Efficient Image Retireval Using Region Based Image Retrieval

Early image retrieval techniques were based on text\udual annotation of images. Manual annotation of images \udis a burdensome and expensive work for a huge image\ud database. It is often introspective, context-sensitive \udand crude. Content based image retrieval, is implem\udented using the optical constituents of an image such \udas shape, colour, spatial layout, and texture to ex\udhibit and index the image. The Region Based Image \udRetrieval (RBIR) system uses the Discrete Wavelet Transform (DWT) and a k-means clustering algorithm \udto segment an image into regions. Each region of th\ude image is represented by a set of optical \udcharacteristics and the likeness between regions an\udd is measured using a particular metric function on\udsuch characteristics