臺灣博碩士論文加值系統

在低亮度的環境下，所拍攝的影像通常會面臨許多問題，像是雜訊較大、光源照度不均勻、曝光度不足導致暗處細節與色彩能見度低，而本篇論文主要建構一個低亮度影像增強系統來解決上述問題，並對此系統內部的色彩校正演算法有詳盡的介紹。
於我所提出的低亮度影像增強系統中，分成三個部分進行處理。首先是對低亮度影像做降噪的前處理，有鑑於影像增強的過程中，會導致雜訊跟著被放大與強化，因此我將去雜訊的步驟放置在整個系統的最前線。接著是對降噪後的低亮度影像做亮度的增強，此處以Retinex理論為基礎，將影像分解為光照分量與反射分量，並結合Camera Response Function來估測實際光照成分，透過提高其低光照區的亮度，進而獲取亮度強化之結果。最後是做色彩校正的後處理，由於提高亮度後的影像色彩會有所偏離，甚至因局部強力人造光源造成色偏現象發生，因此我也提出了不同方案去做處理，一種是修正色彩至與原低亮度影像色彩相近，另一種則是透過統計特性，融合白平衡與強力光源，以符合人眼色彩恆常性。

Images usually suffer from large noise, non-uniform illumination and low visibility due to insufficient exposure when captured in low-light conditions. In this thesis, we introduce a low-light image enhancement system to overcome these problems, and also emphasize a color correction algorithm applied in this system.
There are three parts in the low-light image enhancement system. The first one is to do the pre-processing of noise reduction. Since the process of image enhancement may increase the noise, the noise reduction step is placed at the front of the system. The second one is to enhance the illumination of the image. Based on Retinex theory, the image can be decomposed into two components, illumination and reflectance. The illumination can be estimated precisely by using the camera response function, which transfers irradiance to image intensities. After the region of the low illumination is lightened, the result of illumination enhancement can be acquired. The last one is to do the post-processing of color correction. Here, we propose two different methods. One is preserving the original color information. The other is combining white balance and the information of local light sources to retain color constancy by using statistical properties.

口試委員會審定書 #
致謝 i
摘要 ii
Abstract iii
Contents iv
List of Figures vii
List of Tables xii
Chapter 1 Introduction 1
1.1 Low-Light Image Enhancement 1
1.2 The Goal of the Study 2
1.3 Organization of the Thesis 3
Chapter 2 Related Works 5
2.1 Color Space 5
2.1.1 RGB Color Space 5
2.1.2 XYZ Color Space 7
2.1.3 L*a*b* Color Space 9
2.1.4 HSV Color Space 12
2.2 Human Visual Perception 14
2.2.1 Color Constancy 14
2.3 White Balance 15
2.3.1 Color Temperature 16
2.3.2 Gray-World Assumption and Algorithm 17
2.3.3 White-Patch Assumption and Algorithm 18
2.3.4 Limitation 20
2.4 Color Transfer using Statistical Properties 24
2.4.1 Basic Concept and Applications of Color Transfer 24
2.4.2 Color Transfer Algorithm using Statistical Properties 25
2.4.3 Limitation 27
2.5 Retinex Theory 28
2.6 Related Algorithm for Low-Light Image Enhancement 29
2.6.1 Optimal Function for Illumination Estimation 29
2.6.2 Gamma Correction for Illumination Adjustment 31
2.6.3 Limitation 32
2.7 Camera Response Function for Low-Light Image Enhancement 34
2.7.1 Basic Concept of Camera Response Function 34
2.7.2 Related Algorithm for Estimation of Camera Response Function from A Single Image 34
2.7.3 Limitation 40
Chapter 3 Proposed White Balance Algorithm via Dark Channel and Statistical Properties for Color Correction 41
3.1 Motivation 41
3.2 Proposed White Balance Algorithm 42
3.2.1 Source Image Generation for Color Transfer via Dark Channel 42
3.2.2 Modified Color Transfer using Statistical Properties 51
3.3 Experimental Results 56
3.4 Contribution 59
Chapter 4 Proposed Method of Low-Light Image Enhancement with Denoising and Color Correction 60
4.1 Framework 60
4.1.1 Denoising Part 61
4.1.2 Enhancement Part 61
4.1.3 Color Correction Part 61
4.2 Denoising for the Proposed Method 61
4.2.1 Optimal Function for Denoising 62
4.3 Enhancement for the Proposed Method 65
4.3.1 Illumination Estimation using Optimization and Camera Response Function 65
4.3.2 Illumination Adjustment via Illumination Estimation 67
4.4 Color Correction for the Proposed Method 70
4.4.1 Color Correction Method 1: Original Color Preserving 70
4.4.2 Color Correction Method 2: White Balance Performing 74
4.5 Experimental Results 75
4.6 Contribution 85
Chapter 5 Conclusion and Future Work 87
5.1 Conclusion 87
5.2 Future Work 88
Reference 90

