An improved and efficient implementation of CBIR system based on combined features

In image processing, computer vision and pattern recognition, the Image retrieval is a most popular research area. Our paper presented a novel approach in content-based image retrieval (CBIR) by combining the low level feature i.e. color, texture and shape features. At first, we are transforming the color space from RGB model to HSV model, and then extracting color histogram to form color feature vector. Next, extracting the texture feature by using Block Difference of Inverse Probabilities (BDIP) and Block-Based Local Correlation (BVLC) moment. At last, we are applying Canny edge detection to extract the shape features. Finally, we combined the color, texture and shape features to form the feature vectors of the entire image. Experiments results show that the proposed scheme has a very good performance in respect of the precision and recall when compared with other methods.