Correction of the overexposed region in digital color image

The overexposure usually occurs in the digital image due to the limited dynamic range of the low dynamic range (LDR) displays. In this paper, we propose a novel method to correct the overexposed region in the image, which consists of the lightness recovery and the color correction. In the proposed method, the lightness in the overexposed region is modeled as a two-dimensional Gaussian function, and a new energy functional of both the Gaussian modeled lightness and the gradients of the original image is minimized to recover the lightness. For correcting the color, we apply the bilateral filter with weights obtained using the recovered lightness to the color of the overexposed region. The algorithm's performance is experimentally compared to state-of-the-art algorithm, demonstrating comparable or favorable results.

[1]  Peter Zolliker,et al.  Retaining Local Image Information in Gamut Mapping Algorithms , 2007, IEEE Transactions on Image Processing.

[2]  Kun Zhou,et al.  Fast example-based surface texture synthesis via discrete optimization , 2006, The Visual Computer.

[3]  M. Werman,et al.  Color lines: image specific color representation , 2004, CVPR 2004.

[4]  Xuemei Zhang,et al.  Estimation of saturated pixel values in digital color imaging. , 2004, Journal of the Optical Society of America. A, Optics, image science, and vision.

[5]  J. Shewchuk An Introduction to the Conjugate Gradient Method Without the Agonizing Pain , 1994 .

[6]  Kun Zhou,et al.  High dynamic range image hallucination , 2007, SIGGRAPH '07.

[7]  Rae-Hong Park,et al.  High dynamic range for contrast enhancement , 2006, IEEE Transactions on Consumer Electronics.

[8]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[9]  Rae-Hong Park,et al.  Tone mapping using color correction function and image decomposition in high dynamic range imaging , 2010, IEEE Transactions on Consumer Electronics.

[10]  Laurence Meylan,et al.  High dynamic range image rendering with a retinex-based adaptive filter , 2006, IEEE Transactions on Image Processing.

[11]  Yuan Cheng,et al.  Correcting over-exposure in photographs , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Michael Werman,et al.  Recovering Color and Details of Clipped Image Regions , 2010 .

[13]  Joseph Gil,et al.  Linear Time Euclidean Distance , 1995 .

[14]  Yeo-Jin Yoon,et al.  Correction of the overexposed region in digital color image , 2014, IEEE Transactions on Consumer Electronics.

[15]  Jiejie Zhu,et al.  Automatic Correction of Saturated Regions in Photographs using Cross‐Channel Correlation , 2009, Comput. Graph. Forum.

[16]  Dani Lischinski,et al.  Gradient Domain High Dynamic Range Compression , 2023 .