图像增强在风力机叶片红外缺陷检测中具有重要应用,该文针对红外检测中图像清晰度低的问题,提出一种自适应迭代阈值加权的差分顶帽变换红外图像增强方法（AITWD top-hat）。首先,通过多尺度白顶帽与黑顶帽变换获得多组顶帽信息。其次,为获得更多的图像细节特征,采用对比度改善系数（contrast improvement ratio, CIR）作为阈值数,提出一种迭代阈值的图像加权方法,并对获得的最优尺度集图像进行融合,得到增强图像。最后,将该文所提方法与现有方法从定性和定量2个方面进行对比和验证。实验结果表明,该文方法不仅具有较好的图像细节增强效果,而且有效克服了传统形态学图像增强时稳定性差的问题,PSNR值和SSIM值分别提高了9.01%和9.07%。
Abstract
Image enhancement is very important in infrared defect detection of wind turbine blades. Aiming at the problem of low image definition in infrared detection, an adaptive iterative threshold weighted difference top-hat transform infrared image enhancement method （AITWD top-hat） is proposed in this paper. Firstly, multiple groups of top-hat information are obtained by multi-scale white top-hat and black top-hat transformation. Secondly, in order to obtain more image detail features, using the Contrast improvement ratio（CIR） as the threshold function, an iterative threshold image weighting method is proposed, and the optimal scale set image is fused to obtain the enhanced image. Finally, the proposed method is compared and verified with the existing methods from both qualitative and quantitative aspects. The experimental results show that this method not only has good image detail enhancement effect, but also effectively overcomes the problem of poor stability in traditional morphological image enhancement, the PSNR value and SSIM value are increased by 9.01% and 9.07% respectively.
关键词
风力机叶片 /
顶帽变换 /
图像增强 /
自适应阈值迭代
Key words
wind turbine blades /
top-hat transform /
image enhancement /
adaptive threshold iteration
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 康爽, 陈长征, 罗园庆, 等.基于微分形态学梯度风力发电机叶片缺陷边缘增强的红外检测研究[J]. 太阳能学报, 2021, 42(6): 432-437.
KANG S, CHEN C Z, LUO Y Q, et al.Study on infrared detection edge enhancement of wind turbine blade defects based on differential morphology gradient[J]. Acta energiae solaris sinica, 2021, 42(6): 432-437.
[2] BEALE C, NIEZRECKI C, INALPOLAT M.An adaptive wavelet packet denoising algorithm for enhanced active acoustic damage detection from wind turbine blades[J]. Mechanical systems and signal processing, 2020, 142: 106754.
[3] ZHANG Y, ZHOU B, YU F, et al.Cluster analysis of acoustic emission signals and infrared thermography for defect evolution analysis of glass/epoxy composites[J]. Infrared physics & technology, 2021, 112(17): 103581.
[4] BHANDARI A K, KUMAR A, SINGH G K.Improved knee transfer function and gamma correction based method for contrast and brightness enhancement of satellite image[J]. AEU-International journal of electronics and communications, 2015, 69(2): 579-589.
[5] 赵素娜, 艾矫燕, 李世晓. 小波变换在图像照度不均校正中的应用[J]. 计算技术与自动化, 2010, 29(1): 99-101.
ZHAO S N, AI J Y, LI S X.Application of wavelet transform in illumination uneven elimination[J]. Computing technology and automation, 2010, 29(1): 99-101.
[6] 王殿伟, 韩鹏飞, 范九伦, 等. 基于光照-反射成像模型和形态学操作的多谱段图像增强算法[J]. 物理学报, 2018, 67(21): 104-114.
WANG D W, HAN P F, FAN J L, et al.Multispectral image enhancement based on illuminance-reflection imaging model and morphology operation[J]. Acta physica sinica, 2018, 67(21): 104-114.
[7] 顾兴龙, 王凯, 李露露, 等. 广义形态学闭开差值运算在滚动轴承弱故障诊断中的应用[J]. 中国机械工程, 2017, 28(21): 2595-2600.
GU X L, WANG K, LI L L, et al.Applications of generalized morphological closed and open margin Operation to diagnose weak faults of rolling bearings[J]. China mechanical engineering, 2017, 28(21): 2595-2600.
[8] HASSANPOUR H, SAMADIANI N, MAHDI SALEHI S M. Using morphological transforms to enhance the contrast of medical images[J]. The Egyptian journal of radiology and nuclear medicine, 2015, 46(2): 481-489.
[9] 俞建卫, 罗振山, 尹延国, 等. 基于形态学边缘检测和小波阈值的摩擦副红外图像去噪[J]. 中国机械工程, 2013, 24(9): 1229-1232.
YU J W, LUO Z S, YIN Y G, et al.Study on infrared image denoising of friction pairs based on morphological edge detection and wavelet threshold[J]. China mechanical engineering, 2013, 24(9):1229-1232.
[10] PETER B, NORMAN S C, GRAHAM M G J, et al. Fast retinal vessel detection and measurement using wavelets and edge location refinement[J]. PLoS ONE, 2012, 7(3): 1-12.
[11] 康爽, 陈长征, 赵思雨, 等. 自适应差异多尺度形态学的风力机叶片红外图像增强研究[J]. 中国机械工程, 2021, 32(7): 786-792.
KANG S, CHEN C Z, ZHAO S Y, et al.Study of infrared image enhancement of wind turbine blades based on adaptive differential multiscale morphology[J]. China mechanical engineering, 2021, 32(7): 786-792.
[12] LI Y B, LI G Y, YANG Y T, et al.A fault diagnosis scheme for planetary gearboxes using adaptive multi-scale morphology filter and modified hierarchical permutation entropy[J]. Mechanical systems and signal processing, 2018, 105: 319-337.
[13] LYU J X, YU J B.Average combination difference morphological filters for fault feature extraction of bearing[J]. Mechanical systems and signal processing, 2018, 100: 827-845.
[14] LI Y, ZUO M, CHEN Y, et al.An enhanced morphology gradient product filter for bearing fault detection[J]. Mechanical systems and signal processing, 2018, 109(SEP.): 166-184.
[15] YAN X A, LIU Y, JIA M P.Research on an enhanced scale morphological-hat product filtering in incipient fault detection of rolling element bearings[J]. Measurement, 2019(2019):106856.
[16] LI B, ZHANG P L, WANG Z J, et al.A weighted multi-scale morphological gradient filter for rolling element bearing fault detection[J]. ISA transactions, 2011, 50(4):599-608.
[17] BUSTACARA-MEDINA C, FLÓREZ-VALENCIA L. An automatic stopping criterion for contrast enhancement using multi-scale top-hat transformation[J]. Sensing and imaging, 2019, 20(1): 26.
[18] WANG Z,BOVIK A C.Mean squared error: love it or leave it? A new look at signal fidelity measures[J]. IEEE signal processing magazine, 2009, 26(1): 98-117.
[19] RENIEBLAS G P, NOGUÉS AT, GONZALEZ AM, et al. Structural similarity index family for image quality assessment in radiological images[J]. Journal of medical imaging, 2017, 4(3): 035501.
基金
国家自然科学基金（51675350; 52175105）; 吉林省教育厅科研项目（No.JJKH20220011KJ）
PDF(3079 KB)
