• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1172-1179
• /
• 2015

A wireless license plate region extracting module is proposed for LPR system controlling multiple gates. This module is cheaply implemented using Raspberry Pi which is open source and high performance. First, as the upper 1/3 of the captured image is discarded as it has no useful information on license plate. Using the OpenCV libraries the edge image is got by Canny algorithm after applying Gaussian filtering to gray image, and the labeling is conducted for 4 consecutive numbers in license plate. These numbers are located using various decision equations, and expanding the numbers region the final license plate region can be extracted. The result image is transferred to Server using wifi direct. Using the proposed module it becomes easy to set up and maintain the LPR system. The experimental results showed that the successful extracting rate was 98.4% using 500 car images with 640 × 480 resolution.

• Knowledge Management Research
• /
• v.15 no.2
• /
• pp.147-164
• /
• 2014

This paper investigated the efficiency of automobile firms by using several non-parametric approaches. First, using Data Envelopment Analysis (DEA), the paper has investigated the critical factors that determine the relative efficiency of management performance in automobile companies. Second, we examined how the firm size impact on the difference of this efficiency by using Kruskl-Wallis Test. Third, by using Mann-whitney test, we also investigated the difference of the efficiency accoss existence of technological innovation activity. Finally, the paper explored the relationship between technological innovation and management efficiency by using logistic regression model. The findings of this study provided practical information for inefficient automobile firms to find benchmarking firms and strategic position to improve their efficiency. The result also provided theoretical and methodological implications for those who explore factors affecting management efficiencies. Future research directions with the limitation of the study are discussed.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.225-232
• /
• 2017

Understanding actions in videos is an important task. It helps in finding the anomalies present in videos such as fights. Detection of fights becomes more crucial when it comes to sports. This paper focuses on finding fight scenes in Hockey sport videos using blur & radon transform and convolutional neural networks (CNNs). First, the local motion within the video frames has been extracted using blur information. Next, fast fourier and radon transform have been applied on the local motion. The video frames with fight scene have been identified using transfer learning with the help of pre-trained deep learning model VGG-Net. Finally, a comparison of the methodology has been performed using feed forward neural networks. Accuracies of 56.00% and 75.00% have been achieved using feed forward neural network and VGG16-Net, respectively.

• Journal of information and communication convergence engineering
• /
• v.18 no.2
• /
• pp.132-146
• /
• 2020

Biometric technologies have become widely available in many different fields. However, biometric technologies using existing physical features such as fingerprints, facial features, irises, and veins must consider forgery and alterations targeting them through fraudulent physical characteristics such as fake fingerprints. Thus, a trend toward next-generation biometric technologies using behavioral biometrics of a living person, such as bio-signals and walking characteristics, has emerged. Accordingly, in this study, we developed a bio-signal authentication algorithm using electrocardiogram (ECG) signals, which are the most uniquely identifiable form of bio-signal available. When using ECG signals with our system, the personal identification and authentication accuracy are approximately 90% during a state of rest. When using fingerprints alone, the equal error rate (EER) is 0.243%; however, when fusing the scores of both the ECG signal and fingerprints, the EER decreases to 0.113% on average. In addition, as a function of detecting a presentation attack on a mobile phone, a method for rejecting a transaction when a fake fingerprint is applied was successfully implemented.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2006.11a
• /
• pp.39-40
• /
• 2006

AE sensor using lead-free ceramics should be developed for prohibiting environment protection. In this study, Langevin type AE sensor was manufactured as air backing structure. Here, the piezoelectic element was used as PZT(EC-65) and NKN, respectively. The resonant frequency of AE sensor using PZT was 143 kHz and the resonant frequency of AE sensor using NKN was 178 kHz. The waveform of AE sensor using NKN was responded more sensitively than that of AE sensor using PZT.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.69-74
• /
• 2004

In this paper, we propose a novel method for improving defect-detection performance based on reconstruction of line-scan camera images using both the projection profiles and color space transform. The proposed method consists of RGB region segmentation, representative value reconstruction using the tracing system, and Y image reconstruction using color-space transformation. Through experiments it is demonstrated that the performance using the reconstructed image is better than that using aerial image for LCD surface inspection.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2001.04a
• /
• pp.278-286
• /
• 2001

The purpose of this paper is to suggest an analytical technique for time history analysis of R/C frame structure using high-strength concrete under seismic loading. Current researches in hysteretic model of structral elements using high-strength concrete are not enough. It is the cause of error that apply hysteretic model of element using normal-strength concrete to the inelastic analysis of high-strength concrete R/C frame structures. In this paper time history analysis using IDARC and DRAIN programs was performed for a 2-bay, 20-story R/C frame structures. Particularly nonlinear dynamic analysis was performed by IDARC program that was applied hysteretic model of structural element using high-strength concrete. centro earthquake 1940 NS waves was used in the analysis and its peak ground accelerations are changed to be 0.12g, 0.25g

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.185-191
• /
• 2008

This study tried the 1st, 2nd dimensional numerical analysis according to the pier's shape, size and installing method in order to compare the depth of scour calculation method using the variables calculated by using the 2nd dimensional numerical analysis with the calculated depth of scour value by using the calculated variables by using the 1st dimensional numerical analysis. And then verified the problems occurring when the depth of scour is calculated by using the calculated values by using the 1st dimensional numerical analysis, as calculating the deviation depending on it.

• Journal of ILASS-Korea
• /
• v.21 no.2
• /
• pp.104-110
• /
• 2016

Main purpose of the current paper is to show results of time lag analysis using phase information of flame transfer function in order to predict combustion instabilities in a gas turbine combustor. The flame transfer function (FTF) is modeled using a commercial Computational Fluid Dynamics (CFD) code (Fluent). Comparisons of the modeled flame shapes with the measured ones were made using the optimized heat transfer conditions and combustion models. The FTF modeling results show a quite good agreement with the measurement data in predicting the phase delay (i.e. time lag). Time lag analysis results using the phase of FTF shows better combustion instability prediction accuracy than using time lag calculated from the steady state flame length.

• Korean Journal of Materials Research
• /
• v.16 no.5
• /
• pp.308-311
• /
• 2006

The purpose of this study is to investigate the difference of the wafer nanotopography impact on the oxide-film thickness variation between the STI CMP using ceria slurry and STI CMP using fumed silica slurry. The nanotopography impact on the oxide-film thickness variation after STI CMP using ceria slurry is 2.8 times higher than that after STI CMP using fumed silica slurry. It is attributed that the STI CMP using ceria slurry follows non-Prestonian polishing behavior while that using fumed silica slurry follows Prestonian polishing behavior.