Group-Based Image Retrieval Method for Video Annotation

This paper proposes a group-based image retrieval methodology for video annotation systems. Although the wide spread use of video camera recorders has increased the demand for an automated annotation system for personal videos, conventional image retrieval methods cannot achieve enough accuracy to be used as an annotation engine. Personal video´s degraded image makes the retrieval task difficult. To cope with this difficulty, this paper proposes a group-based image retrieval method. Its characteristics are 1) the use of Earth Mover´s Distance on wavelet- based image features, and 2) the pre-grouping of related images and screening using group information. Experimental results show that the proposed method can improve image retrieval accuracy to 70% up from the conventional method of 15%.