Image retrieval using a fractal signature extraction technique

Content-based image retrieval has become a reliable tool for digital image applications. There are several advantages of the image retrieval techniques compared to other simple retrieval approaches such as text-based retrieval techniques. This paper proposes a new method for color image retrieval, suitable for color image databases. It is based on a fractal scanning technique, which is used to extract signatures for each one of the RGB color components. Features extracted from these signatures are next used for image comparison and retrieval. The system is suitable for retrieving query images even in distortion cases such as deformations, noise, color reduction and smoothing.