• Transactions on Electrical and Electronic Materials
• /
• 제17권6호
• /
• pp.363-368
• /
• 2016

Rectangular shape detection plays an important role in many image recognition systems. However, it requires continued research for its improved performance. In this study, we propose a strong rectangular shape detection algorithm, which combines the canny edge and line detection algorithms based on the perpendicularity and parallelism of a rectangle. First, we use the canny edge detection algorithm in order to obtain an image edge map. We then find the edge of the contour by using the connected component and find each edge contour from the edge map by using a DP (douglas-peucker) algorithm, and convert the contour into a polyline segment by using a DP algorithm. Each of the segments is compared with each other to calculate parallelism, whether or not the segment intersects the perpendicularity intersecting corner necessary to detect the rectangular shape. Using the perpendicularity and the parallelism, the four best line segments are selected and whether a determined the rectangular shape about the combination. According to the result of the experiment, the proposed rectangular shape detection algorithm strongly showed the size, location, direction, and color of the various objects. In addition, the proposed algorithm is applied to the license plate detecting and it wants to show the strength of the results.

• 한국정보통신학회논문지
• /
• 제9권1호
• /
• pp.160-164
• /
• 2005

자동차 번호판 자동인식에서 어두운 조명에서나 날씨가 좋지 않을 경ㅇ 차량의 형상이 왜곡 될 수 있고, 번호판을 식별하는데 어려움이 있다. 이에 본 논문에서는 움직이는 차량의 영상에서 흔들림이 없고, 밝은 햇빛에서 어두운 조명상태까지의 다양한 환경을 수용할 수 있는 자동차 번호판 인식방법을 제안하였다. 제안한 방법은 투시광선을 서로 다른 세기를 갖는 두 개의 빔(beam)으로 분리한 다음 CCD 카메라를 사용하여 두 개의 포착된 이미지를 조합하여 물체가 움직일 때도 동요 없는 이미지를 산출하였다. 실험결과로써 466 개의 움직이는 차량영상을 이용한 결과 98.7%의 인식률을 얻을 수 있었다.

• 제어로봇시스템학회논문지
• /
• 제3권5호
• /
• pp.511-519
• /
• 1997

This paper presents the automatic recognition algorithm of the license number in on vehicle image. The proposed algorithm uses the correlation coefficient and Hough transform to detect license plate. The m/n ratio reduction is performed to save time and memory. By the correlation coefficient between the standard pattern and the target pattern, licence plate area is roughly extracted. On the extracted local area, preprocessing and binarization is performed. The Hough transform is applied to find the extract outline of the plate. If the detection fails, a smaller or a larger standard pattern is used to compute the correlation coefficient. Through this process, the license plate of different size can be extracted. Two algorithms to each separate number are proposed. One segments each number with projection-histogram, and the other segments each number with the label. After each character is separated, it is recognized by the neural network. This research overlomes the problems in conventional methods, such as the time requirement or failure in extraction of outlines which are due to the processing of the entire image, and by processing in real time, the practical application is possible.

• Smart Structures and Systems
• /
• 제19권4호
• /
• pp.361-369
• /
• 2017

Electromechanical impedance method as an efficient tool in Structural Health Monitoring (SHM) utilizes the electromechanical impedance of piezoelectric materials which is directly related to the mechanical impedance of the host structure and will be affected by damages. In this paper, electromechanical impedance of piezoelectric patches attached to simply support rectangular plate is determined theoretically and experimentally in order to detect damage. A pairs of piezoelectric wafer active sensor (PWAS) patches are used on top and bottom of an aluminum plate to generate pure bending. The analytical model and experiments are carried out both for undamaged and damaged plates. To validate theoretical models, the electromechanical impedances of PWAS for undamaged and damaged plate using theoretical models are compared with those obtained experimentally. Both theoretical and experimental results demonstrate that by crack generation and intensifying this crack, natural frequency of structure decreases. Finally, in order to evaluate damage severity, damage metrics such as Root Mean Square Deviation (RMSD), Mean Absolute Percentage Deviation (MAPD), and Correlation Coefficient Deviation (CCD) are used based on experimental results. The results show that generation of crack and crack depth increasing can be detectable by CCD.

