A Method for Reduced-Reference Color Image Quality Assessment

Most of image quality assessment methods only concern about gray image, and don´t make use of image color information sufficiently at present. A method for reduced-reference color image quality assessment is proposed here, which efficiently uses the color information, performs the spatial domain color difference analysis for components H and S, conducts frequency domain distortion analysis for component I transformed by Contourlet. The final image quality assessment is defined by the weighted combination of three components. The experiments show that the proposed objective method has a good coincidence with the subjective perception, and can reflect the image quality effectively.