An Automatic Detection Model for Low-Contrast Discrete Defects on Aluminum Alloy Wheels
Jian Yang, Ping Chen, Mingquan Wang · 2025
Read An Automatic Detection Model for Low-Contrast Discrete Defects on Aluminum Alloy Wheels by Jian Yang, Ping Chen, Mingquan Wang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12788246.txt.
Description
Jian Yang, Ping Chen, and Mingquan Wang present in 2025 an automatic vision model for spotting faint, scattered flaws in cast aluminum car wheels from X-ray images. Casting leaves images with low contrast and broken flaw edges, and complex backgrounds fool older methods. Their framework first cleans the images. A special pinwheel shaped filter catches edge detail. A two stage feature network sharpens location, and an attention block resists background noise.
On their own wheel data set, the model beat the base method by clear margins in detection accuracy and recall while running at thirty nine frames per second. The authors argue the design suits live factory inspection of wheel hubs.
Catalog record
| CREATOR | Jian Yang, Ping Chen, Mingquan Wang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |