• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.121-126
• /
• 2022

The number of vehicles has increased exponentially over the past 20 years due to technological advancements. It is becoming almost impossible to manually control and manage the traffic in a city like Karachi. Without license plate recognition, traffic management is impossible. The Framework for License Plate Detection & Recognition to overcome these issues is proposed. License Plate Detection & Recognition is primarily performed in two steps. The first step is to accurately detect the license plate in the given image, and the second step is to successfully read and recognize each character of that license plate. Some of the most common algorithms used in the past are based on colour, texture, edge-detection and template matching. Nowadays, many researchers are proposing methods based on deep learning. This research proposes a framework for License Plate Detection & Recognition using a custom YOLOv5 Object Detector, image segmentation techniques, and Tesseract's optical character recognition OCR. The accuracy of this framework is 0.89.

• 방송공학회논문지
• /
• 제24권5호
• /
• pp.713-725
• /
• 2019

번호판 자동인식(ALPR: Automatic License Plate Recognition)은 지능형 교통시스템 및 비디오 감시 시스템 등 많은 응용 분야에서 필요한 기술이다. 대부분의 연구는 자동차를 대상으로 번호판 감지 및 인식을 연구하였고, 오토바이를 대상으로 번호판 감지 및 인식은 매우 적은 편이다. 자동차의 경우 번호판이 차량의 전방 또는 후방 중앙에 위치하며 번호판의 뒷배경은 주로 단색으로 덜 복잡한 편이다. 그러나 오토바이의 경우 킥 스탠드를 이용하여 세우기 때문에 주차할 때 오토바이는 다양한 각도로 기울어져 있으므로 번호판의 글자 및 숫자 인식하는 과정이 훨씬 더 복잡하다. 본 논문에서는 다양한 각도로 주차된 오토바이 데이터세트에 대하여 번호판의 문자 인식 정확도를 높이기 위하여 2-스테이지 YOLOv2 알고리즘을 사용하여 오토바이 영역을 선 검출 후 번호판 영역을 검지한다. 인식률을 높이기 위해 앵커박스의 사이즈와 개수를 오토바이 특성에 맞추어 조절하였다. 그 후 기울어진 번호판을 검출한 후 영상 워핑 알고리즘을 적용하였다. 모의실험 결과, 기존 방식의 인식률이 47.74%에 비해 제안된 방식은 80.23%의 번호판의 인식률을 얻었다. 제안된 방법은 전체적으로 오토바이 번호판 특성에 맞는 앵커박스와 이미지 워핑을 통해서 다양한 기울기의 오토바이 번호판 문자 인식을 높일 수 있었다.

• Earthquakes and Structures
• /
• 제15권5호
• /
• pp.463-471
• /
• 2018

The virtual forces of the original local flexibility method are restricted to inducing stress on the local parts of a structure. To circumvent this restriction, we developed a pseudo local flexibility (PLFM) method that can successfully detect damage to hyperstatic beam structures using fewer modes. For this study, we further developed the PLFM so that it could detect damage in plate structures. We also devised the theoretical background for the PLFM with non-local virtual forces for plate structures, and both the lateral and rotary degree of freedom (DOF) measurements were considered separately. This study investigates the effects of the number of modes, the actual location that sustained damage, multiple damage locations, and noise in modal parameters for the damage detection results obtained from damaged numerical plates. The results revealed that the PLFM can be used for damage detection, localization, and quantification for plate structures, regardless of the use of the lateral DOF and/or rotary DOF.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권10호
• /
• pp.3490-3507
• /
• 2014

License plate detection (LPD) is one of the most important aspects of an automatic license plate recognition system. Although there have been some successful license plate recognition (LPR) methods in past decades, it is still a challenging problem because of the diversity of plate formats and outdoor illumination conditions in image acquisition. Because the accurate detection of license plates under different conditions directly affects overall recognition system accuracy, different methods have been developed for LPD systems. In this paper, we propose a license plate detection method that is rapid and robust against variation, especially variations in illumination conditions. Taking the aspects of accuracy and speed into consideration, the proposed system consists of two stages. For each stage, Haar-like features are used to compute and select features from license plate images and a cascade classifier based on the concatenation of classifiers where each classifier is trained by an AdaBoost algorithm is used to classify parts of an image within a search window as either license plate or non-license plate. And it is followed by connected component analysis (CCA) for eliminating false positives. The two stages use different image preprocessing blocks: image preprocessing without adaptive thresholding for the first stage and image preprocessing with adaptive thresholding for the second stage. The method is faster and more accurate than most existing methods used in LPD. Experimental results demonstrate that the LPD rate is 98.38% and the average computational time is 54.64 ms.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1166-1174
• /
• 2017

In general, the detection of the vehicle license plate is a previous step of license plate recognition and has been actively studied for several decades. In this paper, we propose an algorithm to detect a license plate area of a moving vehicle from a video captured by a fixed camera installed on the road using the Convolution Neural Network (CNN) technology. First, license plate images and non-license plate images are applied to a previously learned CNN model (AlexNet) to extract and classify features. Then, after detecting the moving vehicle in the video, CNN detects the license plate area by comparing the features of the license plate region with the features of the license plate area. Experimental result shows relatively good performance in various environments such as incomplete lighting, noise due to rain, and low resolution. In addition, to protect personal information this proposed system can also be used independently to detect the license plate area and hide that area to secure the public's personal information.

