A Survey on CBIR on the Basis of Different Feature Descriptor

Abstract

In this paper we discuss all the CBIR technique and analysis the methods. We also compare all the feature extraction techniques in the tabular form. Color features are extracted with the help of color moments, color histogram, invariant color histogram, and dominant color. Color based CBIR technique there are limitations in the mention method in the table. So we decide to enhance the color based method in the content based image retrieval method. We analysis the all color based method which is used in the proposed method by authors. But color classification methods are not discussed in the above methods. So in the CBIR system if we used the color classification method based on the red, green and blue channel. We easily get the object as well as color. And we also studied various texture and shape based technique that is used by many authors in our research. Texture based various techniques are Gray Level Co-occurrence matrix (GLCM), Gabor Transform and Tamura Features. Texture descriptor provides a measure of properties such as smoothness, roughness, and regularity. The texture of the region is structural, statistical and spectral are three principal approaches used in image processing. Shape features are extracted using many approaches like as Histogram of Edge Directions, Region Moments, invariant Moments, Zernike moments, Legendre Moments.