Improvement of End-of-Life Vehicle Chassis Number Reading Software Using AI-OCR
AI-OCRを用いた使用済み自動車用車台番号読取ソフトウェアの改良
- Delivery
- Available on the other site
- Click here to order.
- Publication code
- 20264400
- Paper/Info type
- JSAE Transaction
Vol.57 No.3
- Pages
- 581-586(Total 6 p)
- Date of publication
- May 2026
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | 論文 Translation |
|---|---|
| Category(E) | Paper |
| Author(J) | 1) 中村 格芳, 2) 池坊 繁屋, 3) 八畝田 諭, 4) 山﨑 均 |
| Author(E) | 1) Masayoshi Nakamura, 2) Shigeya Ikebo, 3) Satoru Yaseda, 4) Hitoshi Yamasaki |
| Affiliation(J) | 1) 明石工業高等専門学校, 2) 名古屋文理大学, 3) (株)荒谷商会, 4) (株)荒谷商会 |
| Abstract(J) | 2026年度より実施予定の資源回収インセンティブ制度に対応するため，AI-OCRを用いた車台番号読み取りソフトウェアを開発したが読み取り精度は64%と低かった．本研究では読み取り精度向上に取り組み一定の成果が得られた．また,プレートのデザインが精度に影響を与えるなど,今後の課題も明らかとなった． Translation |
| Abstract(E) | Starting in April 2026, a new regulation will require accurate management of parts removed from end-of-life vehicles (ELVs). This demands precise reading of vehicle identification numbers (VINs) and tracking of related part information. To address this, we developed VIN reading software, but its recognition accuracy was initially inadequate. In this study, we aimed to improve the software's accuracy. Through testing and analysis, we succeeded in enhancing recognition performance. Additionally, we identified new challenges, such as the impact of VIN plate design on reading accuracy, which must be considered in future improvements. |
