• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.103-113
• /
• 2019

License plate recognition camera is dedicated device designed for acquiring images of the target vehicle for recognizing letters and numbers in a license plate. Mostly, it is used as a part of the system combined with server and image analysis module rather than as a single use. However, building a system for vehicle license plate recognition is costly because it is required to construct a facility with a server providing the management and analysis of the captured images and an image analysis module providing the extraction of numbers and characters and recognition of the vehicle's plate. In this study, we would like to develop an embedded type convergent camera (Edge Base) which can expand the function of the camera to not only the license plate recognition but also the security CCTV function together and to perform two functions within the camera. This embedded type convergence camera equipped with a high resolution 4K IP camera for clear image acquisition and fast data transmission extracted license plate area by applying YOLO, a deep learning software for multi object recognition based on open source neural network algorithm and detected number and characters of the plate and verified the detection accuracy and recognition accuracy and confirmed that this camera can perform CCTV security function and vehicle number plate recognition function successfully.

• Korean Journal of Otorhinolaryngology-Head and Neck Surgery
• /
• v.61 no.12
• /
• pp.692-696
• /
• 2018

Background and Objectives This study investigated the relationship between reflux symptom index (RSI) and psychiatric problems such as depression, somatization, and anxiety. Subjects and Method We prospectively analyzed 231 patients with symptoms with laryngopharyngeal reflux (LPR) using the RSI and the reflux finding score. Results Seventy nine patients (34.2%) were diagnosed with LPR. A significant correlation was detected between the RSI and depression ($18.4{\pm}8.3$ vs. $12.3{\pm}7.0$, p<0.001), anxiety ($19.5{\pm}8.5$ vs. $13.0{\pm}7.3$, p<0.001), and somatization ($19.2{\pm}9.1$ vs. $13.6{\pm}7.5$, p<0.001). A multivariate analysis confirmed a significant association between heartburn and depression [odds ratio (OR): 1.241, 95% confidence interval (CI): 1.003-1.537, p=0.047], choking and anxiety (OR: 1.747, 95% CI: 1.297-2.352, p<0.001), and choking and somatization (OR: 1.707, 95% CI: 1.248-2.336, p=0.001). Conclusion Our preliminary results suggest that patients with high RSI may need to be carefully evaluated for psychiatric problems.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.25 no.1
• /
• pp.27-30
• /
• 2014

Objectives : The purpose of this study was to investigate the endoscopic evidence of esophagitis in laryngopharyngeal reflux disease (LPRD) patients using transnasal esophagoscopy (TNE) and to correlate these findings with treatment response. Methods : Fifty patients underwent TNE at Korea University Anam Hospital from July 2007 to Feb 2009. Participants were selected from patients that presented with various laryngeal symptoms. One experienced otolaryngologist assessed esophagitis according to the Los Angeles classification system using the TNE findings. Results : Fifteen of 50 LPR patients (30%) were found to have esophagitis (12 patients with Grade A, 3 patients with Grade B, no patients with grade C/ D esophagitis). Among the 15 patients positive for esophagitis based on the endoscopic findings, 12 (80%) showed symptom improvement after pharmacological therapy. Symptom improvement was correlated with evidence of esophagitis (p=0.002) but not with RFS (p=0.749). Conclusion : Endoscopic evaluation of esophagitis using TNE is a potentially valuable tool for predicting treatment response in LPRD patients.

• Advances in concrete construction
• /
• v.2 no.3
• /
• pp.193-207
• /
• 2014

The study presented herein aims to investigate the durability related properties of rubberized concrete. Two types of waste scrap tire rubber were used as fine and coarse aggregate, respectively. The rubber was replaced with aggregate by three crumb rubber and tire chips levels of 5, 15, and 25% for the rubberized concrete productions. In order to improve the transport properties and corrosion resistance of rubberized concretes, SF was replaced with cement at 10% replacement level by weight of total binder content. The transport properties of the rubberized concretes were investigated through water absorption, gas permeability, and water permeability tests. The corrosion behavior of reinforcing bars embedded in plain and silica fume based rubberized concretes was investigated by linear polarization resistance (LPR) test. The results indicated that the utilization of SF in the rubberized concrete production enhanced the corrosion behavior and decreased corrosion current density values. Moreover, the reduction in the water and gas permeability coefficients was observed by the incorporation of SF in plain and especially rubberized concretes.

• Corrosion Science and Technology
• /
• v.3 no.3
• /
• pp.118-126
• /
• 2004

The correlation between sensor output and corrosion rate of reinforcing steel was evaluated by laboratory electrochemical tests in saturated $Ca(OH)_2$ with 3.5 wt.% NaCl and confirmed in concrete environment. In this paper, two types of electrochemical probes were developed: galvanic cells containing of steel/copper and steel/stainless steel couples. Potentiodynamic test, weight loss measurement, monitoring of open-circuit potential, linear polarization resistance (LPR) measurement and electrochemical impedance spectroscopy (EIS) were used to evaluate the corrosion behavior of steel bar embedded in concrete. Also, galvanic current measurements were conducted to obtain the charge of sensor embedded in concrete. In this study, steel/copper and steel/stainless steel sensors showed a good correlation in simulated concrete solution between sensor output and corrosion rate of steel bar. However, there was no linear relationship between steel/stainless steel sensor output and corrosion rate of steel bar in concrete environment due to the low galvanic current output. Thus, steel/copper sensor is a reliable corrosion monitoring sensor system which can detect corrosion rate of reinforcing steel in concrete structures.

