DR image quality optimization of stainless steel girth weld for nuclear power based on dark channel technology
-
摘要: 为提高曝光不足的小径管环焊缝缺陷数字射线成像(DR)检测识别度,以完成核电站压力容器的安全性监测,将导向滤波和暗通道去雾理论相结合,对低剂量下的小径管环焊缝DR图像进行图像增强,通过客观评价指标对图像质量进行评价,并与自适应直方图均衡化(AHE)和限制对比度自适应直方图均衡化(CLAHE)图像增强方法进行对比。结果表明,暗通道图像增强技术对图像质量的改善效果更好,图像对比度噪声比提高了31.5%,信噪比提高了约1.5倍,缺陷轮廓更清晰。Abstract: In order to improve the detection and identification of underexposed small-diameter pipe girth weld defects, digital radiography (DR) was used to complete the safety monitoring of pressure vessels in nuclear power plants. Guided filtering and dark channel demisting theory were combined to enhance the DR Image of small-diameter pipe girth weld at low dose. The image quality was evaluated through objective evaluation indicators, and compared with adaptive histogram equalization (AHE) and contrast limited adaptive histogram equalization (CLAHE) image enhancement methods. The results show that the dark channel image enhancement technology has a better impact on image quality improvement, the image contrast-to-noise ratio was increased by 31. 5% and signal-to-noise ratio was increased by about 1. 5 times, and the defect contour was clearer.
-
-
[1] 迟露鑫,麻永林,邢淑清,等.核电SA508-3钢焊接连续冷却转变曲线的分析[J].焊接学报,2011,32(5):61-64,116. [2] 苏锦成,王振中,贾小攀,等.基于A*算法的核电厂工艺管道自动布局方法[J].核科学与工程,2022,42(1):129-135. [3] NADDAF-SH M M,NADDAF-SH S,ZARGARZADEH H,et al.Defect detection and classification in welding using deep learning and digital radiography[C]//Fault Diagnosis and Prognosis Techniques for Complex Engineering Systems.Amsterdam:Elsevier,2021.
[4] 樊丁,胡桉得,黄健康,等.基于改进卷积神经网络的管焊缝X射线图像缺陷识别方法[J].焊接学报,2020,41(1):7-11,97. [5] TYYSTJÄRVI T,VIRKKUNEN I,FRIDOLF P,et al.Automated defect detection in digital radiography of aerospace welds using deep learning[J].Welding in the World,2022,66(4):643-671.
[6] 穆为磊,高建民,陈富民,等.符合人眼视觉特性的焊缝射线数字图像增强方法[J].西安交通大学学报,2012,46(3):90-93,99. [7] 闫军,韩炜,张利.基于不同增强处理技术的DR图像质量优化分析[J].中国医学装备,2017,14(12):39-42. [8] MUNIYAPPAN S,ALLIRANI A,SARASWATHI S.A novel approach for image enhancement by using contrast limited adaptive histogram equalization method[C]//2013 Fourth International Conference on Computing,Communications and Networking Technologies (ICCCNT).Tiruchengode,India:IEEE,2014.
[9] DONG X,WANG G,PANG Y,et al.Fast efficient algorithm for enhancement of low lighting video[C]//2011 IEEE International Conference on Multimedia and Expo.Barcelona:IEEE,2011.
[10] FENG J F,CHEN Q,HE W J,et al.Optimization of low illumination image enhancement algorithm based on dark channel prior[C]//2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education (ICISCAE).Dalian,China:IEEE,2020.
[11] 郑金华,盛涛,冯君伟,等.暗通道图像增强技术在数字射线检测中的应用[J].玻璃钢/复合材料,2019(11):105-110. [12] SABIR A,KHURSHID K,SALMAN A.Segmentation-based image defogging using modified dark channel prior[J].EURASIP Journal on Image and Video Processing,2020,2020(1):1-14.
[13] SUSIL O,YULIANTI I,ADDAWIYAH A,et al.Optimization of exposure factors for X-ray radiography non-destructive testing of pearl oyster[J].Journal of Physics:Conference Series,2018,983:012004.
[14] YUGANDER P,TEJASWINI C H,MEENAKSHI J,et al.MR image enhancement using adaptive weighted mean filtering and homomorphic filtering[J].Procedia Computer Science,2020,167:677-685.
计量
- 文章访问数: 9
- HTML全文浏览量: 0
- PDF下载量: 3
下载:
