With the introduction of the one-tolling and smart-tolling, Vehicle number recognition technology of ITS imaging equipment that was used to prevent the escape and tolling evasion will play an important role in the collection system. Korea Highway Corporation will prepare a ITSK-00088 Performance Assessment to improve the license plate recognition. and there are a number of efforts to improve the accuracy of vehicle number recognition. But even if the ITS equipment had passed the performance assessment, it is in a situation which does not achieve the target value due to physical and environmental factors. we propose a method for acquiring the additional information(color, type, pattern) including plate number of the vehicle in order to improve the recognition rate of the vehicle number. Through that link the vehicle additional information, vehicle specifications DB, image analysis system, the goal is to build a system that can be identified for the misrecognized and unrecognized vehicle.

With the introduction of the one-tolling and smart-tolling, Vehicle number recognition technology of ITS imaging equipment that was used to prevent the escape and tolling evasion will play an important role in the collection system. Korea Highway Corporation will prepare a ITSK-00088 Performance Assessment to improve the license plate recognition. and there are a number of efforts to improve the accuracy of vehicle number recognition. But even if the ITS equipment had passed the performance assessment, it is in a situation which does not achieve the target value due to physical and environmental factors. we propose a method for acquiring the additional information(color, type, pattern) including plate number of the vehicle in order to improve the recognition rate of the vehicle number. Through that link the vehicle additional information, vehicle specifications DB, image analysis system, the goal is to build a system that can be identified for the misrecognized and unrecognized vehicle.

자동차 번호판 인식 시스템에서 가장 중요한 요소가 자동차 이미지 영역에서 번호판 영역을 정확히 검출해 내는 것이다. 자동차 이미지에서 번호판 영역을 추출하기 위한 방법으로 색상과 밝기 정보와 자동차 번호판의 가로 세로 비율 등 번호판을 인식할 수 있는 정보를 혼용한 ACL 알고리즘을 제안한다. ACL 알고리즘을 사용함으로써 기존의 색상 정보나 명암 정보만을 이용할 경우 자동차 번호판 영역 추출이 잘되지 않는 문제를 해소시켜 준다. 본 논문에서 제안하는 ACL 알고리즘은 자동차 이미지에서 번호판 영역을 추출할 경우 색상 정보와 명암정보, 기타 자동차 번호판을 판단할 수 있는 정보를 모두 이용한다. ACL 알고리즘을 이용하여 번호판 추출 실험을 한 결과 97%의 추출률을 보였다. ACL 알고리즘을 이용하여 추출된 번호판을 이용하여 문자 영역, 문자 인식을 한 결과 92%의 결과를 보였다.