훈련예제 병합을 이용한 자동차 차량번호판 문자인식 성능 향상 방안
백남철, 이상협, 류광렬 · 대한토목학회논문집 D · 2006
To cope with traffic congestion, traffic accidents and lack of parking facilities, caused by dramatic increase in total vehicle number, vigorous researches on managing vehicles efficiently are done, both domestically and internationally. The vehicle license plate recognition makes effective management of traffic possible, with its wide application in many fields, covering from speed enforcement, collecting toll, stolen vehicle detection to parking management. The vehicle license plate recognition system causes high cost for collecting training data. Many researches are done by using the virtual sample method, which can be effective for utilizing limited number of training data by generating virtual sample. This paper investigates techniques to improve the performance of vehicle license plate recognition by using the training data's annexation. Also, popular methods for virtual sample creation used for text recognition algorithm are analyzed and their effectiveness is verified.
Cited by 0 works.