Survey on Sketch based Image Retrieval

CBIR is stand for Content based image retrieval. It is one of the most popular, rising research areas of the digital image processing. Now-a-days the available image search tools, such as Google Images and Bing, Yahoo. Image search, are based on textual annotation of images. In these tools, images are manually commented with keywords and then they are recovered using text-based search methods. The performance of the system is unsatisfactory. The goal of CBIR is to extract the visual content of an image automatically such as color, texture, or shape with the help of the existing methods, describe a possible remedy of how to design and implement a task specific descriptor, which can bridge the informational gap between a sketch and image, hereby making an opportunity for the efficient search. CBIR system is mainly based on a free hand sketch, Sketch based image retrieval. The SBIR is used to construct a special sequence of preprocessing steps in such a way that the transformed full color image and the sketch can be compared. We present an efficient approach for image retrieval from number of images based on user-drawn sketches. We concentrate on the creative ideas instead of symbols to deliver their thoughts. However, most of the current graphics constructing tools require users to input graphical components using mouse with lots of toolbar buttons or menu items for selection.