• Journal of Electrochemical Science and Technology
• /
• v.11 no.3
• /
• pp.257-272
• /
• 2020

This study covers the stages of testing whether the azo dye with chemical name (E)-5-[(4-(benzyl(methyl)amino)phenyl)diazenyl]-1,4-dimethyl-1H-1,2,4-triazol-4-ium zinc (II) chloride (DMT), known as Maxilon Red GRL in the dye industry, can be used as an anticorrosive feasible inhibitory agent, especially in industrial areas other than carpet, yarn and fibre dyeing. These test stages consist of the electrochemical measurement techniques such as potentiodynamic polarization, electrochemical impedance spectroscopy (EIS) and linear polarization resistance (LPR) for diverse concentrations and durations. The adsorption of the viewed DMT molecule on the mild steel surface obeyed the Langmuir isotherm. The zero charge potential (PZC) of mild steel was also found to assess the inhibition mechanism in containing DMT solution. The inhibition performance of DMT on the mild steel in a 1.0 M HCl solution was also investigated using methods such as metal microscope, atomic force microscope (AFM) and field emission scanning electron microscope (FE-SEM).

• Nuclear Engineering and Technology
• /
• v.50 no.1
• /
• pp.107-115
• /
• 2018

To ensure the structural integrity of nuclear power plants, it is essential to predict the lifetime of Alloy 182 weld, which is used for welding in nuclear reactors. The lifetime of Alloy 182 weld is directly related to the crack initiation time. Owing to the large time scatter in most crack initiation tests, a probabilistic model, such as the Weibull distribution, has mainly been adopted for prediction. However, since statistically more advanced methods than current typical methods may be applied, we suggest a statistical procedure for parameter estimation of the crack initiation time of Alloy 182 weld, considering right-censored data and the covariate effect. Furthermore, we suggest a procedure for uncertainty evaluation of the estimators based on the bootstrap method. The suggested statistical procedure can be applied not only to Alloy 182 weld but also to any material degradation data set including right-censored data with covariate effect.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2016.11a
• /
• pp.116.1-116.1
• /
• 2016

반도체 가스센서에서는 가연성 및 탄화수소계 가스를 감지 하기 위해서 $100{\sim}500^{\circ}C$ 이상의 동작온도를 필요로 한며, 이에 따라 반도체식 가스센서의 마이크로 히터 소재는 고온에서 열적 안정성이 있는 소재가 요구된다. 현재 상용화되고 있는 반도체식 가스센서는 실리콘(Silicon) 기반의 MEMS 기술을 이용한 가스센서이며, 구조적으로나 성능적 한계가 드러남에 따라 실리콘 이외의 다양한 재료의 MEMS 응용기술 개발이 필요한 실정이다. 본 연구에서는 이러한 실리콘의 재료적 한계를 극복하기 위해 다공성 알루미늄 산화물(AAO)을 기판으로 사용하여 마이크로 히터를 제작하였다. AAO의 제작에 앞서 CMP, 화학연마, 전해연마를 이용하여 적합한 전처리 공정을 선정하였고, AAO 제작 시 온도, 시간, 전압의 변수를 주어 마이크로 히터 기판에 적합한 공정을 탐색하였다. 마이크로 플랫폼은 MEMS 공정으로 제작되었으며, PR(Photo Resist)을 LPR(Liquid Photo Resist)과 DFR(Dry Film Resist)로 각각 2종 씩 선택하여 AAO에 적합한 제품을 선정하였다. 제작된 마이크로 히터는 $1.8mm{\times}1,8mm$로 소형화 하였고, 열손실의 제어를 위해 열확산 방지층을 추가하였다. 구동 온도, 소비전력, 장시간 구동시 안정성의 측정 및 평가는 적외선 열화상 카메라와 kiethly 2420 source meter를 이용하여 측정하였으며, 열확산 방지층의 유 무에 따른 온도 분포 및 소비전력을 비교평가 하였다. 최종적으로는 현재 사용화 되어있는 가스센서들의 소비전력과 비교 평가 하여 논의 하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.830-833
• /
• 2016

자동차 번호판 인식은 대중적인 감시 기술 중의 한 종류로서, 주어진 비디오나 영상 내 광학문자 인식을 수반한다. 고속도로나 국도 상에 과속 단속 시스템, 재형 건물이나 유통센서 및 주차장 등에서 주차 정산 시스템, 고속도로 톨 게이트에서 hi-pass 에러 및 불법 도주 차량 잔속 시스템, 전국 주요 도로 불법 주 정차 단속 시스템, 공공기관, 기업 출퇴근 시간 확인 및 외부 차양 안내 시스템 등의 지능형 교통 시스템(ITS)이나 국도 상에 범위 차량 검거 시스템, 사건 발생 시 주요 도로상에 설치된 CCTV를 통해 용의 차량 이동 추적 시스템, 이동식 범죄 차량 조회, 버스에 탑재된 버스 전용차선 위반 단속들의 지능형 방범 시스템 등에 활용하고 있다. 번호판 인식은 자동차 번호판 국부화, 번호판의 크기, 차원, 명암대비, 밝기를 조정하는 정규화, 개별문자를 얻어내는 문자 분할, 문자를 인식하는 광학 문자 인식, 번호판의 형태, 크기, 위치 들이 연도별, 지역별로 차이가 있는 번호판들의 데이터베이스를 비교하여 구문 분석을 하는 절차를 거친다. 본 논문에서는 EmguCV를 이용하여 구현한 번호판 감지를 수행하여 위치를 찾아내고, 오픈 소스 광학 문자 인식 엔진으로 잘 알려져 있는 테서렉트 OCR을 이용하여 번호판의 문자를 인식하는 자동 인식 프로그램을 구현하고 기술하였다.