Surf Based Large Scale Image Retrieval

Image matching is the primary and important process which is mainly used in target tracking, space exploration, 3D reconstruction, modification identification. The existing system is utilizes the Scale Invariant Feature Transform (SIFT) is used to identifying corresponding points becomes difficult in the case of changing illumination or two surfaces with a similar intensity. Image retrieval refers to the searching for digital images in large databases. Generally gray based retrieval method is used. The loss of color information may result in decreasing of matching ratio. SURF is proposed, which adds a color offset and an exposure offset when converting color images to grayscale images in order to enhance the matching ratio. This provides higher efficiency in matching and provides good result.