A New Approach for CBIR Using Coefficient of Correlation

An up-to-date comparison of state-of-the-art low-level color and texture feature extraction methods, for the purpose of content-based image retrieval (CBIR) is presented in this paper. The CBIR problem is motivated by the need to search the exponentially increasing space of image and video databases efficiently and effectively. We implement and compare color and texture feature extraction algorithms in this work. Special attention is given to the similarity measurement using correlation coefficient with different distance matrices properties. A New approach for image retrieval technique is proposed to improve retrieval performance, and reduce the extraction search times. The techniques are tested both generally for multi-component images and particularly for isolated color and texture. Finally, matching is performed between the test image and the object image and quality of matching is measured.