• Mass Spectrometry Letters
• /
• 제8권1호
• /
• pp.14-17
• /
• 2017

The effect of cationization agent concentration on glycan detection via matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) was investigated using $Na^+$ ions in the form of NaCl as the cationization agent. NaCl solution concentrations ranging from 1 mM to 1 M were investigated. Glycans from ovalbumin were mixed with the cationization agent solution and the 2,5-dihydroxybenzoic acid (2,5-DHB) matrix solution in a volume ratio of 1:1:1. The resulting mixture was loaded onto the MALDI plate. Two MALDI-TOF MS instruments (Voyager DE-STR MALDI-TOF MS and Tinkerbell RT MALDI-TOF MS) were used for detection of glycans. The best detection, in terms of the number of identified glycans, the peak intensity, and the signal-to-noise (S/N) ratio, was obtained with NaCl concentrations of 0.01-0.1 M for both MALDI-TOF MS instruments.

• 전기학회논문지
• /
• 제66권7호
• /
• pp.1092-1099
• /
• 2017

This paper proposes a novel way of vehicle detection and classification based on image features. There are two main processes in the proposed system, which are database construction and vehicle classification processes. In the database construction, there is a tight censorship for choosing appropriate images of the training set under the rigorous standard. These images are trained using Haar features for vehicle detection and histogram of oriented gradients extraction for vehicle classification based on the support vector machine. Additionally, in the vehicle detection and classification processes, the region of interest is reset using a number plate to reduce complexity. In the experimental results, the proposed system had the accuracy of 0.9776 and the $F_1$ score of 0.9327 for vehicle classification.

• 디지털산업정보학회논문지
• /
• 제17권4호
• /
• pp.85-94
• /
• 2021

The LPR system's trigger sensor makes problem occasionally due to the heave weight of vehicle or the obsolescence equipment. If we replace the hardware sensor to the deep-learning based software sensor in order to generate the trigger signal, LPR system maintenance would be a lot easier. In this paper we proposed the deep-learning sliding window based object detection and tracking algorithm for the LPR system's trigger signal generation. The gate passing vehicle's license plate recognition results are combined into the normal tracking algorithm to catch the position of the vehicle on the trigger line. The experimental results show that the deep learning sliding window based trigger signal generating performance was 100% for the gate passing vehicles including the 5.5% trigger signal position errors due to the minimum bounding box location errors in the vehicle detection process.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.792-794
• /
• 2014

문자인식은 문서 및 자동차 번호판 등의 문자정보를 얻는 영상처리 기술이며, 이를 위하여 에지를 검출하는 방법이 주로 사용되고 있다. 기존의 에지검출 방법은 대부분 영상에 가중치 마스크를 적용하는 방법이며, 영상의 전체 영역에 동일한 마스크를 적용하므로 처리결과가 다소 미흡하다. 따라서 본 논문은 문자인식에 적합하도록 화소의 분포 및 위치를 고려한 가중치 마스크를 적용하여 에지검출 알고리즘을 제안하였다.

• Smart Structures and Systems
• /
• 제8권3호
• /
• pp.253-274
• /
• 2011

In this paper, the harmonic displacement response of a damaged square plate with all-over part-through damage parallel to one edge is utilized as the input signal function in wavelet analysis. The method requires the properties of the damaged plate, i.e., no information about the original undamaged structure is required. The location of damage is identified by sudden changes in the spatial variation of transformed response. The incurred damage causes a change in the stiffness or mass of the plate. This causes a localized singularity which can be identified by a wavelet analysis of the displacement response. In this study via numerical examples shown by using harmonic response is more versatile and effective compared with the static deflection response, specially in the presence of noise. In the light of the obtained results, suggestions for future work are presented and discussed.

• 한국정밀공학회지
• /
• 제19권12호
• /
• pp.45-56
• /
• 2002

A pneumatic servo system requiring a fine gap control in a photo-electric sensor which is used for a LCD array detection device is introduced. The gap controlled by the pneumatic servo system remains within around 50~80 ${\mu}{\textrm}{m}$, and the system possesses an effect to eliminate undesirable particles on the LCD plate by blowing air out. The air flow rate is initially controlled by a servo valve and expanded by a booster valve, thus the controlled air pressure contributes to maintaining an appropriate gap between the LCD plate and photo-electric sensor An air floating plate of two degrees of freedom is designed and fabricated, and a fine tilting motion control is also implemented by assigning different gap commands. The pressure control and direct gap control are proposed, and each performance is verified experimentally.