• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.3
• /
• pp.12-19
• /
• 2008

Detection of a number plate consists of three stages; division of a number plate, extraction of each character from the plate, recognition of the characters. Among of these three states, division stage of a number plate is the most important part and also the most time-consuming state. This paper suggests an effective region extraction method of a number plate for various images obtained from unmanned inspection systems of illegal parking violation, especially when we have to consider the diverse surrounding environments of roads. Our approaching method detects each region by investigating the characteristics in changes of brightness and intensity between the background part and character part, and the characteristics on character parts such as the sizes, heights, widths, and distance in between two characters. The method also divides a number plate into different types of the plate. This research can solve the number plate region detection failure problems caused by plate edge damages not only for Korean domestic number plates but also for new European style number plates. The method also reduces the time consumption by processing the detection in real-time, therefore, it can be used as a practical solution.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.500-502
• /
• 1999

영상으로부터 유용한 정보를 얻는 방법 중 하나인 문자인식이 이루어지기 위해서는 주어진 영상의 이진화가 필수적이다. 이진화 알고리즘은 다양한 방법으로 연구되어 왔다. 기존의 이진화 알고리즘은 일반 영상에서는 우수한 성능을 보이나, 그림자가 포함된 영상의 이진화 결과는 그림자가 없는 영상에서 만큼의 성능을 기대하기 어렵다. 이진화의 결과에 따라 문자의 인식율이 크게 좌우되므로 환경에 독립적인 이진화 알고리즘에 관한 연구는 중요하다고 하겠다. 본 논문에서는 자동화 번호판 영상을 대상으로 문자인식의 전처리 단계라고 할 수 있는 이진화를 환경에 독립적으로 수행하기 위하여 모폴로지를 적용하여 실험하고, 특히 그림자가 존재하는 영상에서의 이진화 성능을 기존의 이진화 알고리즘과 비교 분석해 본다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.121-123
• /
• 2004

차량 번호판 인식 시스템은 무인 카메라 등의 영상 장치로부터 입력된 차량 이미지로부터, 차량 번호판 정보를 읽어내는 시스템이다. 이러한 차량 번호판 인식 시스템의 응용 시스템 중 과속 차량 단속과 같은 일부 응용 시스템은 번호판의 글자나 숫자를 다른 글자나 숫자로 잘못 인식할 경우 심각한 문제를 발생시킬 수 있다. 이러한 시스템을 위해 우리는 인식 결과에 대한 신뢰도가 낮은 경우 인식을 포기 또는 위임하는 신중한 분류기(Cautious Classifier)를 이용 인식 시스템을 구성하였다. 또한 학습 예제의 가중치를 조절하는 방법을 사용 이러한 신중한 분류기의 성능을 향상 시켰다. 실제 번호판 인식 실험 결과 우리가 제안한 가중치 부여 방식이 차량 번호판 인식 문제에 좋은 결과를 보임을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.82-85
• /
• 2009

본 논문에서는 실제 도로환경의 속도 표지판 영역 추출 및 인식 방법을 제안한다. 화소의 색상정보를 이용하여 속도 표지판 영역을 추출하고 추출된 속도 표지판 영역 안에서 숫자 영역만 다시 추출한다. 표지판의 경사여부를 판단하여 시계방향, 반시계방향으로 각각 표지판을 회전시켜 기울기를 보정한 후 인식을 행함으로써 인식률을 제고한다. 도로환경의 동영상을 대상으로 인식을 행한 결과 일반적인 속도표지판 뿐 아니라 기울어진 환경에서도 매우 강건한 인식 결과를 보인다.

