Image Similarity Measure using Color Histogram, Color Coherence Vector, and Sobel Method

Kalyan Roy, Joydeep Mukherjee

Abstract: Image Retrieval means searching, browsing, and retrieving the images from an image database. Two different methods are used for image retrieval, namely text based image retrieval and content based image retrieval techniques. But now Text based search technique is old one. In Content Based Image Retrieval many visual feature like color, shape, and texture are extracted, next when we query an image its feature are compared with the stored feature and we get most similar kind of image. In our proposed method we firstly extract low level image feature like- color histogram, color coherence vector. Then we add edge detection technique sobel edge detection method to get better output. Finally we use Manhattan distance to find the similar images from our database.

Keywords: Histogram, Color Coherence Vector, Sobel Edge detection method, Manhattan distance