Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS)
With the development of optics, light section method has become a feasible measurement for surface roughness, while the short sampling length is negative to the accuracy. To overcome this defect, this article proposed a measurement under ResNet-based roughness classification and light section with s...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Instrumentation and Measurement |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10713234/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536177016930304 |
|---|---|
| author | Huashen Guan Qiushen Cai Xiaobin Li Guofu Sun |
| author_facet | Huashen Guan Qiushen Cai Xiaobin Li Guofu Sun |
| author_sort | Huashen Guan |
| collection | DOAJ |
| description | With the development of optics, light section method has become a feasible measurement for surface roughness, while the short sampling length is negative to the accuracy. To overcome this defect, this article proposed a measurement under ResNet-based roughness classification and light section with seam-driven image stitching (RCLS). First, the images were classified with ResNet neural network, then stitched and enhanced by scale invariant feature transform (SIFT) and optimized random sample consensus (RANSAC) algorithm for the best visual effect. After this, images were processed by Nobuyuki Otsu method and Freeman chain code tracking algorithm. Least square was also adopted to calculate the optical band edge curve and contour midline. Finally, the roughness contour arithmetic mean deviation model was established to evaluate the surface roughness. The experiments were conducted with vertical milled, planned, and turned samples that self-machined. The light section method had a reduction of 2.75% on the mean relative error compared to stylus and RCLS could further reduce the mean relative error by 1.42%, especially in planned sample. The RCLS could achieve a more accurate surface roughness by overcoming the disadvantages of small sample length and low precision of the light section method, and is more convenient than stylus. |
| format | Article |
| id | doaj-art-629df9dfbe4e447e8856b7e96f14b742 |
| institution | Kabale University |
| issn | 2768-7236 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Instrumentation and Measurement |
| spelling | doaj-art-629df9dfbe4e447e8856b7e96f14b7422025-01-15T00:04:17ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362024-01-0131910.1109/OJIM.2024.347756810713234Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS)Huashen Guan0https://orcid.org/0009-0006-8578-6963Qiushen Cai1https://orcid.org/0009-0006-6155-5650Xiaobin Li2https://orcid.org/0009-0008-8817-0157Guofu Sun3https://orcid.org/0009-0000-1140-878XProduction Technology Department, Jiangmen Power Supply Bureau of Guangdong Power Grid Company Ltd., Jiangmen, Guangdong, ChinaProduction Technology Department, Jiangmen Power Supply Bureau of Guangdong Power Grid Company Ltd., Jiangmen, Guangdong, ChinaProduction Technology Department, Jiangmen Power Supply Bureau of Guangdong Power Grid Company Ltd., Jiangmen, Guangdong, ChinaProduction Technology Department, Jiangmen Power Supply Bureau of Guangdong Power Grid Company Ltd., Jiangmen, Guangdong, ChinaWith the development of optics, light section method has become a feasible measurement for surface roughness, while the short sampling length is negative to the accuracy. To overcome this defect, this article proposed a measurement under ResNet-based roughness classification and light section with seam-driven image stitching (RCLS). First, the images were classified with ResNet neural network, then stitched and enhanced by scale invariant feature transform (SIFT) and optimized random sample consensus (RANSAC) algorithm for the best visual effect. After this, images were processed by Nobuyuki Otsu method and Freeman chain code tracking algorithm. Least square was also adopted to calculate the optical band edge curve and contour midline. Finally, the roughness contour arithmetic mean deviation model was established to evaluate the surface roughness. The experiments were conducted with vertical milled, planned, and turned samples that self-machined. The light section method had a reduction of 2.75% on the mean relative error compared to stylus and RCLS could further reduce the mean relative error by 1.42%, especially in planned sample. The RCLS could achieve a more accurate surface roughness by overcoming the disadvantages of small sample length and low precision of the light section method, and is more convenient than stylus.https://ieeexplore.ieee.org/document/10713234/Elongated sampling lengthimage stitchinglight sectionseam drivensurface roughness measurement |
| spellingShingle | Huashen Guan Qiushen Cai Xiaobin Li Guofu Sun Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS) IEEE Open Journal of Instrumentation and Measurement Elongated sampling length image stitching light section seam driven surface roughness measurement |
| title | Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS) |
| title_full | Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS) |
| title_fullStr | Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS) |
| title_full_unstemmed | Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS) |
| title_short | Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS) |
| title_sort | research on a surface roughness measurement under resnet based roughness classification and light section with seam driven image stitching rcls |
| topic | Elongated sampling length image stitching light section seam driven surface roughness measurement |
| url | https://ieeexplore.ieee.org/document/10713234/ |
| work_keys_str_mv | AT huashenguan researchonasurfaceroughnessmeasurementunderresnetbasedroughnessclassificationandlightsectionwithseamdrivenimagestitchingrcls AT qiushencai researchonasurfaceroughnessmeasurementunderresnetbasedroughnessclassificationandlightsectionwithseamdrivenimagestitchingrcls AT xiaobinli researchonasurfaceroughnessmeasurementunderresnetbasedroughnessclassificationandlightsectionwithseamdrivenimagestitchingrcls AT guofusun researchonasurfaceroughnessmeasurementunderresnetbasedroughnessclassificationandlightsectionwithseamdrivenimagestitchingrcls |