1
|
Hena B, Wei Z, Castanedo CI, Maldague X. Deep Learning Neural Network Performance on NDT Digital X-ray Radiography Images: Analyzing the Impact of Image Quality Parameters-An Experimental Study. SENSORS (BASEL, SWITZERLAND) 2023; 23:s23094324. [PMID: 37177528 PMCID: PMC10181732 DOI: 10.3390/s23094324] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Revised: 04/13/2023] [Accepted: 04/25/2023] [Indexed: 05/15/2023]
Abstract
In response to the growing inspection demand exerted by process automation in component manufacturing, non-destructive testing (NDT) continues to explore automated approaches that utilize deep-learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep-learning models. This study investigated the influence of two image-quality parameters, namely signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), on the performance of a U-net deep-learning semantic segmentation model. Input images were acquired with varying combinations of exposure factors, such as kilovoltage, milli-ampere, and exposure time, which altered the resultant radiographic image quality. The data were sorted into five different datasets according to their measured SNR and CNR values. The deep-learning model was trained five distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection-over-union (IoU) metric of 0.9594 on test data of the same category but dropped to 0.5875 when tested on lower CNR test data. The result of this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters in order to enhance the performance of deep-learning segmentation models for NDT digital X-ray radiography applications.
Collapse
Affiliation(s)
- Bata Hena
- Department of Electrical and Computer Engineering, Université Laval, Quebec City, QC G1V 0A6, Canada
- Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la Médecine, Université Laval, Quebec City, QC G1V 0A6, Canada
| | - Ziang Wei
- Department of Electrical and Computer Engineering, Université Laval, Quebec City, QC G1V 0A6, Canada
- Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la Médecine, Université Laval, Quebec City, QC G1V 0A6, Canada
- School of Engineering, University of Applied Sciences in Saarbrücken, 66117 Saarbrücken, Germany
- Fraunhofer Institute for Nondestructive Testing IZFP, 66123 Saarbrücken, Germany
| | - Clemente Ibarra Castanedo
- Department of Electrical and Computer Engineering, Université Laval, Quebec City, QC G1V 0A6, Canada
- Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la Médecine, Université Laval, Quebec City, QC G1V 0A6, Canada
| | - Xavier Maldague
- Department of Electrical and Computer Engineering, Université Laval, Quebec City, QC G1V 0A6, Canada
- Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, 1065, Ave de la Médecine, Université Laval, Quebec City, QC G1V 0A6, Canada
| |
Collapse
|
2
|
Zhang L, Zheng G, Zhang K, Wang Y, Chen C, Zhao L, Xu J, Liu X, Wang L, Tan Y, Xing C. Study on the Extraction of CT Images with Non-Uniform Illumination for the Microstructure of Asphalt Mixture. MATERIALS (BASEL, SWITZERLAND) 2022; 15:ma15207364. [PMID: 36295429 PMCID: PMC9610159 DOI: 10.3390/ma15207364] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Revised: 10/03/2022] [Accepted: 10/10/2022] [Indexed: 06/12/2023]
Abstract
An adaptive image-processing method for CT images of asphalt mixture is proposed in this paper. Different methods are compared according to the error analysis calculated between the real gradation and 3D reconstruction gradation. As revealed by the test results, the adaptive image-processing method was effective in carrying out different brightness homogenization processes for each image. The Wiener filter with 7 × 7 size filter was able to produce a better noise reduction effect without compromising image sharpness. Among the three methods, the adaptive image-processing method performed best in the accuracy of coarse aggregate recognition, followed by the ring division method and the global threshold segmentation method. The error of the gradation extracted by the adaptive image-processing method was found to be lowest compared with the real gradation. For a variety of engineering applications, the developed method helps to improve the analysis of CT images of asphalt mixtures.
Collapse
Affiliation(s)
- Lei Zhang
- School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China
| | - Guiping Zheng
- School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China
| | - Kai Zhang
- China State Construction International Holdings Limited, Hong Kong 999077, China
| | - Yongfeng Wang
- CCCC NO. 1 Highway Survey Design & Research Institute Co., Ltd., Xi’an 710065, China
| | - Changming Chen
- CCCC NO. 1 Highway Survey Design & Research Institute Co., Ltd., Xi’an 710065, China
| | - Liting Zhao
- CCCC NO. 1 Highway Survey Design & Research Institute Co., Ltd., Xi’an 710065, China
| | - Jiquan Xu
- Sichuan Gezhouba Batongwan Expressway Co., Ltd., Bazhong 636600, China
| | - Xinqing Liu
- Sichuan Gezhouba Batongwan Expressway Co., Ltd., Bazhong 636600, China
| | - Liqing Wang
- Sichuan Gezhouba Batongwan Expressway Co., Ltd., Bazhong 636600, China
| | - Yiqiu Tan
- School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China
| | - Chao Xing
- School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China
| |
Collapse
|
3
|
Kim S, Ahn J, Kim B, Kim C, Baek J. Convolutional neural network‐based metal and streak artifacts reduction in dental CT images with sparse‐view sampling scheme. Med Phys 2022; 49:6253-6277. [DOI: 10.1002/mp.15884] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2021] [Revised: 07/02/2022] [Accepted: 07/18/2022] [Indexed: 11/08/2022] Open
Affiliation(s)
- Seongjun Kim
- School of Integrated Technology Yonsei University Incheon 21983 South Korea
| | - Junhyun Ahn
- School of Integrated Technology Yonsei University Incheon 21983 South Korea
| | - Byeongjoon Kim
- School of Integrated Technology Yonsei University Incheon 21983 South Korea
| | - Chulhong Kim
- Departments of Electrical Engineering Convergence IT Engineering, Mechanical Engineering School of Interdisciplinary Bioscience and Bioengineering, and Medical Device Innovation Center Pohang University of Science and Technology Pohang 37673 South Korea
| | - Jongduk Baek
- School of Integrated Technology Yonsei University Incheon 21983 South Korea
| |
Collapse
|
4
|
Masselot V, Bosc V, Benkhelifa H. Analyzing the microstructure of a fresh sorbet with X-ray micro-computed tomography: Sampling, acquisition, and image processing. J FOOD ENG 2021. [DOI: 10.1016/j.jfoodeng.2020.110347] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|