Cromaticity improvement in images with poor lighting using the Multiscale-Retinex MSR algorithm

An important factor when realizing image capture using electronic means (photographic or video camera), is the lighting source type present at the capture moment. If the lighting is deficient, the information present in the image is hidden for the Human Vision System (HVS), such that the color and detail characteristics introduce values with low luminance. As a solution for this lighting problem, the Multiscale-Retinex (MSR) algorithm is proposed, based on the understanding of how the HVS interprets and adapts the perception of colors. This solution can be used as a preprocessing stage to correct the lack of an adequate lighting source like the standard illuminant D65 (light source with similar characteristics to midday sunlight). The MSR algorithm increase the chromatic content of the image, this improves the objects visibility in the scene. The lack effects of lighting are minimized and its magnitude content evaluates the resulting chromaticity vector to characterize the MSR.

[1]  Marius Herscovitz,et al.  A modified Multi Scale Retinex algorithm with an improved global impressionof brightness for wide dynamic range pictures , 2004, Machine Vision and Applications.

[2]  Michael H. Brill,et al.  Color appearance models , 1998 .

[3]  Brian A. Wandell,et al.  Color image fidelity metrics evaluated using image distortion maps , 1998, Signal Process..

[4]  Rahman Zia Properties of a Center/Surround Retinex: Part 1. Signal Processing Design , 1995 .

[5]  John J. McCann,et al.  Retinex in MATLABTM , 2004, J. Electronic Imaging.

[6]  Ajay Kumar,et al.  CONTRAST ENHANCEMENT OF COLOR IMAGES USING IMPROVED RETINEX METHOD , 2014 .

[7]  J. Schanda,et al.  Colorimetry : understanding the CIE system , 2007 .

[8]  Marc Ebner,et al.  Color Constancy , 2007, Computer Vision, A Reference Guide.

[9]  John J. McCann,et al.  Retinex in Matlab , 2000, CIC.

[10]  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..

[11]  Vassilis Tsagaris,et al.  A measure for evaluation of the information content in color images , 2005, IEEE International Conference on Image Processing 2005.

[12]  Carlo Gatta,et al.  From Retinex to Automatic Color Equalization: issues in developing a new algorithm for unsupervised color equalization , 2004, J. Electronic Imaging.

[13]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[14]  Xiao-Ping Zhang,et al.  A novel retinex based approach for image enhancement with illumination adjustment , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).