A Review of Feature Extraction Methods in Content Based Image Retrieval

Abstract: Image retrieval is an active research area for the last two decades. This area is gaining more importance as the growth of multimedia content over the internet is increasing. Content Based Image Retrieval (CBIR) uses the visual content of images like color, shape and texture for image comparison and retrieval. Compared to the text based retrieval content based image retrieval is used for better accuracy. Content based means search makes use of the visual content of the images. These contents are extracted from the images and are described by multi-dimensional vectors. Similarity measurement and visual feature extraction are two important issues in CBIR. The accuracy of the retrieved images mainly depends on the features extracted. A review of feature extraction methods is present in this paper.

Keywords: Content Based Image Retrieval, Feature Extraction, Color, Shape, Texture.