近年來隨著科技的快速發展，許多的數位設備已經成為人們生活中不可或缺的產品，如相機、手機…等。人們可以藉由它們快速且方便的去拍攝生活中的各種影像。但在許多惡劣環境的影響下，例如在背向光源或是光源不足的情況下做拍攝，往往會造成低對比、低亮度以及低色彩的情況產生，而導致影像整體的品值不佳。目前現有的方法無法同時處理因不同環境影響所造成的影像問題。為此，本篇論文提出了一個自適應性的方法，來改善上述影像的問題，以利於後續相關的技術應用。
這裡我們提出了一個基於人眼視覺系統的自適應性方法。首先基於JND (Just-Noticeable-Distortion)的概念，以亮度值127為基準點將影像分成兩部份，其所代表的分別是影像的暗部區域和亮部區域，之後再各別去計算他們的加權平均，用以代表他們的影響力。而後利用兩個區域之間的關係去判斷其影像的特性。根據其對應的特性產生一組增強曲線去進行校正。除了亮度的改善外，另外一方面，我們也利用的地區性的標準差和JND權重，進一步的增強影像的細節和對比，使其能有更豐富的細節與邊緣資訊。
在最後的實驗結果上，我們也將本篇所提出的方法跟其他暗部影像增強演算法進行比較。除了使用主觀評估(pairwise comparisons)外，我們也採用了熵、平均亮度誤差以及亮度飽和，三項指標來做為客觀評估的依據。藉此來判斷影像經過對比增強後的效果如何。實驗證明透過本篇方法增強後的影像，能夠有較好的細節與對比，並保有原影像的色彩而不失真，使其得到一個更好的影像品質以利於往後的應用，如:辨識、紀錄…等。

The developments of technology grow fast in recent years, and the digital equipment becomes essential in human live, such as mobiles and camera. People can use the digital equipment to take a picture fast and conveniently to record their live. However, poor illumination will impair the quality of images. The state-of-the-art methods can’t deal with the problems of different poorly illuminated environment at the same time. Therefore, this paper presents an adaptive method to improve the problems which is beneficial to related applications.
We propose an adaptive method based on the human visual system. First, based on JND model, we use 127 of the intensity as the standard to separate images into two parts which are the dark region and the bright region respectively. Second, we calculate the weighted arithmetic mean of the dark region and the bright region to represent the influence respectively. Third, we use the relationship between the dark region and the bright region to determine the characteristic of images. We produce an enhancement curves with the characteristics to adjust images. In the other hand, we use not only local standard deviation but also the weight of JND to enhance the detail and the contrast, so the enhanced images are provided with more details and edge information.
In the final experimental result, we compare the result with the proposed method and other image enhancement methods. We use the experiments to prove the proposed method not only have more details and better contrast but also keep the original color without distortion. Therefore, with the proposed method, we can get a better image for other applications, such as recognition and recording.

[1] X. Xie, and K. M. Lam, “Face recognition under varying illumination based on a 2D face shape model,” International Conference on Pattern Recognition, pp.221–230, 2005.
[2] G. Ginesu, D. Giusto, V. Margner, and P. Meinlschmidt, “Detection of foreign bodies in food by thermal image processing,” IEEE Transactions on Industrial Electronics, pp. 480–490,2004.
[3] P. F. Stetson, F. G. Sommer, and A. Macovski, “Lesion contrast enhancement in medical ultrasound imaging,” IEEE Transactions on Medical Imaging, pp. 416–425, 1997.
[4] C. L. Chin, and C. T. Lin, “Detection and compensation algorithm for backlight images with fuzzy logic and adaptive compensation curve,” International Journal of Pattern Recognition and Artificial Intelligence, pp. 1041-1057, 2005.
[5] C. M. Tsai, and Z. M. Yeh, “Contrast compensation by fuzzy classification and image illumination analysis for back-lit and front-lit color face images,” IEEE Transactions on Consumer Electronics, pp. 1570–1578, 2010.
[6] A. Yamasaki, H. Takauji, S. Kaneko, T. Kanade, and H. Ohki, “Denighting: Enhancement of nighttime images for a surveillance camera,” International Conference on Pattern Recognition, pp. 1-4, 2008.
[7] A. R. Rivera, B. Ryu, and O. Chae, “Content-Aware Dark Image Enhancement Through Channel Division,” IEEE Transactions on Image Processing, pp. 3967-3980, 2012.
[8] R. C. Gonzalez, and R. E. Woods, “Digital Image Processing, 3rd ed.” Prentice Hall, 2008.
