Spectral image distortion map

In this paper, a novel technique of spectral image quality evaluation using spectral image distortion map (SIDM) is proposed. The method is based on a recent approach to evaluation of color differences in a spectral space. What is calculated here, in fact, is a pixelwise spectral distortion. As the measure of the dissimilarity, a novel kernel based similarity measure is used. The metric produces comparable values of differences for perceptually equally disparate colors. As a result, a grayscale spectral distortion image is obtained, where the intensity of each of the pixels is a difference between the original image and the distorted one. A perceptual image distortion map (PIDM) has also been constructed to show the accuracy of SIDM. A comparison of PIDM and SIDM shows that the latter provides an excellent fit to the response of the human visual system.

[1]  Michael J. Ryan,et al.  A suitable distortion measure for the lossy compression of hyperspectral data , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[2]  T Troscianko,et al.  Color and luminance information in natural scenes. , 1998, Journal of the Optical Society of America. A, Optics, image science, and vision.

[3]  Brian A. Wandell,et al.  Image Distortion Maps , 1997, Color Imaging Conference.

[4]  Arto Kaarna,et al.  Blockwise distortion measure for lossy compression of multispectral images , 2000, 2000 10th European Signal Processing Conference.

[5]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[6]  Jussi Parkkinen,et al.  Color Differences in a Spectral Space , 2003, PICS.

[7]  Yee Leung,et al.  Spatial Analysis and Planning under Imprecision , 1988 .

[8]  Arto Kaarna,et al.  Quality Metric for Multispectral Image Compression , 2002 .

[9]  Michael Hild,et al.  Which Color Similarity Measure is Most Effective for Background-Frame Differencing? , 2001, Color Imaging Conference.

[10]  Michael Hild.  On the Effectiveness of Color Similarity Measures in Background-Frame Differencing Applications , 2002, CGIV.