Querying Images by Content Using Color, Texture and Shape

Abstract The existing system uses a keyword to search an image. Suppose we have to search for an image of an apple, keyword should be ?apple? & images related to apple will be displayed accordingly. These images are stored in a database and are displayed according to the keywords. The objective is to extract visual content of an image automatically like color, texture and shape. In proposed system, the user input a query image and then the system extracts the image feature and measure the distance with images in the database. An initial retrieval list is generated. The user can choose the relevant image to further refine the query and this process can be iterated many times until the user find the desired images. In this, the color is retrieved using RGB color space and histogram method. The edge detection method is used for finding shape or edges of an image. The Euclidean Distance is used for similarity measure between query image and database images. Finally, images are successively retrieved for query image.