為了使影像的顯示能夠更接近人類視覺的感受，各種影像強化演算法已被廣泛地研究，而整體來說，影像強化演算法可分為全域性及區域性兩方面。在這篇論文中我們提出一個創新的影像強化流程，其主要包含雙邊色調調整和突出區域對比增強兩部分。和其他以曲線為基礎來做全域性影像增強的演算法相比，雙邊色調調整不僅能強化過亮及過暗的區域，同時也能強化通常包含許多重要資訊之中間亮度的區域。我們提出兩種實作雙邊色調調整的方法：雙邊伽瑪調整以及雙邊多項式調整。雙邊伽瑪調整提高影像整體之「強化機率」而雙邊多項式調整能夠減低運算複雜度。對於區域性對比強化，突出區域對比增強將突出性的觀念整合至一以濾波器為基礎之簡單區域對比增強方法。突出值愈高的區域表示人類對此區域感興趣的程度愈高，其被強化的程度也就愈高。此外，我們提出突出權重相對熵以及突出權重相對熵與雜訊程度之比值來評估強化的品質。藉由模擬結果顯示提出之的影像強化流程能夠達到高程度的影像強化並且保留很好的影像品質。

Various image enhancement methods have been proposed to make image better correlated to human visual perception. Generally, image enhancement can be performed in a local and/or global aspect. In this paper, we propose an innovative image enhancement framework consisting of bilateral tone adjustment (BiTA) and saliency-weighted contrast enhancement (SWCE).
Different from most curve-based global contrast enhancement methods that enhance the bright and dark regions, BiTA furthermore enhances mid-tone regions that normally contain important scenes. Two implementation approaches of BiTA are presented: bilateral gamma adjustment (BiGA) and bilateral polynomial adjustment (BiPA). BiGA increases the overall “enhancement probability” and BiPA reduces the computational cost. For local contrast enhancement, SWCE integrates the concept of image saliency into a simple filter-based contrast enhancement method. Regions with higher saliency values, which indicates the regions have higher extent of human’s interest, deserve more degree of enhancement. In addition, saliency weighted relative entropy (SWRE) and saliency weighted relative entropy to noise (SWRE/N) are proposed to evaluate the enhancement quality. Simulation results show our proposed schemes achieve high contrast enhancement and great image quality.

[1] E. Reinhard, M. Stark, P. Shirley, J. Ferwerda, “Photographic tone reproduction for digital images,” ACM Trans. Graphics, vol. 21, no. 3, pp. 267-276, 2002.
[2] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” 2nd edition, Prentice Hall, 2002.
[3] Y.-T Kim, “Contrast enhancement using brightness preserving bi-histogram equalization,” IEEE Trans. Consumer Electronics, vol. 43, no. 1, pp. 1-8, 1997.
[4] S.-D. Chen and A. R. Ramli, “Minimum mean brightness error bi-Histogram equalization in contrast enhancement,” IEEE Trans. Consumer Electronics, vol. 49, no. 4, pp. 1310-1319, 2003.
[5] C. Wang and Z. Ye, “Brightness preserving histogram equalization with maximum entropy: a variational perspective,” IEEE Trans. Consumer Electronics, vol. 51, no. 4, pp. 1326-1334, 2005.
[6] T.-K. Kim, J.-K. Paik, and B.-S. Kang, “Contrast enhancement system spatially adaptive histogram equalization with temporal filtering,” IEEE Trans. Consumer Electronics, vol. 44, no. 1, pp. 82-86, 1998.
[7] J.-Y Kim, L.-S. Kim, and S.-H. Hwang, “An advanced contrast enhancement using partially overlapped sub-block histogram equalization,” IEEE Trans. Circuit and Systems for Video Technology, vol. 11, no. 4, pp. 475-484, 2001.
[8] R. Kogan, S. Agaian, and K. Panetta, “Visualization using rational morphology and zonal magnitude reduction,” Proc. SPIE, pp. 153-162, 1998.
[9] S. Lee, “An Efficient Contrast-based image enhancement in the compressed domain using retinex theory,” IEEE Trans. Circuit and System for Video Technology, vol. 17, no. 2, pp. 199-213, 2007.
[10] K. Schutte, “Multi-scale adaptive gain control of IR images,” Proc. SPIE, vol. 3061, pp. 906-914, 1997
[11] S. D. Cvetkovic, J. Schirris, and P. H. N. de With, “Locally-adaptive image contrast enhancement without noise and ringing artifacts,” IEEE Proc. ICIP, vol. 3, pp. 551-560, 2007.
[12] D.-C. Chang and W.-R. Wu, “Image contrast enhancement based on a histogram transformation of local standard deviation,” IEEE Trans. Medical Imaging, vol. 17, no. 4, pp. 518-531, 1998.
[13] Paul E. Debevec and J. Malik, “Recovering high dynamic range radiance maps from photographs,” SIGGRAPH 97, pp.369-378.
[14] S. K. Nayar and T. Mitsunaga, “High dynamic range imaging: spatially varying pixel exposures,” IEEE Proc. CVPR, pp. 473-479, 2000.
[15] E. Ikeda. “Image data processing apparatus for processing combined image signals in order to extend dynamic range”, U.S. Patent 5801773, Sep. 1998.
[16] R. A. Street. “High dynamic range segmented pixel sensor array”, U.S. Patent 5789737, Aug. 1998.
[17] R. Fattal, D. Lischinski, M. Werman, “Gradient domain high dynamic range compression,” SIGGRAPH 2002, pp. 249-256.
[18] G. Deng, “An entropy interpretation of the logarithmic image processing model with application to contrast enhancement,” IEEE Trans. Image Processing, vol. 18, no. 5, pp. 1135-1140, 2009.
[19] T. Liu, J. Sun, N.-N. Zheng, X. Tang, and H.Y. Shum, “Learning to detect a salient object,” IEEE Proc. CVPR, pp. 1-8, 2007.
[20] L. Itti, C. Koch, and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis,” IEEE Trans. PAMI, vol. 20, no. 11, pp. 1254-1259, 1998
[21] V. Gopalakrishnan, Y. Hu, and D. Rajan, “Salient region detection by modeling distributions of color and orientation,” IEEE. Trans. Image Processing, 2009.
[22] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Trans. Systems, Man and Cybernetics, vol.9, pp. 62–66, 1979.
[23] T.-H. Huang, C.-K. Liang, S.-L. Yeh, and H. H. Chen, “JND-based enhancement of perceptibility for dim images, ” IEEE Proc. ICIP, pp. 1752-1755, 2008.
[24] R. Mantiuk, K. Myszkowski, and H.-P. Seidel, “A perceptual framework for contrast processing of high dynamic range images,” ACM Trans. Applied Perception, vol. 3, no. 3, pp. 286-308, 2006.