Content Based Image Retrieval in Art Collection Using Edbtc

Abstract

Image retrieval has been one of the most interesting and vivid research areas in the field of computer vision. Content-based image retrieval (CBIR) systems are used in order to automatically index, search, retrieve and browse image databases. Color and texture features are important properties in content-based image retrieval systems. Content Based Image Retrieval is an important technique which uses visual contents to retrieve images from large database. Many traditional methods have been employed to retrieve images. Significance feedback is often a critical component when designing image databases. Relevance feedback interactively determines the user’s query by asking the user whether image is relevant or not. The project depicts the retrieval of images from a database using texture, shape and color features of a image. The size of an output image is reduced to (64x64) from the input size is of (256x256) through minimum and maximum quantifier. CCF is used to extract the color factors. EDBTC and BPF are used to extract the shape of the image. Garbor wavelet is used to extract the texture of the image. Images are retrieved using similarity measures through Euclidean distances. The main purpose is to extract the image factors using EDBTC to reduce the size of data stream without altering the image quality and offers indexing of images.