• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.06a
• /
• pp.343-347
• /
• 2002

본 논문에서 는 자동차 영상에서 모폴로지 연산을 이용한 번호판 추출 방법을 제안한다. 먼저 입력 받은 자동차 영상을 적응적 임계값을 적용하여 이진화 한다. 이 진화 영상에 대하여 모폴로지 연산의 침식/팽창 과정을 연속적으로 수행하여 번호판 내의 문자영역을 제거하는 opening과정 과 팽창/침식 과정을 연속적으로 수행하여 번호판 내의 문자영역을 확장하는 closing 연산을 병렬 수행한 후 그들간의 차영상을 추출한다. 추출된 차영상에 Geo-correction과 번호판의 일반적인 특성을 이용한 필터링 작업을 수행하여 실제 번호판 영역을 추출한다. 제안한 방법을 구현하고 다양한 각도에서 취득된 다양한 형태의 자동차 영상에 적용하여 본 알고리즘의 효용성을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.275-278
• /
• 2003

자동차 번호판 인식 시스템은 영상획득, 번호판추출, 전처리(이진화), 문자영역 분할, 문자인식 등의 5가지 핵심 부분으로 구성된다. 따라서 자동차 번호판 인식 시스템의 최종 인식율은 각 단계의 성능에 따라 직접적인 영향을 받는다. 본 논문은 영상처리 기법을 이용하여 영상에서 번호판 영역을 추출을 위한 연구로 문자인식 단계에서 높은 인식율을 확보할 수 있도록 빠른 연산속도와 추출 정확성을 높일 수 있는 알고리즘을 제안한다.

• Journal of Intelligence and Information Systems
• /
• v.8 no.1
• /
• pp.87-101
• /
• 2002

In this paper, we proposes the car plate recognition and describe the parking control system using the proposed car plate recognition algorithm. The car plate recognition system using color information and fuzzy c-means algorithm consists of the extraction part of a car plate from a car image and the recognition part of characters in the extracted car plate. This paper eliminates green noise from car image using the mode smoothing and extract plate region using green and white information of RGB color. The codes of extracted plate region is extracted by histogram based approach method and is recognized by fuzzy c-means algorithm. For experimental, we tested 80 car images. We shows that the proposed extraction method is better than that from the color information of RGB and HSI, respectively. So, we can know that the proposed car plate recognition method using fuzzy c-means algorithm was very efficient. We develop the parking control system using the proposed car plate recognition method, which showed performance improvement by the experimental results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.2
• /
• pp.339-345
• /
• 2002

Extracting of car licens plate os important for identifying the car. Since there are some problems such as poor ambient lighting problem, bad weather problem and so on, the car images are distorted and the car license plate is difficult to be extracted. This paper proposes a method of extracting car license plate using motor vehicle regulation. In this method, some features of car license plate according to motor vehicle regulation such as color information, shape are applied to determine the candidate of car license plates. For the result of recognition by neural network, the candidate which has characters and numbers patterns according to motor vehicle regulation is certified as license-plate region. The results of the experiments with 70 samples of real car images shoe the performance of car license-plate extraction by 84.29%, and the recognition rate is 80.81%.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.6
• /
• pp.1686-1692
• /
• 1999

This paper describes the feature area-based vehicle plate recognition system(VPRS). For the extraction of vehicle plate in a vehicle image, we used the method which extracts vehicle plate area from a s vehicle image using intensity variation. For the extraction of the feature area containing character from the extracted vehicle plate, we used the histogram-based approach and the relative location information of individual characters in the extracted vehicle plate. The extracted feature area is used as the input vector of ART2 neural network. The proposed method simplifies the existing complex preprocessing the solves the problem of distortion and noise in the binarization process. In the difficult cases of character extraction by binarization process of previous method, our method efficiently extracts characters regions and recognizes it.

