Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision
Abstract Whether the wheelset of a high-speed train has defects such as cracks is very important to the safety of high-speed trains. Hence, the wheelset must be regularly inspected for flaws. For flaw detection of a wheelset, it is necessary to record the axle end information of the wheelset to corr...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-12-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-022-00178-2 |
| _version_ | 1828086875700592640 |
|---|---|
| author | Yuchun He Dezhi Liu Yong Zeng Qian Lu Suheng Yao Yuxin Yuan |
| author_facet | Yuchun He Dezhi Liu Yong Zeng Qian Lu Suheng Yao Yuxin Yuan |
| author_sort | Yuchun He |
| collection | DOAJ |
| description | Abstract Whether the wheelset of a high-speed train has defects such as cracks is very important to the safety of high-speed trains. Hence, the wheelset must be regularly inspected for flaws. For flaw detection of a wheelset, it is necessary to record the axle end information of the wheelset to correlate with the flaw detection results. To quickly and accurately identify the axle end mark of the wheelset, an automatic identification method based on machine vision is proposed. Our method identifies seven types of marks on the axle end, including the smelting number, steel grade number, unit number, sequence number, year and month, axle type mark, and the azimuth mark. Using the established automatic identification method of axle end marks, based on Retinex theory, an improved dual-core Laplacian combined with Gaussian filtering operation is proposed to solve the problem of the low contrast of the wheelset axle end image. An improved image tilt correction algorithm based on the combination of Hough circle detection and bilinear interpolation is proposed, which solves the angle tilt problem of the target character area of the axis end image. To handle the various types of axis end markers and the small amount of data, a retraining method to improve recognition accuracy is proposed. This method first uses Chi_Sim as the basic font for training and then retrains based on the trained font. Finally, Tesseract-OCR is used to improve the accuracy of the recognition results. Experiments are carried out by developing an automatic recognition program for axle end marks. The results show that the proposed method can effectively identify and classify seven-character types, and the recognition accuracy reaches 96.88% while the recognition time of each image is 5.88 s. |
| first_indexed | 2024-04-11T05:04:01Z |
| format | Article |
| id | doaj.art-3ef79d41925347339b7f8844dbf44ad2 |
| institution | Directory Open Access Journal |
| issn | 1875-6883 |
| language | English |
| last_indexed | 2024-04-11T05:04:01Z |
| publishDate | 2022-12-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj.art-3ef79d41925347339b7f8844dbf44ad22022-12-25T12:28:49ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832022-12-0115111910.1007/s44196-022-00178-2Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine VisionYuchun He0Dezhi Liu1Yong Zeng2Qian Lu3Suheng Yao4Yuxin Yuan5College of Mechanical Engineering, Yancheng Institute of TechnologyCollege of Mechanical Engineering, Yancheng Institute of TechnologyCollege of Mechanical Engineering, Yancheng Institute of TechnologyCollege of Mechanical Engineering, Yancheng Institute of TechnologyCollege of Mechanical Engineering, Yancheng Institute of TechnologyCollege of Mechanical Engineering, Yancheng Institute of TechnologyAbstract Whether the wheelset of a high-speed train has defects such as cracks is very important to the safety of high-speed trains. Hence, the wheelset must be regularly inspected for flaws. For flaw detection of a wheelset, it is necessary to record the axle end information of the wheelset to correlate with the flaw detection results. To quickly and accurately identify the axle end mark of the wheelset, an automatic identification method based on machine vision is proposed. Our method identifies seven types of marks on the axle end, including the smelting number, steel grade number, unit number, sequence number, year and month, axle type mark, and the azimuth mark. Using the established automatic identification method of axle end marks, based on Retinex theory, an improved dual-core Laplacian combined with Gaussian filtering operation is proposed to solve the problem of the low contrast of the wheelset axle end image. An improved image tilt correction algorithm based on the combination of Hough circle detection and bilinear interpolation is proposed, which solves the angle tilt problem of the target character area of the axis end image. To handle the various types of axis end markers and the small amount of data, a retraining method to improve recognition accuracy is proposed. This method first uses Chi_Sim as the basic font for training and then retrains based on the trained font. Finally, Tesseract-OCR is used to improve the accuracy of the recognition results. Experiments are carried out by developing an automatic recognition program for axle end marks. The results show that the proposed method can effectively identify and classify seven-character types, and the recognition accuracy reaches 96.88% while the recognition time of each image is 5.88 s.https://doi.org/10.1007/s44196-022-00178-2Machine visionTrain wheelsetImage enhancementTilt correctionCharacter recognition |
| spellingShingle | Yuchun He Dezhi Liu Yong Zeng Qian Lu Suheng Yao Yuxin Yuan Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision International Journal of Computational Intelligence Systems Machine vision Train wheelset Image enhancement Tilt correction Character recognition |
| title | Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision |
| title_full | Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision |
| title_fullStr | Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision |
| title_full_unstemmed | Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision |
| title_short | Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision |
| title_sort | research on the recognition method of the axle end mark of a train wheelset based on machine vision |
| topic | Machine vision Train wheelset Image enhancement Tilt correction Character recognition |
| url | https://doi.org/10.1007/s44196-022-00178-2 |
| work_keys_str_mv | AT yuchunhe researchontherecognitionmethodoftheaxleendmarkofatrainwheelsetbasedonmachinevision AT dezhiliu researchontherecognitionmethodoftheaxleendmarkofatrainwheelsetbasedonmachinevision AT yongzeng researchontherecognitionmethodoftheaxleendmarkofatrainwheelsetbasedonmachinevision AT qianlu researchontherecognitionmethodoftheaxleendmarkofatrainwheelsetbasedonmachinevision AT suhengyao researchontherecognitionmethodoftheaxleendmarkofatrainwheelsetbasedonmachinevision AT yuxinyuan researchontherecognitionmethodoftheaxleendmarkofatrainwheelsetbasedonmachinevision |