Circular trace transform (CTT) is proposed to extract the texture features that are more suitable for describing images containing circular or arc-shaped texture than the ones extracted by Trace Transform. CTT consists of tracing an image with circles around which certain functionals of the image function are calculated. The functional results on the circular trace are mapped to the space generated by three parameters such as radius

length and angle. With functional integral in the results

the image quadruple texture features can be generated. Different circular trace transformations can be obtained by using different compositions of functionals and the quadruple features by CTT can represent different texture properties and deeper intrinsic information of images. It shows better performance on recognizing images with circular or arc-shaped texture in Coil-20 and Brodatz database. In the case of fewer training samples

the recognition capability of the features is obviously improved.