• Structural Engineering and Mechanics
• /
• 제5권4호
• /
• pp.471-490
• /
• 1997

In this paper, the classical Irons' patch tests which have been generally accepted for the convergence proof of a finite element are performed for Mindlin plate bending elements with a special emphasis on the nonconforming elements. The elements considered are 4-node and 8-node quadrilateral isoparametric elements which have been dominantly used for the analyses of plate bending problems. It was recognized from the patch tests that some nonconforming Mindlin plate elements pass all the cases of patch tests even though nonconforming elements do not preserve conformity. Then, the clues for the Mindlin plate element to pass the Irons' patch tests are investigated. Also, the convergent characteristics of some nonconforming Mindlin plate elements that do not pass the Irons' patch tests are examined by weak patch tests. The convergence tests are performed on the benchmark numerical problems for both nonconforming elements which pass the patch tests and which do not. Some conclusions on the relationship between the patch test and convergence of nonconforming Mindlin plate elements are drawn.

• ETRI Journal
• /
• 제37권2호
• /
• pp.251-261
• /
• 2015

We present a novel method for real-time automatic license plate detection in high-resolution videos. Although there have been extensive studies of license plate detection since the 1970s, the suggested approaches resulting from such studies have difficulties in processing high-resolution imagery in real-time. Herein, we propose a novel cascade structure, the fastest classifier available, by rejecting false positives most efficiently. Furthermore, we train the classifier using the core patterns of various types of license plates, improving both the computation load and the accuracy of license plate detection. To show its superiority, our approach is compared with other state-of-the-art approaches. In addition, we collected 20,000 images including license plates from real traffic scenes for comprehensive experiments. The results show that our proposed approach significantly reduces the computational load in comparison to the other state-of-the-art approaches, with comparable performance accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2509-2528
• /
• 2019

There are various styles of license plates for different countries and use cases that require style-specific methods. In this paper, we propose and illustrate a multi-style license plate recognition system. The proposed system performs a series of processes for license plate candidates detection, structure classification, character segmentation and character recognition, respectively. Specifically, we introduce a license plate structure classification process to identify its style that precedes character segmentation and recognition processes. We use a K-Nearest Neighbors algorithm with pre-training steps to recognize numbers and characters on multi-style license plates. To show feasibility of our multi-style license plate recognition system, we evaluate our system for multi-style license plates covering single line, double line, different backgrounds and character colors on Korean and the U.S. license plates. For the evaluation of Korean license plate recognition, we used a 50 minutes long input video that contains 138 vehicles of 6 different license plate styles, where each frame of the video is processed through a series of license plate recognition processes. From two experiments results, we show that various LP styles can be recognized under 50 ms processing time and with over 99% accuracy, and can be extended through additional learning and training steps.

• 미래기술융합논문지
• /
• 제2권4호
• /
• pp.7-11
• /
• 2023

본 연구에서는 Convolutional Neural Networks(CNNs) 기법을 이용하여 차량 번호판을 인식하는 방법을 제시하였다. 차량 번호판은 일반적으로 차량의 공식 식별 목적으로 사용됩니다. 대부분의 일반적인 광학 문자 인식(OCR) 기술은 문서에 인쇄된 문자를 인식하는 데는 효과적이지만 번호판의 등록 번호는 식별할 수 없다. 그리고 번호판 감지에 대한 기존 접근 방식에서는 차량이 움직이지 않고 정지해 있어야 한다. 번호판 감지에 대한 이러한 문제를 해결하기 위해 CNN 기법을 활용한 번호판 인식 기법을 제안한다. 먼저 획득된 차량 번호판 이미지의 데이터베이스를 생성하고 CNN 기법을 활용하여 자동차 번호판 문자를 인식한다. 본 연구의 결과는 주차관리 시스템과 단속 카메라 등에 유용하게 활용 될 수 있다.

