Zaocai Xu
ABSTRACT
How to solve the low recall rate and poor positioning accuracy in current CT image defect positioning methods is a thorny problem. Therefore, this study proposes an automatic positioning system for industrial CT image defects based on machine vision. This article uses image preprocessing and scale-invariant feature transformation to process the image, uses a defect location algorithm to locate defects in CT images, and uses threshold segmentation and morphological operations to extract defect areas, and at the same time, designs experiments to compare and evaluate the positioning results with manual annotations, verifying the effectiveness and accuracy of the system. After experimental testing, the positioning accuracy of this system is between 0.01-0.1. The automatic industrial CT image defect positioning system based on machine vision can quickly and accurately locate different types of defects. Compared with traditional manual intervention methods, the system has higher efficiency and repeatability, which can improve the level of quality control on the production line.
- Xue Lin, Zhang Dejian, He Qun, Ma Kai, Xu Jialong. Part size measurement method based on industrial CT images [J]. Nondestructive Testing, 2023, 45(7): 16-19+60.Google Scholar
- Cui Wei, Wu Yimeng, Cao Fukai. Industrial CT image feature extraction of alloy cracks in aircraft body [J]. Ordnance Materials Science and Engineering, 2022, 45(4): 115-119.Google Scholar
- Lu Jian, Luan Chuanbin, Zhang Xiuying, Cai Yufang. Industrial CT image measurement method of precision parts [J]. Nondestructive Testing, 2022, 44(4): 28-34+54.Google Scholar
- Wang Fuquan, Xia Dezhi, Wen Hao. Internal defect detection of castings based on industrial CT images [J]. Shanghai Metrology and Testing, 2022, 49(3): 17-21.Google Scholar
- Xu Xuehui. Intelligent determination method of rigid body slice thickness based on industrial CT images [J]. Ordnance Materials Science and Engineering, 2020, 43(6): 129-132.Google Scholar
- Shan H, Padole A, Homayounieh F, Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction [J]. Nature Machine Intelligence, 2019, 1(6): 269-276.Google ScholarCross Ref
- Zhao Z. Review of non-destruCTive testing methods for defeCT deteCTion of ceramics[J]. Ceramics International, 2021, 47(4): 4389-4397.Google ScholarCross Ref
- Samei E, Bakalyar D, Boedeker K L, Performance evaluation of computed tomography systems: summary of AAPM Task Group 233 [J]. Medical physics, 2019, 46(11): e735-e756.Google ScholarCross Ref
- KłosowsKi G, Rymarczyk T, Kania K, Maintenance of industrial reaCTors supported by deep learning driven ultrasound tomography[J]. Eksploatacja i Niezawodność, 2020, 22(1): 138-147.Google Scholar
- Ren Z, Fang F, Yan N, State of the art in defeCT deteCTion based on machine vision[J]. International Journal of Precision Engineering and ManufaCTuring-Green Technology, 2022, 9(2): 661-691.Google ScholarCross Ref
- Niu S, Li B, Wang X, DefeCT image sample generation with GAN for improving defeCT recognition [J]. IEEE TransaCTions on Automation Science and Engineering, 2020, 17(3): 1611-1622.Google Scholar
- Mitterreiter E, Schuler B, Cochrane K A, Atomistic positioning of defeCTs in helium ion treated single-layer MoS2[J]. Nano letters, 2020, 20(6): 4437-4444.Google Scholar
- Luo Q, Fang X, Liu L, Automated visual defeCT deteCTion for flat steel surface: A survey[J]. IEEE TransaCTions on Instrumentation and Measurement, 2020, 69(3): 626-644.Google ScholarCross Ref
- He Y, Song K, Meng Q, An end-to-end steel surface defeCT deteCTion approach via fusing multiple hierarchical features [J]. IEEE transaCTions on instrumentation and measurement, 2019, 69(4): 1493-1504.Google Scholar
- Dong H, Song K, He Y, PGA-Net: Pyramid feature fusion and global context attention network for automated surface defeCT detection [J]. IEEE TransaCTions on Industrial Informatics, 2019, 16(12): 7448-7458.Google ScholarCross Ref
- Wu Y, Cao H, Yang G, Digital twin of intelligent small surface defeCT deteCTion with cyber-manufaCTuring systems[J]. ACM TransaCTions on Internet Technology, 2023, 23(4): 1-20.Google ScholarDigital Library
- Baumgartl H, Tomas J, Buettner R, A deep learning-based model for defeCT deteCTion in laser-powder bed fusion using in-situ thermographic monitoring[J]. Progress in Additive ManufaCTuring, 2020, 5(3): 277-285.Google ScholarCross Ref
- Tabernik D, Šela S, Skvarč J, Segmentation-based deep-learning approach for surface-defeCT deteCTion[J]. Journal of Intelligent ManufaCTuring, 2020, 31(3): 759-776.Google ScholarCross Ref
- Ding R, Dai L, Li G, TDD‐net: a tiny defeCT deteCTion network for printed circuit boards[J]. CAAI TransaCTions on Intelligence Technology, 2019, 4(2): 110-116.Google ScholarDigital Library
- Sun J, Li C, Wu X J, An effeCTive method of weld defeCT deteCTion and classification based on machine vision[J]. IEEE TransaCTions on Industrial Informatics, 2019, 15(12): 6322-6333.Google ScholarCross Ref
Index Terms
- Automatic Positioning System for Industrial CT Image Defects Based on Machine Vision
Recommendations
Image Segmentation Algorithm of Fracture Tracking Trajectory in Industrial CT Image Management System
ICMTMA '14: Proceedings of the 2014 Sixth International Conference on Measuring Technology and Mechatronics AutomationAccording to the industrial CT image management system, the high precise segmentation of CT image fracture is a key technology, and it was researched in this paper. The industrial CT image management system can manage and process different industrial CT ...
A System for Detection of Internal Log Defects by Computer Analysis of Axial CT Images
WACV '96: Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV '96)This paper presents a system for detection of some important internal log defects via analysis of axial CT images. Two major procedures are used: the first is the segmentation of a single computer tomography (CT) image slice which extracts defect-like ...
Automatic Liver Segmentation in Abdomen CT Images using SLIC and AdaBoost Algorithms
ICBBB '18: Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and BioinformaticsThis study is an implementation of liver segmentation on abdomen CT images. The liver organ was segmented by using SLIC super-pixel and AdaBoost algorithms. Firstly, the images were clustered by SLIC super-pixel algorithm. Then, the liver was segmented ...
Comments