Development of the Content Based Image Retrieval Using Color, Texture and Edge Features

The purpose of this paper is to describe solution to the problem of designing a Content Based Image Retrieval (CBIR) system. CBIR has become an active and fast-advancing research area in image retrieval in the last decade. With the rapid development of computer technology, the amount of digital imagery data is rapidly increasing. There is an inevitable need for efficient methods that can help in searching for and retrieving the visual information that a user is interested in. The manual annotation of images is becoming more and more an infeasible process. An ever flourishing retrieval technique is content based image retrieval (CBIR), where the visual contents found in the images are exploited for representing and retrieving the images. The increased need of content based image retrieval technique can be found in a number of different domains such as Data Mining, Education, Medical, Weather forecasting, Remote Sensing etc. This paper presents the content based image retrieval using features like color, texture and edge histogram. The combinations of these three techniques are used and the Euclidian distance is calculated for the every feature is added and the averages are made. Our software application built using OpenCv with Microsoft visual studio 2010, with an image database. It extracts color, texture and edge features of the input image and images in the database as the basis of comparison and retrieval. Keywords— Content-based image retrieval (CBIR), HSV Color Space, GLCM, EHD.