다층퍼셉트론을 이용한 자동차 번호판 인식에 관한 연구

이의철, 성병문, 이왕헌 · 제어로봇시스템학회 국내학술대회 논문집 · 2014

The Car License Plate Recognition [CLPR] is required in searching the hit-and-run car, measuring the traffic density, investigating the traffic accidents as well as in pursuing a gateway vehicle according to the increased car supplying. The real environment of the CLPR is contaminated not only by snow and rain, illumination changes, but also by the geometrical distortion due to the pose changes between camera and car at the moment of image capturing. We propose Multilayer Perceptron Algorithm in car plate recognition considering such as adverse environment. Especially, in this paper, not only the correlation between recognition rate and execution speed changes are identified, but also the optimized ratio between the number of input, hidden and output layers are determined by the real data while changing the node numbers of input and hidden as well as output layers.

Cited by 0 works.

Authors