Author(s)

Zijing Yi, Luo Yang, Yifei Liao, Hao Luo, Tian Bai

Corresponding Author

Tian Bai

ABSTRACT

This paper presents a VIN (Vehicle Identification Number) recognition system based on machine vision. By capturing the VIN code on the car through the camera, the management system of unlicensed merchandise car garage is realized. The system achieves locally adaptive non-linear interference detection through improved threshold partition and morphological change pretreatment methods. Experiments show that the algorithm can be well adapted to dynamic environment and effectively improve the recognition accuracy.The algorithm fully considers the problems of backlighting and low illumination, and is simple in calculation and short in processing time. It is suitable for embedded devices with low computational speed.

KEYWORDS

Machine vision, management system, Nonlinear interference detection