Retinex影像增強法是一種基於人類視覺的演算法，它是一種能保留局部對比的TRO方法。Retinex演算法能增強非均勻影像的對比並能平衡影像的明暗。然而，在亮地方Retinex的表現有許多缺失，因為Retinex演算法分別計算R,G和B三個彩色頻道。

本論文提出一基於Retinex法的影像增強演算法。此法受Kim和Hahn兩法的概念所啟發。原始非均勻影像在亮地方有良好的表現，而Retinex法增強影像在暗處有傑出的表現。因此所提演算法結合原始影像和Retinex增強影像兩者的優點，藉由Fuzzy C-means分群演算法將影像分割成三區塊，對每一區塊採取不同的策略去混合原始與Retinex增強影像。為避免混合步驟失去對比和細節資訊，所提演算法以雙邊濾波器在切割之前先將細節成分取出。

首先我們使用動態範圍獨立影像品質評估量距(DRIM)主觀評估並比較所提演算法與三種現存演算法。實驗結果顯示在暗處所提方法改善之影像有顯著的對比增強，而在其他地方只有輕微的對比喪失和對比反轉。接著我們使用峰值訊噪比(PSNR)，信息熵和光線次序誤差(LOE)客觀比較各演算法。實驗結果顯示，所提出演算法具有第二高PSNR，最高信息熵與第二低LOE，因此整體表現為最佳，再者，所提演算法的改善影像在視覺上賞心悅目且自然。

Based on the human visual system, the Retinex image enhancement algorithm follows the method tone reproduction operator (TRO) which well preserves local contrast. The Retinex algorithm offers a forcefully improvement for nonuniformly illuminated images and keeps a good balance between darkness and brightness. However, it still has some weakness. Especially in the bright area, the image has distortions of grey out due to separately calculating the R, G and B components.

In this thesis, a Retinex based image enhancement algorithm is proposed. The proposed algorithm is inspired by the Kim’s and the Hahn’s concepts. Since the original nonuniformly illuminated images have good performance in the bright area and the Retinex algorithm improved image has outstanding performance in the dark area, the proposed algorithm aimed to integrate the merits from both images. The proposed algorithm segments the histogram of an image into three areas by using the Fuzzy C-means clustering algorithm and adopts an appropriate strategy for each area to mix the original image and its Retinex improved images. To avoid the loss of contrast and information detail in mixing two images, the proposed algorithm extracts the detail component before segmentation by using the bilateral filter.

The proposed algorithm is first subjectively assessed by using the dynamic range independent image quality assessment metric (DRIM) and compared with three existing algorithms. Experimental results show that the improved images using our proposed algorithm reveal significant amplification of contrast in the dark areas and mild loss and reversal of contrast in other areas. Then the proposed algorithm is objectively assessed by using peak signal-to-noise ratio (PSNR), information entropy and lightness order error (LOE). Experimental results show that among the four methods compared the PSNR of our proposed algorithm is the second highest, the information entropy is the highest and the LOE is the second lowest, all together, this indicates that our algorithm is the best among the four algorithms. Also the improved images by our proposed algorithm are visually pleasing and natural looking.

[1] T. O. Aydin, R. Mantiuk, K. Myszkowski, and H. Seidel “Dynamic range independent image quality assessment”, ACM Trans. Graph. , Vol. 27, No. 3, pp. 1-10, 2008.
[2] D. Brainard, and B. Wandell, “Analysis of the Retinex Theory of Color Vision,” J. Opt. Soc. Amer. A, Vol. 3, No. 10, pp. 1651–1661, 1986.
[3] P. E. Debevec and J. Malik, “Recovering High Dynamic Range Images,” SIGGRAPH '97 Proceedings of the 24th annual conference on Computer graphics and interactive techniques, pp. 369-378, 1997.
[4] F. Durand, and J. Dorsey, “Fast Bilateral Filtering for the Display of High-Dynamic-Range Images,” ACM Transactions on Graphics, Vol. 21, No. 3, pp. 257-266, 2002.
[5] M. Elad, R. Kimmel, D. Shaked, and R. Keshet, “Reduced Complexity Retinex Algorithm Via the Variational Approach,” J. Vis. Commun. Image Represent. , Vol. 14, No. 1, pp. 369–388, 2003.
[6] R. Fattal, D. Lischinski, and M. Werman, “Gradient Domain High Dynamic Range Compression,” ACM Transactions on Graphics, Vol. 21, No. 3, pp. 249-256, 2002.
[7] B. Funt, F. Ciurea, and J. McCann, “Retinex in matlab,” J. Electron. Imag., Vol. 13, No. 1, pp. 48–57, Jan. 2004.
[8] C. Gauge and S. Sasi, “Modified Fuzzy C-Means Clus-tering Algorithm with Spatial Distance to Cluster Center of Gravity,” Proceedings of the 6th IEEE International Workshop on Multimedia Information and Retrieval, pp. 308-313, 2010.
[9] C. Gauge and S. Sasi, “Automated Colorization of Grayscale Images Using Texture Descriptors and a Modified Fuzzy C-Means Clustering,” Journal of Intelligent Learning Systems and Applications, Vol. 3, No. 3, pp. 81-87, 2012.
[10] G. Guarnieri, S. Marsi and G. Ramponi, “High Dynamic Range Image Display With Halo and Clipping Prevention”, IEEE Transactions on Image processing, Vol. 20, No. 5, pp. 1351-1362, 2011.
[11] H. S. Hahn, “Image Enhancement using FCM Algorithm Based on HSV Color Model,” 2013 Seventh International Conference on Image and Graphics (ICIG), pp. xxv-xxvi, 2013.
[12] A. Hurlbert, “Formal Connections Between Lightness Algorithms,” J. Opt. Soc. Amer. A, vol. 3, pp. 1684–1692, 1986.
[13] J. H. Jang, Y. S. Bae, and J. B. Ra “Contrast-Enhanced Fusion of Multisensor Images Using Subband-Decomposed Multiscale Retinex,” IEEE Transactions on Image Processing, Vol. 21, No. 8, pp. 3479-3490, 2012.
[14] J. H. Jang, S. D. Kim, and J. B. Ra “Enhancement of Optical Remote Sensing Images by Subband-Decomposed Multiscale Retinex With Hybrid Intensity Transfer Function,” IEEE Geoscience and Remote Sensing Letters, Vol. 8, No. 5, pp. 983-987, 2011.
[15] D. J. Jobson, Z. Rahman, and G. A. Woodell, "Properties and Performance of a Center/ Surround Retinex," IEEE Transactions on Image Processing, Vol. 6, No. 3, pp. 451-492, 1997.
[16] K. M. Kim, J. H. Bae, and J. S. Kim, “Natural HDR Image Tone Mapping Based on Retinex,” IEEE Transactions on Consumer Electronics, Vol. 57, No. 4, pp. 1807-1814, 2011.
[17] Y. T. Kim, J. H. Yu, and H. S. Hahn, “Retinex Algorithm Improvement for Color Compensation in Back-Light Image Efficently,” Journal of the Korea Society of Computer and Information, Vol. 16, No. 1, pp. 61-69, 2011.
[18] R. Kimmel, M. Elad, D. Shaked, R. Keshet, and I. Sobel, “A Variational Framework for Retinex,” Int. J. Comput. Vis. , Vol. 52, No. 1, pp. 7–23, 2003.
[19] H. Kotera and M. Fujita, “Appearance Improvement of Color Image by Daptive Scale-Gain Retinex Model,” Proc. IS&T/SID 10th Color Imaging Conference, pp. 166–171, 2002.
[20] E. Land, “The Retinex,” Amer. Scient. ,” Vol. 52, No. 2, pp. 247–264, 1964.
[21] E. Land, “Lightness and Retinex Theory,” J. Opt. Soc. Amer. , Vol. 61, No. 1, pp. 1–11, Jan. 1971.
[22] G. S. Miller and C. R. Hoffman, “Illumination and reflection maps: simulated objects in simulated and real environments,” in SIGGRAPH 84 Course Notes for Advanced Computer Graphics Animation, July 1984.
[23] Z. Rahman, D. J. Jobson, and G. A. Woodell. “A Multiscale Retinex for Color Rendition and Dynamic Range Compression,” in SPIE Proceedings: Applications of Digital Image Processing XIX, Vol. 2847, 1996.
[24] E. Reinhard, M. Stark, P. Shirley, and J. Ferwerda. “Photographic tone reproduction for digital images,” ACM Transactions on Graphics, Vol. 21, No. 3, pp. 267–276, 2002.
[25] N. Sengee, A. Sengee, and H. K. Choi, “Image Contrast Enhancement using Bi-Histogram Equalization with Neighborhood Metrics,” IEEE Transactions on Consumer Electronics, Vol. 56, No. 4, pp. 2727-2734, 2010.
[26] R. Sobol, “Improving the Retinex algorithm for rendering wide dynamic range photographs,” J. Electron. Imag. , Vol. 13, No. 1, pp. 65–74, 2004.
[27] S. C. Tai, T. C. Tsai, Y. Y. Chang, W. T. Tsai and K. H. Tang, “Contrast Enhancement through Clustered Histogram Equalization,” Research Journal of Applied Sciences, Engineering and Technology, Vol. 4, No. 20, pp. 3965-3968, 2012.
[28] L. Tang, W. X. Xie, J. J. Huang, Z. J. Xiao, and S. Lin “Removing Shadows from Urban Aerial Images Based on Fuzzy Retinex,” Acta Electronica Sinica, Vol. 33, No. 3, pp. 500-503, 2005.
[29] C. Tomasi, R. Manduchi, “Bilateral Filtering for Gray and Color Images,” Proceedings of the Sixth International Conference on Computer Vision, pp. 839-846, jan. 1998.
[30] J. Tumblin and H. Rushmeier, "Tone reproduction for computer generated images," IEEE Computer Graphics and Applications, Vol. 13, No. 6, pp. 42–48, 1993.
[31] L. Wang, T. Horiuchi, and H. Kotera, “High Dynamic Range Image Compression by Fast Integrated Surround Retinex Model,” J. Imaging Sci. Technol. , Vol. 51, No. 1, pp. 32-34, 2007.
[32] S. H. Wang, J. Zheng, H. M. Hu, and B. Li, “Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images,” IEEE Transactions on Image Processing, Vol. 22, No. 9, pp. 983-987, 2013.
[33] J. L. Wu, “An Automatic Enhancement Method for High Contrast Images via Bilateral Filtering,” Journal of Science and Engineering Technology, Vol. 3, No. 3, pp. 81-87, 2007.
[34] Q. Zhao, P. Tan, Q. Dai, L. Shen, E. H. Wu, and S. Lin, “A Closed-Form Solution to Retinex with Nonlocal Texture Constraints,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 7, pp. 1437-1444, 2012.