[1] C. H. Ooi and N. A. M. Isa, "Quadrants dynamic histogram equalization for contrast enhancement," IEEE Transactions on Consumer Electronics, vol. 56, no. 4, pp. 2552-2559, 2010.
[2] K. Singh, R. Kapoor, and S. K. Sinha, "Enhancement of low exposure images via recursive histogram equalization algorithms," Optik, vol. 126, no. 20, pp. 2619-2625, 2015.
[3] X. Guo, Y. Li, and H. Ling, "LIME: Low-light image enhancement via illumination map estimation," IEEE Transactions on image processing, vol. 26, no. 2, pp. 982-993, 2016.
[4] X. Fu, D. Zeng, Y. Huang, X.-P. Zhang, and X. Ding, "A weighted variational model for simultaneous reflectance and illumination estimation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2782-2790.
[5] S.-Y. Yu and H. Zhu, "Low-illumination image enhancement algorithm based on a physical lighting model," IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 1, pp. 28-37, 2017.
[6] D. Parihar, A. Singh, and K. Singh, "Illumination Estimation for Nature Preserving low-light image enhancement," 2020.
[7] L. Drissi-Daoudi, A. Doerig, K. Parkosadze, M. Kunchulia, and M. H. Herzog, "How stable is perception in# TheDress and# TheShoe?," Vision research, vol. 169, pp. 1-5, 2020.
[8] G. Buchsbaum, "A spatial processor model for object colour perception," Journal of the Franklin institute, vol. 310, no. 1, pp. 1-26, 1980.
[9] M. Afifi, B. Price, S. Cohen, and M. S. Brown, "When color constancy goes wrong: Correcting improperly white-balanced images," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 1535-1544.
[10] E. H. Land, "The retinex theory of color vision," Scientific american, vol. 237, no. 6, pp. 108-129, 1977.
[11] M. Grogan and R. Dahyot, "L2 divergence for robust colour transfer," Computer Vision and Image Understanding, vol. 181, pp. 39-49, 2019.
[12] H. Alghamdi, M. Grogan, and R. Dahyot, "Patch-based colour transfer with optimal transport," in 2019 27th European Signal Processing Conference (EUSIPCO), 2019: IEEE, pp. 1-5.
[13] I. Zabaleta and M. Bertalmío, "Photorealistic style transfer for cinema shoots," in 2018 Colour and Visual Computing Symposium (CVCS), 2018: IEEE, pp. 1-6.
[14] J. Cepeda-Negrete, R. E. Sanchez-Yanez, F. E. Correa-Tome, and R. A. Lizarraga-Morales, "Dark image enhancement using perceptual color transfer," IEEE Access, vol. 6, pp. 14935-14945, 2017.
[15] C. O. Ancuti, C. Ancuti, C. De Vleeschouwer, L. Neumann, and R. Garcia, "Color transfer for underwater dehazing and depth estimation," in 2017 IEEE International Conference on Image Processing (ICIP), 2017: IEEE, pp. 695-699.
[16] E. Reinhard, M. Adhikhmin, B. Gooch, and P. Shirley, "Color transfer between images," IEEE Computer graphics and applications, vol. 21, no. 5, pp. 34-41, 2001.
[17] Y. P. Loh and C. S. Chan, "Getting to know low-light images with the exclusively dark dataset," Computer Vision and Image Understanding, vol. 178, pp. 30-42, 2019.
[18] P. E. Debevec and J. Malik, "Recovering high dynamic range radiance maps from photographs," in ACM SIGGRAPH 2008 classes, 2008, pp. 1-10.
[19] S. Lin, J. Gu, S. Yamazaki, and H.-Y. Shum, "Radiometric calibration from a single image," in Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004, vol. 2: IEEE, pp. II-II.
[20] Y. Matsushita and S. Lin, "Radiometric calibration from noise distributions," in 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007: Ieee, pp. 1-8.
[21] A. Sharma, R. T. Tan, and L.-F. Cheong, "Single-Image Camera Response Function Using Prediction Consistency and Gradual Refinement," in Proceedings of the Asian Conference on Computer Vision, 2020.
[22] K. He, J. Sun, and X. Tang, "Single image haze removal using dark channel prior," IEEE transactions on pattern analysis and machine intelligence, vol. 33, no. 12, pp. 2341-2353, 2010.
[23] D. S. Shafer and Z. Zhang, Introductory Statistics. Saylor Foundation Washington, DC, 2012.
[24] C. Li, S. Tang, J. Yan, and T. Zhou, "Low-light image enhancement via pair of complementary gamma functions by fusion," IEEE Access, vol. 8, pp. 169887-169896, 2020.
[25] S. 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. 3538-3548, 2013.
[26] X. Fu, D. Zeng, Y. Huang, Y. Liao, X. Ding, and J. Paisley, "A fusion-based enhancing method for weakly illuminated images," Signal Processing, vol. 129, pp. 82-96, 2016.
[27] M. Li, J. Liu, W. Yang, X. Sun, and Z. Guo, "Structure-revealing low-light image enhancement via robust retinex model," IEEE Transactions on Image Processing, vol. 27, no. 6, pp. 2828-2841, 2018.
[28] Z. Ying, G. Li, Y. Ren, R. Wang, and W. Wang, "A new low-light image enhancement algorithm using camera response model," in Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, pp. 3015-3022.
[29] Z. Ying, G. Li, and W. Gao, "A bio-inspired multi-exposure fusion framework for low-light image enhancement," arXiv preprint arXiv:1711.00591, 2017.