Retrieval of Images Based on Texture and Color Features

Content-based image retrieval (CBIR) is a new but widely espoused method for finding images from enormous image databases. The need of content based image retrieval technique is in different domains such as medical imaging, crime prevention, weather forecasting, surveillance, historical research and remote sensing. This paper presents the content based image retrieval, using texture and color features. The different features are extracted and the effectiveness of content based image retrieval can be increased. The proposed system has confirmed a faster retrieval method on a COREL image data base and CASIA image database containing 1000 color images and medical images respectively. The performance of this proposed method is evaluated using color image and medical image database and measured using average precision, average recall. The experimental result shows this proposed method has accomplished the highest retrieval rate.