotation for processing large video datasets more efficiently, but it appears incremental as it builds on existing entropy-based methods.
The paper tackled the problem of video key-frame extraction by proposing a novel approach using entropy values as global and local features to classify frames and eliminate redundancies, with results showing the algorithm successfully helps annotators automatically identify key-frames.
Key frames play an important role in video annotation. It is one of the widely used methods for video abstraction as this will help us for processing a large set of video data with sufficient content representation in faster way. In this paper a novel approach for key-frame extraction using entropy value is proposed. The proposed approach classifies frames based on entropy values as global feature and selects frame from each class as representative key-frame. It also eliminates redundant frames from selected key-frames using entropy value as local feature. Evaluation of the approach on several video clips has been presented. Results show that the algorithm is successful in helping annotators automatically identify video key-frames.