Adaptive Color Restoration and Luminance MSR Based Scheme for Image Enhancement

A non-linear image enhancement algorithm called Adaptive Color Restoration and Luminance MSR Based Scheme for Image Enhancement (ACRL_MSR) is presented in this paper to improve the visual quality of color images under poor lighting condition. The Red, Green, Blue(R, G, B) color bands are enhanced by adjusting luminance which is automatically enhanced to a proper range based on Human Visual System (HVS) via the adaptive parameter. At the same time the percentage of R, G, B in three bands of the output images is almost as same as the original one to prevent color distortion. The color bands in dark/shadow zones are enhanced partly by luminance and partly by their original color values to make these areas more colorful and natural. The new algorithm is observed from the experiment results, which produces more natural and vivid color than those by MSRCR and LB_MSR.

[1]  Zia-ur Rahman,et al.  Retinex processing for automatic image enhancement , 2004, J. Electronic Imaging.

[2]  Brian V. Funt,et al.  Color Constancy for Scenes with Varying Illumination , 1997, Comput. Vis. Image Underst..

[3]  E. Land.  Recent advances in retinex theory , 1986, Vision Research.

[4]  Vijayan K. Asari,et al.  Modified luminance based MSR for fast and efficient image enhancement , 2003, 32nd Applied Imagery Pattern Recognition Workshop, 2003. Proceedings..

[5]  Brian V. Funt,et al.  Colour Constancy for Scenes with Varying Illumination , 1996, ECCV.

[6]  Zia-ur Rahman,et al.  A multiscale retinex for bridging the gap between color images and the human observation of scenes , 1997, IEEE Trans. Image Process..

[7]  James F. Blinn.  NTSC: nice technology, super color , 1993, IEEE Computer Graphics and Applications.

[8]  Brian V. Funt,et al.  Analysis and Improvement of Multi-Scale Retinex , 1997, CIC.

[9]  Vijayan K. Asari,et al.  Adaptive and integrated neighborhood-dependent approach for nonlinear enhancement of color images , 2005, J. Electronic Imaging.

[10]  C. Munteanu,et al.  Color image enhancement using evolutionary principles and the Retinex theory of color constancy , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[11]  E H Land,et al.  An alternative technique for the computation of the designator in the retinex theory of color vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[13]  E H Land,et al.  Recent advances in retinex theory and some implications for cortical computations: color vision and the natural image. , 1983, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Glenn D. Hines,et al.  Image enhancement, image quality, and noise , 2005, SPIE Optics + Photonics.