• 한국컴퓨터정보학회논문지
• /
• 제26권1호
• /
• pp.93-101
• /
• 2021

본 논문에서는 실제 도로의 다양한 상황에서도 차량 번호판을 정확하게 탐지하기 위해 차량 번호판의 후보 지역을 공간 집중 영역으로 사용하는 차량 번호판 탐지 모델을 제안하였다. 먼저, 기존의 WPOD-NET이 전처리 과정에서 검출된 차량 영역을 이용하기 때문에 넓은 탐지 후보 영역으로 인해 불필요한 노이즈가 포함되어 탐지 정확도가 낮아짐을 확인하였다. 이를 개선하기 위해 차량 번호판의 후보 지역을 공간 집중 영역으로 사용하는 차량 번호판 탐지 모델을 제안하였고, 제안한 방법이 기존 WPOD-NET보다 탐지 정확도를 어느 정도 개선하는지 분석하기 위해 GT 데이터를 기반으로 최적의 공간 집중 영역을 설정한 경우와 함께 탐지 정확도를 비교하였다. 실험에 따르면 제안된 모델이 기존 WPOD-NET에 비해 타이트한 탐지 후보 영역을 갖기 때문에 약 20% 더 높은 탐지 정확도를 보임을 확인하였다.

• 한국컴퓨터정보학회논문지
• /
• 제16권4호
• /
• pp.53-60
• /
• 2011

본 논문에서는 저해상도 영상에서 번호판 인식 성능 향상을 위해 번호판 검출 기술과 초해상도 복원 기술의 융합 방법을 제안한다. 제안된 알고리즘에서 번호판 검출 부분은 구조적 패턴 특징을 기반으로 하였으며, 초해상도 부분은 칼만 필터 기반 순차적 데이터 방법으로 구성된다. 제안한 융합 방법은 입력 영상에서 번호판 검출 여부에 따라 (i) 전체 영상에 대한 초해상도 복원 과정을 거친 후 고해상도 번호판 영상을 얻는 방법과, (ii) 번호판 검출 후 검출된 번호판 영역에 대해 초해상도 복원을 수행하여 고해상도 번호판 영상을 얻는 방법으로 나뉜다. 다양한 환경에서의 모의 실험을 통해 제안된 융합 방법의효용성을 입증하였다. 다양한 환경에서의 모의 실험을 통해 제안된 융합 방법의 효용성을 입증하였다.

• Structural Engineering and Mechanics
• /
• 제54권2호
• /
• pp.239-256
• /
• 2015

An adaptive-scale damage detection strategy based on a wavelet finite element model (WFEM) for thin plate structures is established in this study. Equations of motion and corresponding lifting schemes for thin plate structures are derived with the tensor products of cubic Hermite multi-wavelets as the elemental interpolation functions. Sub-element damages are localized by using of the change ratio of modal strain energy. Subsequently, such damages are adaptively quantified by a damage quantification equation deduced from differential equations of plate structure motion. WFEM scales vary spatially and change dynamically according to actual needs. Numerical examples clearly demonstrate that the proposed strategy can progressively locate and quantify plate damages. The strategy can operate efficiently in terms of the degrees-of-freedom in WFEM and sensors in the vibration test.

• Journal of Multimedia Information System
• /
• 제6권3호
• /
• pp.119-124
• /
• 2019

In this paper, a method of detecting vehicle plates through depth pictures is proposed. A vehicle plate can be recognized by detecting the plane areas. First, plane factors of each square block are calculated. After that, the same plane areas are grouped by comparing the neighboring blocks to whether they are similar planes. Width and height for the detected plane area are obtained. If the height and width are matched to an actual vehicle plate, the area is recognized as a vehicle plate. Simulations results show that the recognition rates for the proposed method are about 87.8%.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 추계학술발표대회
• /
• pp.333-334
• /
• 2009

In this paper, I propose the novel method based on Labeled Hough transform and GLCM(Grey-Level Co-occurrence Matrix) for license plate detection. A lot of conventional methods have been proposed to detect the license plate, but those are useless in order to detect the license plate well in case of dark or unstable images. Histogram equalization is preprocessed to each image before applying this method. As a result, the license plate is detected accurately