Abstract
In recent years, there is a demand for accurate reading of the Vehicle Identification Numbers (VIN) stamped on End-of-Life Vehicles (ELV) in order to manage which parts have been removed from each ELV. In this study, VIN reading software was developed to realize individual management of ELVs and their parts, and the verification and improvement of its accuracy were discussed.
To realize individual management of ELVs and their parts, we used AI-OCR to read VINs and verified the accuracy of the software. As a result, we were able to understand the characteristics of the software and text strings that are easily misrecognized. In the future, we plan to incorporate these obtained results into our reading software to further improve accuracy.