• 한국산업융합학회 논문집
• /
• 제21권4호
• /
• pp.175-181
• /
• 2018

Stamping process and rubber pad forming process were performed to manufacture the bipolar plate for fuel cells. For that, a vacuum die casting process and a semi-solid forming process wherein liquid-state materials were used were adopted. After preparing the blank with the stainless steel thin plate having a thickness of 0.1 mm, the bipolar plate channel was formed with the stamping process and rubber pad forming process. The depth of the bipolar plate channel prepared by the stamping method was 0.45 mm and the depth of the bipolar plate channel prepared by the rubber pad forming process was 0.41 mm. Meanwhile, with the vacuum die casting and semi solid forming, the bipolar plate having a channel depth of 0.3 mm, same as the size of the die, could be formed.

• Structural Engineering and Mechanics
• /
• 제5권1호
• /
• pp.69-83
• /
• 1997

A new efficient hybrid/mixed thin~moderately thick plate bending element with 6-node (HM6-14) is formulated based on the Reissner-Mindlin plate bending theory. The convergence of this element is proved by error estimate theories and verified by patch test respectively. Numerical studies on such an element as HM6-14 demonstrate that it has remarkable convergence, invariability to geometric distorted mesh situations, to axial rotations, and to node positions, and no "locking" phenomenon in thin plate limit. The present element is suitable to many kinds of shape and thin~moderately thick plate bending problems. Further, in comparison with original hybrid/mixed plate bending element HP4, the present element yields an improvement of solutions. Therefore, it is an efficient element and suitable for the development of adaptive multi-field finite element method (FEM).

• 한국소음진동공학회논문집
• /
• 제20권12호
• /
• pp.1153-1160
• /
• 2010

A circular plate is the main part of a circular saw blade, which is widely used in industrial cutting tools. In experiments using a circular saw containing slots, we observed that a number of natural frequencies are simultaneously emerged in specific frequency regions. The interesting phenomenon is called the frequency convergence. Effects of design parameters such as the number, the length and the width of slots, on the frequency-convergence phenomenon are analyzed by FEM simulations using ALGOR. The frequency-convergence phenomenon will be intensified when the number, length and width of slots increase.

• 한국광학회지
• /
• 제32권5호
• /
• pp.220-229
• /
• 2021

눈부심 방지를 위한 확산판의 투과율과 연색지수 향상을 위한 양자점 필름의 농도가 고출력 직하형 백색 LED 조명의 광특성에 미치는 영향을 조사했다. 확산판의 투과율이 감소할 경우 조명의 휘도는 줄어들었고 색좌표, 상관색온도는 별다른 변화를 보이지 않았으며 연색지수는 약간 상승했다. 시야각에 따른 광특성의 편차는 거의 없었고 휘도 분포는 람버시안 분포에 가까웠다. 양자점 필름의 농도가 증가할 경우 스펙트럼 상 적색 성분이 늘어나면서 이 성분의 비중을 표현하는 색좌표 x가 증가했고 상관색온도는 약 6000 K에서 4000 K 부근으로 현저히 감소했다. 아울러 조명의 구조를 최적화하면 연색지수가 95까지 증가함을 확인했다. 이런 결과는 적절한 투과율의 확산판과 양자점 필름의 조합을 통해 눈부심이 없고 시야각에 따른 색편차가 거의 없으며 특히 색좌표의 가변이 가능한 고연색성의 조명 구현이 가능함을 보여준다.

• 한국산업융합학회 논문집
• /
• 제24권6_2호
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• Journal of Information Processing Systems
• /
• 제12권4호
• /
• pp.661-680
• /
• 2016

The vehicle license plate recognition (VLPR) system analyzes and monitors the speed of vehicles, theft of vehicles, the violation of traffic rules, illegal parking, etc., on the motorway. The VLPR consists of three major parts: license plate detection (LPD), license plate character segmentation (LPCS), and license plate character recognition (LPCR). This paper presents an efficient method for the LPCS and LPCR of Korean vehicle license plates (LPs). LP tilt adjustment is a very important process in LPCS. Radon transformation is used to correct the tilt adjustment of LP. The global threshold segmentation method is used for segmented LP characters from two different types of Korean LPs, which are a single row LP (SRLP) and double row LP (DRLP). The cross-correlation matching method is used for LPCR. Our experimental results show that the proposed methods for LPCS and LPCR can be easily implemented, and they achieved 99.35% and 99.85% segmentation and recognition accuracy rates, respectively for Korean LPs.