Bi-Histogram Equalization Algorithm for Infrared Image Enhancement
-
摘要: 为了抑制全局直方图均衡产生的灰度饱和和局部细节丢失的情况,提出了一种双直方图均衡算法。首先对图像的背景和前景进行分割,提出基于直方图的局部最小值和修正的K-Means聚类算法来确定图像的理想分割阈值,然后再对分割的子图分别作全局直方图均衡(Global Histogram Equalization,GHE)。对该算法进行了实验验证,结果表明,相较于GHE算法,经该算法增强后的图像峰值信噪比(Peak Signal to Noise Ratio,PSNR)提高约16.425%,结构相似度(Structural Similarity Index,SSIM)提高约14.85%。同时通过主观分析,基于直方图局部最小值和修正的K-Means聚类算法的图像分割进行双直方图均衡可以有效抑制GHE算法产生的灰度饱和和细节丢失现象。Abstract: A modified bi-histogram equalization algorithm is proposed to suppress gray saturation and loss of local details caused by global histogram equalization. First, the background and foreground of the image are segmented, and a modified k-means clustering algorithm based on the local minimum of the histogram is proposed to determine the ideal segmentation threshold of the image. Then, histogram equalization is performed for the segmented sub-graphs. The algorithm is verified by experiments; the results for the experiment show that, compared with those from global histogram equalization, the peak signal to noise ratio and structural similarity are improved by approximately 16.425% and 14.85%, respectively. Simultaneously, through subjective evaluation, the algorithm based on histogram local minimum and modified k-means can effectively suppress the gray saturation and detail loss caused by GHE.
-
Key words:
- image segmentation /
- double histogram equalization /
- K-Means /
- local minimum
-
表 1 本文算法增强后图像与GHE算法增强后图像的指标对比
Table 1. The index comparison between the image enhanced by this algorithm and the image enhanced by GHE algorithm
Scene number GHE Algorithm in this paper PSNR/dB Scene1 48.5525 57.265 Scene2 32.8 37.0987 Scene3 28.3774 33.1055 Scene4 33.0233 38.9685 SSIM Scene1 0.9349 0.9515 Scene2 0.6845 0.7820 Scene3 0.3256 0.4260 Scene4 0.6197 0.6988 -
[1] 孔松涛, 黄镇, 杨谨如. 红外热像无损检测图像处理研究现状与进展[J]. 红外技术, 2019, 41(12): 1133-1140. http://hwjs.nvir.cn/article/id/hwjs201912007KONG Songtao, HUANG Zhen, YANG Jinru. Research status and development of image processing for infrared thermal image nondestructive testing[J]. Infrared Technology, 2019, 41(12): 1133-1140. http://hwjs.nvir.cn/article/id/hwjs201912007 [2] 陈尧, 尹丽菊, 咸日常, 等. 基于NSCT和改进PalKing算法的电力设备红外图像增强方法[J]. 计算机应用与软件, 2021, 38(11): 236-241, 287. doi: 10.3969/j.issn.1000-386x.2021.11.038CHEN Yao, YIN Liju, XIAN Richang, et al. Infrared image enhancement method for power equipment based on NSCT and improved Pal_King algorithm[J]. Computer Applications and Software, 2021, 38(11): 236-241, 287. doi: 10.3969/j.issn.1000-386x.2021.11.038 [3] Silverman J. Display and enhancement of infrared images[C]//Image Processing and Its Applications, International Conference on. IET, 1992: 345-348. [4] 孔松涛, 谢义, 王松, 等. 红外热像增强算法发展研究综述[J]. 重庆科技学院学报: 自然科学版, 2021, 23(4): 77-83. doi: 10.3969/j.issn.1673-1980.2021.04.014KONG Songtao, XIE Yi, WANG Song, et al. Review on the development of infrared thermal image enhancement algorithms[J]. Journal of Chongqing University of Science and Technology: Natural Sciences Edition, 2021, 23(4): 77-83. doi: 10.3969/j.issn.1673-1980.2021.04.014 [5] 任其干, 谭钦红, 万志卫. 红外热成像系统的采集与驱动电路设计[J]. 红外, 2011, 32(2): 13-17. doi: 10.3969/j.issn.1672-8785.2011.02.004REN Qigan, TAN Qinhong, WAN Zhiwei. Design of acquisition and driving circuit of infrared thermal imaging system[J]. Infrared, 2011, 32(2): 13-17. doi: 10.3969/j.issn.1672-8785.2011.02.004 [6] 祝红彬, 李伟, 刘子骥, 等. 一种低噪声红外焦平面器件采集电路的设计[J]. 红外技术, 2010, 32(3): 165-168, 172. doi: 10.3969/j.issn.1001-8891.2010.03.011ZHU Hongbin, LI Wei, LIU Ziji, et al. Design of a low noise infrared focal plane device acquisition circuit[J]. Infrared Technology, 2010, 32(3): 165-168, 172. doi: 10.3969/j.issn.1001-8891.2010.03.011 [7] Gonzalez Rafael C, Woods Richard E. Digital Image Processing[M]. Beijing: Publishing House of Electronics Industry, 2010. [8] 王炳健, 刘上乾, 周慧鑫, 等. 基于平台直方图的红外图像自适应增强算法[J]. 光子学报, 2005, 34(2): 299-301. