Group-Based Image Retrieval Method for Video Image Annotation

Abstract

This paper proposes a group-based image retrieval method for video image 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. Recording conditions, such as change of the brightness by weather condition, shadow by the surroundings, and etc, affect the qualities of images recorded by the personal video camera recorders. The degraded image of personal video makes the retrieval task difficult. Furthermore, it is difficult to discriminate similar images without any auxiliary information. To cope with these difficulties, this paper proposes a group-based image retrieval method. Its characteristics are
1) the use of image similarity based on the wavelet transformation based features and the scale invariant feature transform based 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 90% up from the conventional method of 40%.