Content-Based Image Retrieval by the Extraction of Color and Shape Features

Abstract

Content-Based Image Retrieval (CBIR) is the application of computer vision techniques to the image retrieval problem, that is, the problem of searching for digital images in large databases. Due to enormous increase in image database sizes, as well as its vast deployment in various applications, the need for CBIR development arose. The basis of presenting this paper is the retrieval of images based on the color and shape components with SURF descriptors in the query images. The proposed CBIR system, extracts color features using HSV color model and shape features using shape components. The performance of the retrieval system has been analyzed by Precision and Recall. Practical implementations of the above techniques are done using MATLAB. The efficiency of the proposed image retrieval techniques is tested using Caltech- 101 image database.