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB20050200Z.htmWANG Bingjian, LIU Shangqian, ZHOU Huixin, et al. Self-adaptive contrast enhancement algorithm for infrared images based on plateau histogram[J]. Acta Photonica Sinica, 2005, 34(2): 299-301. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB20050200Z.htm [9] 宋岩峰, 邵晓鹏, 徐军. 基于双平台直方图的红外图像增强算法[J]. 红外与激光工程, 2008, 37(4): 308-311. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ200802029.htmSONG Yanfeng, SHAO Xiaopeng, XU Jun. New enhancement algorithm for infrared image based on double plateaus histogram[J]. Infrared and Laser Engineering, 2008, 37(4): 308-311. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ200802029.htm [10] 毛义伟, 顾国华, 陈钱, 等. 基于改进型平台直方图的红外均衡化算法[J]. 光学与光电技术, 2012, 10(5): 63-66. https://www.cnki.com.cn/Article/CJFDTOTAL-GXGD201205017.htmMAO Yiwei, GU Guohua, CHEN Qian, et al. Infrared image equalization algorithm based on improved plateaus histogram[J]. Optics & Optoelectronic Technology, 2012, 10(5): 63-66. https://www.cnki.com.cn/Article/CJFDTOTAL-GXGD201205017.htm [11] WAN M, GU G, QIAN W, et al. Particle swarm optimization-based local entropy weighted histogram equalization for infrared image enhance-ment[J]. Infrared Physics & Technology, 2018, 91(10): 164-181. [12] LIANG K, MA Y, XIE Y, et al. A new adaptive contrast enhancement algorithm for infrared images based on double plateaus histogram equalization[J]. Infrared Physics & Technology, 2012, 55(4): 309-315. [13] 陈钱, 柏连发, 张保民. 红外图像直方图双向均衡技术研究[J]. 红外与毫米波学报, 2003, 22(6): 428-430. doi: 10.3321/j.issn:1001-9014.2003.06.007CHEN Qian, BO Lianfa, ZHANG Baomin. Histogram double equalization in infrared image[J]. Journal of Infrared and Millimeter Waves, 2003, 22(6): 428-430. doi: 10.3321/j.issn:1001-9014.2003.06.007 [14] LEE C, LEE C, KIM C. Contrast enhancement based on layered difference representation of 2D histograms[J]. IEEE Transactions on Image Processing, 2013, 22(12): 5372-5384. [15] Pizer S M, Amburn E P, Austin J D, et al. Adaptive histogram equalization and its variations[J]. Computer Vis. Graph. Image Process, 1987, 39(3): 355-368. [16] Zuiderveld K. Contrast Limited Adaptive Histogram Equalization[M]. San Diego: Academic Press Professional, Inc. 1994. [17] Kim J, Kim L, Hwang S. An advanced contrast enhancement using partially overlapped sub-block histogram equalization[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11(4): 475-483. [18] Ganesan S D, Rabbani M. Contrast enhancement using completely overlapped uniformly decrementing sub-block histogram equalization for less controlled illumination variation[J]. The International Arab Journal of Information Technology, 2019, 16(3): 389-395. [19] KIM Y T. Contrast enhancement using brightness preserving bi-histogram equalization[J]. IEEE Transactions on Consumer Electronics, 1997, 43(1): 1-8. [20] 万俊霞, 林珊玲, 梅婷, 等. 基于图像分割和动态直方图均衡的电润湿显示器图像增强算法[J]. 光子学报, 2022, 51(2): 240-250. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB202202024.htmWAN Junxia, LIN Shanling, MEI Ting, et al. Image enhancement algorithm of electrowetting display based on image segmentation and dynamic histogram equalization[J]. Acta Photonica Sinica, 2022, 51(2): 240-250. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB202202024.htm [21] 韩少刚, 江巨浪. 基于图像分割的双直方图均衡算法[J]. 安庆师范大学学报: 自然科学版, 2021, 27(1): 66-69. https://www.cnki.com.cn/Article/CJFDTOTAL-AQSX202101015.htmHAN Shaogang, JIANG Julang. Double histogram equalization algorithm based on image segmentation[J]. Journal of Anqing Normal University: Natural Science Edition, 2021, 27(1): 66-69. https://www.cnki.com.cn/Article/CJFDTOTAL-AQSX202101015.htm [22] 张霖泽, 王晶琦, 吴文. 一种基于K-means改进聚类的图像增强算法[J]. 应用光学, 2016, 37(4): 549-554. https://www.cnki.com.cn/Article/CJFDTOTAL-YYGX201604010.htmZHANG Linze, WANG Jingqi, WU Wen. Image enhancement algorithm based on improved K-means clustering[J]. Journal of Applied Optics, 2016, 37(4): 549-554. https://www.cnki.com.cn/Article/CJFDTOTAL-YYGX201604010.htm