Feature Matching Process Using Euclidean Distance of Weighted Block Color Histogram and Color Co-Occurrence Matrix for Content Based Image Retrieval System

In the present days, Images are widely used everywhere. The Image retrieval are classified into content based image retrieval that is using image contents such as color, texture, shape and spatial information and context based image retrieval that is using annotated text. Content Based Image Retrieval (CBIR) is a well-known technique for effective image retrieval. The fused features are used to retrieve more similar images from the database. Color histogram is the widely used method to extract color features which is liberates translation, rotation and scaling of image and avoid spatial feature. The color co-occurrence matrix of HSV of a pixel extracts spatial feature. The Proposed CBIR system have a fused feature of weighted 3*3 block color histogram and color co-occurrence matrix. The images in the database are indexed with Feature vectors which are used to increase the speed of retrieval. The Feature Matching process is carried out using Euclidean distance of color histogram and color co-occurrence matrix. Further the images are classified which reduce the number of images in the search space and required number of images is to be retrieved. KeywordsBlock Color histogram, Color co-occurrence Matrix, Content Based Image Retrieval, Euclidean distance, HSV Color space