Optical High-Speed Rolling Mark Detection Using Object Detection and Levenshtein Distance

This paper presents an automated high-speed rolling mark recognition system for railroad rails utilizing image processing techniques. Rolling marks, which consist of numbers, letters, and special characters, were engraved into the rail web as 3D information. These marks provide crucial details regarding manufacturer, steel quality, year production, profile. As a result, they empower infrastructure managers to gain valuable insights their infrastructure. The captured using standard color camera under dark field illumination. individual characters was achieved through state-of-the-art deep neural network object detection, specifically employing YOLO architecture. By leveraging reference detected can then be accurately interpreted corrected. correction process involves calculating weighted Levenshtein distance, ensuring that identify rectify partially misidentified marks. Through proposed system, accurate reliable identification achieved, even in cases there partial errors detection process. novel thus has potential substantially improve management maintenance