[9] Y. T. Kim, “Contrast enhancement using brightness preserving bi-histogram equalization,” IEEE Transactions on Consumer Electronics, pp. 1-8, 1997.
[10] Y. Wang, Q. Chen, and B. Zhang, “Image enhancement based on equal area dualistic sub-image histogram equalization method,” IEEE Transactions on Consumer Electronics, pp. 68-75, 1999.
[11] S. D. Chen, and A. R. Ramli, “Contrast enhancement using recursive mean-separate histogram equalization for scalable brightness preservation,” IEEE Transactions on Consumer Electronics, pp. 1301-1309, 2003.
[12] E. H. Land, and J. J. McCann, “Lightness and retinex theory,” Journal of the Optical Society of America, pp.1-11, 1971.
[13] Z. Rahman, D. J. Jobson, and G. A. Woodell, “Multi-scale retinex for color image enhancement,” International Conference on Image processing, pp. 1003-1006, 1996.
[14] Z. Rahman, D. D. Jobson, and G. A. Woodell, “Retinex processing for automatic image enhancement,” Journal of Electronic Imaging, pp. 100–110, 2004.
[15] J. Im, I. Yoon, M. H. Hayes, and J. Pail, “Dark channel prior-based spatially adaptive contrast enhancement for back lighting compensation,” IEEE International Conference on Acoustics, Speech and Signal Processing,
pp. 2464-2468, 2013.
[16] Li, Bo, S. Wang, and Y. Geng, “Image enhancement based on retinex and lightness decomposition,” International Conference on Image Processing, pp. 3417-3420, 2011.
[17] H. Fu, H. Ma, and S. Wu, “Night Removal by Color Estimation and sparse representation,” International Conference on Pattern Recognition, pp. 3656-3659, 2012.
[18] X. Zhang, P. Shen, L. Liang, and J. Song, “Enhancement and noise reduction of very low light level images,” International Conference on Pattern Recognition, pp. 2034-2037, 2012.
[19] C. J. Chung, W. Y. Chou, and C. W. Lin, “Under-exposed image enhancement using exposure compensation,” International Conference on ITS Telecommunications, pp. 204-209, 2013.
[20] S. C. Huang, F. C. Cheng, and Y. S. Chiu, “Efficient Contrast Enhancement Using Adaptive Gamma Correction with Weighting Distribution,” IEEE Transaction on Image Processing, pp. 1032-1041, 2013.
[21] X. Dong, G. Wang, Y. Pang, W. Li, J. Wen, W. Meng, and Y. Lu “Fast efficient algorithm for enhancement of low lighting video,” IEEE International Conference on Multimedia & Expo, pp. 1-6, 2011.
[22] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE Conference on Computer Vision and Pattern Recognition pp. 1956–1963,2009.
[23] C. H. Chou and Y. C. Li, "A perceptually tuned subband image coder based on the measure of just-noticeable-distortion profile," IEEE Transactions on Circuits and Systems for Video Technology, pp. 467-476, 1995.
[24] J. Seok, and Lee, “On designing paired comparison experiments for subjective multimedia quality assessment,” IEEE Transactions on Multimedia, pp. 564–571, 2014.
[25] A. K. Moorthy, K. Seshadrinathan, R. Soundararajan, and A. C. Bovik, “Wireless video quality assessment: A study of subjective scores and objective algorithms,” IEEE Transactions on Circuits and Systems for Video Technology, pp. 587–599, 2010.
[26] T. Celik, and T. Tjahjadi, “Contextual and variational contrast enhancement,” IEEE Transactions on Image Processing, pp. 3431-3441, 2011.
[27] S. D. Chen, and A. R. Ramli, “Preserving Brightness in Histogram Equalization Based Contrast Enhancement Techniques,” Journal of Digital Signal Processing, pp. 413-428, 2004.
[28] J. P. Tarel, and, N. Hautiere, “Blind contrast enhancement assessment by gradient ratioing at visible edges,” Journal of Image Analysis and Stereology, pp.87-95, 2008.
[29] S. S. Agaian, B. Silver, and K. A. Panetta, “Transform coefficient histogram based image enhancement algorithms using contrast entropy,” IEEE Transactions on Image Processing, pp. 741–758, 2007.
[30] K. Panetta, C. Gao, and S. Agaian, “No Reference Color Image Contrast
and Quality Measures,” IEEE Transactions on Consumer Electronics, pp. 643-651, 2013.
[31] H. Han, and K. Sohn, “Automatic Illumination and Color Compensation Using Mean Shift and Sigma Filter,” IEEE Transactions on Consumer Electronics, pp.978-986, 2009