• Progress in Medical Physics
• /
• v.21 no.1
• /
• pp.52-59
• /
• 2010

To examine among patients with vertebral compression fracture the extent to which signal-to-noise ratio (SNR) and Apparent Diffusion Coefficient (ADC) values at the lumbar vertebral compression fracture site vary on diffusion-weighted MR images according to varying b values on the 1.5T MR device. Diffusion-weighted MR images of 30 patients with compression fracture due to chronic osteoporosis who underwent vertebral MRI from Jan. 2008 to Nov. 2009 were respectively obtained using a 1.5-T MR scanner with the b values increased from 400, 600, 800, 1,000 to $1,200\;s/mm^2$. For diffusion-weighted MR images with different b values, the signal-to-noise ratio (SNR) was assessed at three sites: the site of compression fracture of the lumbar vertebral body at L1 to L5, and both the upper and lower discs of the said fracture site, while for ADC map images with different b values, the SNR and ADC were respectively assessed at those three sites. As a quantitative analysis, diffusion-weighted MR images and ADC map images with b value of $400\;s/mm^2$ (the base b values) were respectively compared with the corresponding images with each different b value. As far as qualitative analysis is concerned, for both diffusion-weighted MR and ADC map images with b value of $400\;s/mm^2$, the extent to which signal intensity values obtained at the site of compression fracture of the lumbar vertebral body at L1 to L5 vary according to the increasing b values were examined. The quantitative analysis found that for both diffusion-weighted MR and ADC map images, as the b values increased, the SNR were relatively lowered at all the three sites, compared to the base b value. Also, it was found that as the b values increased, ADC valueswere relatively lowered at all the three sites on ADC map images. On the other hand, the qualitative analysis found that as the b values increased to more than $400\;s/mm^2$, the signal intensity gradually decreased at all the sites, while at the levels of more than $1,000\;s/mm^2$, severe image noises appeared at all of the three sites. In addition, higher signal intensity was found at the site of compression fracture of the lumbar vertebral body than at the discs. Findings showed that with the b value being increased, both the signal-to-noise ratio (SNR) and Apparent Diffusion Coefficient (ADC) values gradually decreased at all the sites of the lumbar vertebral compression fracture and both the upper and lower discs of the fracture site, suggesting that there is a possibility of a wider range of applications to assessment of various vertebral pathologies by utilizing multi b values in the diffusion-weighted MRI examination.

• Optical Science and Technology
• /
• v.5 no.3
• /
• pp.16-21
• /
• 2001

• Journal of radiological science and technology
• /
• v.11 no.1
• /
• pp.79-87
• /
• 1988

• Proceedings of the Korean Nuclear Society Conference
• /
• 2003.05a
• /
• pp.365.2-365.2
• /
• 2003

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1415-1422
• /
• 2011

In this paper, full color billboards for the efficient expression of the resolution to offer dual-scanning control method, using the LED display it on a fixed pixel video signal to the pixel dot pattern was changed. And DICT(Dynamic Image Correction Technology) using the main controller in accordance with video information, histogram equalization of image gray scale values to be uniformly distributed, and dynamically improves image quality by converting the area, and a dual auto-scan input video switching controller board as the pixels in the LED Module by controlling the physical manifestation of the existing board LED pixel dots than 4 times the resolution proposes a technique that can be expressed and made it through testing verified the performance.

• Journal of the Korean Society of Radiology
• /
• v.9 no.6
• /
• pp.349-356
• /
• 2015

The study is to recognize the interactions with bone ages by measuring the length between the end of the bone and the growth plate on selected highest weight of regions of seven for bone maturity in TW3 method. The experiment is subjected on seventy-two children (36 males, 36 females) who have examined the growth plate test from March, 2014 to March, 2015 and implemented a regression analysis by measuring the length between the end of the bone and the growth plate in Hand AP image of the children. In result, each bone age has produced a mean value and a standard deviation corresponding to the specific range and as bone age increases the length between the end of the bone and the growth plate decreased. In addition, female children showed lower mean value in comparison to male and also the measurement of the length between the end of the bone and the growth plate and its bone age are shown to be statistically valid(p<0.001) according to the results of regression analysis using its result value. Therefore, the probability of prediction on the bone age read off through the applied TW3 method and regression equation in the Hand AP image of the children.