분해 심층 학습을 이용한 저조도 영상 개선 방식

국문 초록 (Abstract)

본 논문에서는 저조도 영상을 개선하기 위한 영상 분해 기반 심층 학습 방법 및 분해 채널 특성에 따른 손실함수를 제안한다. 기존 기법들의 문제점인 색신호 왜곡 및 할로 현상을 제거하기 위해, 입력 영상의 휘도 채널을 반사 성분과 조도 성분으로 분해하고, 반사 성분, 조도 성분 및 색차 신호를 신호 특성에 적합한 심층학습 과정을 적용하는 분해 기반 다중 구조 심층학습 방법을 제안한다. 더불어, 분해 채널들의 특성에 따른 혼합 놈 기반의 손실함수를 정의하여 복원 영상의 안정성을 증대하고 열화 현상을 제거하기 위한 기법에 대해 기술한다. 실험 결과를 통해 제안한 방법이 다양한 저조도 영상을 효과적으로 개선하였음을 확인할 수 있었다.

다국어 초록 (Multilingual Abstract)

This paper introduces an image decomposition-based deep learning method and loss function to improve low-light images. In order to remove color distortion and halo artifact, illuminance channel of an input image is decomposed into reflectance and luminance channels, and a decomposition-based multiple structural deep learning process is applied to each channel. In addition, a mixed norm-based loss function is described to increase the stability and remove blurring in reconstructed image. Experimental results show that the proposed method effectively improve various low-light images.

목차 (Table of Contents)

• Abstract
• 요약
• Ⅰ. 서론
• Ⅱ. 분해 심층 학습 기반 저조도 영상 복원
• Ⅲ. 실험 결과
• Ⅳ. 결론
• References

참고문헌 (Reference)

1 P. Arbelaez, "The Berkeley Segmentation Dataset and Benchmark"

2 T. Celik, "Spatial entropy-based global and local image contrast enhancement" 23 (23): 5298-5308, 2014

3 E. Provenzi, "Random spray retinex:A new retinex implementation to investigate the local properties of the model" 16 (16): 162-171, 2007

4 D. J. Jobson, "Properties and performance of a center/surround retinex" 6 (6): 451-461, 1997

5 D. Zosso, "Non-local retinex-A unifying framework and beyond" 8 (8): 787-826, 2015

6 Shuhang Wang, "Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images" Institute of Electrical and Electronics Engineers (IEEE) 22 (22): 3538-3548, 2013

7 L. Shen, "Msr-net: lowlight image enhancement using deep convolutional network" 2017

8 A. Mittal, "Making a “Completely Blind” Image Quality Analyzer" Institute of Electrical and Electronics Engineers (IEEE) 20 (20): 209-212, 2013

9 F. Lv, "MBLLEn:Low-light image/video enhancement using CNNs" 1 (1): 1-13, 2019

10 S. Park, "Low-light image enhancement using variational optimization-based retinex model" 63 (63): 178-184, 2017

11 H. R. Sheikh, "Live image quality assessment database release 2"

12 X. Guo, "Lime: Low-light image enhancement via illumination map estimation" 26 (26): 982-999, 2017

13 E. H. Land, "Lightness and retinex theory" 61 (61): 1-11, 1971

14 K. G. Lore, "LLNet: A deep autoencoder approach to natural low-light image enhancement" 61 : 650-662, 2017

15 Y. Zhang, "Kindling the darkness: A practical low-light image enhancer" 1632 (1632): 1632-1640, 2019

16 Stanford Vision Lab, "ImageNet"

17 M. Lecca, "GRASS:A gradient-based random sampling scheme for Milano retinex" 26 (26): 2767-2780, 2017

18 NASA, "Electromagnetics and Sensors Research Branch"

19 Y. Shin, "Efficient naturalness restoration for non-uniform illumination images" 9 (9): 662-671, 2015

20 C. Wei, "Deep retinex decomposition for low-light enhancement"

21 Wencheng Wang, "An Experiment-Based Review of Low-Light Image Enhancement Methods" Institute of Electrical and Electronics Engineers (IEEE) 8 : 87884-87917, 2020

22 J. G. Oh, "Adaptive image rendering using a nonlinear mapping function based retinex model" 19 (19): 969-, 2019

23 D. P. Kingma, "Adam: A method for stochastic optimization" 2017

24 R. Kimmel, "A variational framework for retinex" 52 : 7-23, 2003

25 D. J. Jobson, "A multi-scale retinex for bridging the gap between color images and the human observation of scenes" 6 (6): 965-976, 199