• Journal of Navigation and Port Research
• /
• v.32 no.10
• /
• pp.845-850
• /
• 2008

In this paper, we propose a license plate locating algorithm by using SVM. Tipically, the features regarding license plate format include height-to-width ratio, color, and spatial frequency. The method is dived into three steps which are image acquisition, detecting license plate candidate regions, verifying the license plate accurately. In the course of detecting license plate candidate regions, color filtering and edge detecting are performed to detect candidate regions, and then verify candidate region using Support Vector Machines(SVM) with DCT coefficients of candidates. It is possible to perform reliable license plate location bemuse we can protect false detection through these verification process. We validate our approach with experimental results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.596-599
• /
• 2001

Extracting of car licens plate is important for identifying the car. Since there are some problems such as poor ambient lighting problem, bad weather problem and so on, the car images we distorted and the tar license plate is difficult to be extracted. This paper proposes a method of extracting car license plate using motor vehicle regulation. In this method, some features of car license plate according to motor vehicle regulation such as color information, shape are applied to determine the candidate of car license plates. For the result of recognition by neural network, the candidate which has characters and numbers patterns according to motor vehicle regulation is certified as license-plate region. The results of the experiments with 70 samples of real car images shoe the performance of car license-plate extraction by 84.29%, and the recognition rate is 80.81%.

• Journal of Intelligence and Information Systems
• /
• v.8 no.1
• /
• pp.15-25
• /
• 2002

This paper proposes a vehicle license plate recognition system, which has relatively a simple structure and is highly tolerant of noise, by using the DCT(Discrete Cosine Transform) coefficients extracted from the character region of a license plate and the LVQ(Learning Vector Quantization) neural network. The image of a license plate is taken from a captured vehicle image based on RGB color information, and the character region is derived by the histogram of the license plate and the relative position of individual characters in the plate. The feature vector obtained by the DCT of extracted character region is utilized as an input to the LVQ neural classifier fur the recognition process. In the experiment, 109 vehicle images captured under various types of circumstances were tested with the proposed method, and the relatively high extraction rate of license plates and recognition rate were achieved.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.1
• /
• pp.29-35
• /
• 2009

In this paper by using the image taken from the rear of the vehicle to effectively extract the license plate and how to recognize the characters appearing in the offer. How to existing research on the entire video by following the pre-edge (edge) images to obtain yijinhwa. Qualified heopeu in a binary image (Hough) to convert the horizontal and vertical lines to obtain, using the characteristics of the plates to extract the license plate area. The problem with this method, the processing time is so difficult to handle real-time status of irregular points, and visual contrast with yagangwan border does not appear in the plates to extract the license plate area is that it is not. In addition, the rear of the vehicle license plate area from images taken using the characteristics of the plates myeongamgap changes sutjapok in the area, background area and the number number area of the region confirmed the contrast of the car and identified the number and the number of 42 of distance to extract the license plate area. How to research, the existing damage to the border of the plate to fail to extract the license plate area, a matter of hours to resolve problems in real-time, practical application is processed. Chapter 100 as the results of the experiment the sample video image in a car that far experiment results automatically read license plates have been able to extract the license plate and failing to represent 13% of images, character recognition result of failing to represent the image was 0.4%

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.850-852
• /
• 2005

차량을 포함하는 임의의 영상에서 번호판 추출은 다양한 조명조건 및 배경, 촬영 각도, 번호판 종류 등의 요인으로 인해 고도의 영상처리 과정을 필요로 한다. 본 논문에서는 실제 환경에서 발생할 수 있는 이러한 요인들에 대해 강건한 번호판 추출 방법을 제안한다. 제안하는 방법은 입력영상의 RGB 성분들을 색상성분과 영암성분으로 분리할 수 있는 칼라모델 HSI로 변환하고 H(hue)와 S(saturation)성분을 이용하여 번호판의 배경색상을 고려한 칼라 퍼지지도를 구성한다. 또한, I(intensity)성분을 이용하여 에지밀도를 추출하고 에지밀도 지도에 기반한 영역분리 퍼지지도를 생성한다. 마지막으로, 후보영역 탐색을 위해 칼라 퍼지지도와 영역분리 퍼지지도를 결합하고, 연결성분 해석(Connected Component Analysis)을 통해 ROI(Region Of Interest)를 추출한다. 제안하는 방법의 유효성 검증을 위해 조명 및 촬영 각도에 제한을 거의 두지 않고 촬영된 차량 영상 410장을 실험 영상으로 사용하였다. 실험 결과에서는 $97.1\%$의 효과적인 추출 성공률을 볼 수 있었다.