An Improved Haze Image Restoration Algorithm

Abstract

Abstract:

Aiming at the problems of classical algorithm can’t obtain the accurate atmospheric brightness A and the restored image is easy to appear the color distortion

in the sky region, this paper proposes an improved algorithm which sets three sky thresholds to obtain the pixels in the sky region, then averages the brightness of these pixels

to eliminate the effect of a white object; Adaptive the threshold which is used to segment the sky region and non-sky region using k-means clustering algorithm. This improved

algorithm can obtain more accurate atmospheric brightness A, and it can segment the sky region more accurately, so it can rectify the transmittance of the sky region easily,

these improvements can make a better visual effect of restored image. Simulation results show that the improved algorithm can achieve the anticipated effect.

Key words: dark channel prior, atmospheric brightness A, k-means clustering, adaptive threshold T

GUO Geng-shan, YE Qing, HU Xin. An Improved Haze Image Restoration Algorithm[J]. Computer and Modernization, 2015, 0(4): 94-97,102.

References

［1］ Kim J Y, Kim L S, Hwang S H. An advanced contrast enhancement using partially overlapped sub-block histogram equalization［J］. IEEE Transactions on Circuits and Systems for

Video Technology, 2001,11(4):475-484.
［2］ Kimmel R, Elad M, Shaked D, et al. A variation framework for Retinex［J］. International Journal of Computer Vision, 2003,52(1):7-23.
［3］刘海波,汤群芳,杨杰. 改进直方图均衡和Retinex算法在灰度图像增强中的应用［J］. 量子电子学报, 2014,31(5):525-532.
［4］陈文飞,许雪峰,苗作华,等. 亮度自适应的保熵直方图均衡化方法［J］. 计算机工程与应用, 2012,48(16):157-161.
［5］李锦. 图像增强算法的研究及其应用［D］. 西安:西安电子科技大学, 2013.
［6］黄黎红. 退化图像的去雾方法［J］. 红外与激光工程, 2010,39(5):985-988.
［7］郁自翔. 彩色图像复原研究［D］. 南京:南京理工大学, 2014.
［8］干宗良,邱一雯,朱秀昌. 基于图像先验和结构特征的盲图像复原算法［J］. 中国电子科学研究院学报, 2012,7(3):235-240.
［9］ Narasimhan S G, Nayar S K. Vision and the atmosphere［J］. International Journal of Computer Vision, 2002,48(3):233-254．
［10］Fattal R. Single image dehazing［J］． ACM Transactions on Graphics, 2008,27(3):1-9.
［11］He K, Sun J, Tang X. Single image haze removal using dark channel prior［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(12):2341-2353.

［12］蒋建国,侯天峰,齐美彬. 改进的基于暗原色先验的图像去雾算法［J］. 电路与系统学报, 2011,16(2):7-12.
［13］熊浩. 基于暗原色先验的图像去雾处理方法研究［D］. 武汉:华中科技大学, 2013.
［14］ 孙小明,孙俊喜,赵立荣,等. 暗原色先验单幅图像去雾改进算法［J］. 中国图象图形学报, 2014,19(3):381-385. 
［15］南栋,毕笃彦,许悦雷,等. 基于暗原色先验的图像去雾算法［J］. 中南大学学报(自然科学版), 2013,44(10):4101-4108.
［16］Levin A, Lischinski D, Weiss Y. A closed-form solution to natural image matting［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008,30(2):228-242.


［17］He Kaiming, Sun Jian, Tang Xiaoou. Guided image filtering［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(6):1397-1409.

[1]	WANG Yi-cheng, ZHANG Guo-liang, ZHANG Zi-jie, . Small Object Detection Method Based on Improved YOLOv5 [J]. Computer and Modernization, 2023, 0(05): 100-105.
[2]	ZHANG Zi-xuan, SHA Xiu-yan, XIAO Fei, SU Bao-chan, SUI Yu-lu, MENG Zi-chen. Research and Application of Hesitant Fuzzy Canopy-K-means Clustering Algorithm [J]. Computer and Modernization, 2022, 0(11): 17-21.
[3]	ZHANG Lei, CUI Juan-juan, LI Jing-jing. A Clustering Data Collection Algorithm in WSN Based on Compressed Sensing [J]. Computer and Modernization, 2020, 0(09): 1-5.
[4]	ZHANG Zi-ye1, LIU Yu-long1, HU Bei2 . Multi-source Data Integration Method Based on Data Virtualization Technology [J]. Computer and Modernization, 2019, 0(11): 18-.
[5]	JI Yan-ling1, LIN Zhi-xian1, TANG Qian1, GUO Tai-liang1, TANG Biao2. OLED Defective Pixel Recognition Based on K-means Clustering and LVQ Neural Network [J]. Computer and Modernization, 2019, 0(07): 37-.
[6]	YU Li-ling， JIN Hao-yu . Prediction of Blood Glucose Based on K-means Clustering Algorithm with RBF Neural Network [J]. Computer and Modernization, 2019, 0(03): 9-.
[7]	FAN Xin-nan, WU Jing-jing, SHI Peng-fei, ZHANG Xue-wu. A Novel Underwater Dam Crack Extraction Algorithm Based on Lorentz Information Measure [J]. Computer and Modernization, 2018, 0(03): 73-.
[8]	WANG Huan, LI Hong-hui, ZHANG Jun-wen. Cloud Task Scheduling Algorithm Based on Modified K-means Clustering [J]. Computer and Modernization, 2017, 0(2): 1-5+11.
[9]	SUN Zhen, WANG Jing-dong, MAO Tian-yi, WEI Xue-ying. Segmentation of River Based on Self-supervised Learning [J]. Computer and Modernization, 2017, 0(10): 10-14.
[10]	LIN Kang, YANG Yun, QIN Yi, MIN Yu-juan. Collaborative Filtering Recommendation Algorithm Based on User Attributes Clustering [J]. Computer and Modernization, 2016, 251(07): 28-32.
[11]	HUO Hai-meng, XU Shi-xu, WANG Han-ping. Beach Foggy Images Haze Removal Based on Dark Channel Prior [J]. Computer and Modernization, 2016, 251(07): 18-23.
[12]	CHEN Ji-wei, FAN Yin, XIANG Jun-li, LI Qian, ZHOU Rui, YANG Tong-man. Transfer Function Design Based on K-means Clustering [J]. Computer and Modernization, 2014, 0(7): 31-35.
[13]	WU Jian1,2, FENG Guo-rui1,2. Intrusion Detection Based on Simulated Annealing and Semi-supervised Clustering [J]. Computer and Modernization, 2014, 0(11): 27-30.
[14]	WANG Xiu-hua . A Speeding K-means Clustering Method Based on Sampling [J]. Computer and Modernization, 2013, 12(12): 27-29.
[15]	JIANG Qing-yun. Study on Clustering Algorithms in Wireless Sensor Networks Based on K-means [J]. Computer and Modernization, 2012, 1(10): 38-40,4.