• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.5
• /
• pp.359-363
• /
• 2017

The LED (Liquid Emitting Diode) frame device is a big part of the representative display industry in Korea. LED is an essential part for TV, monitor, notebook, and mobile phone. In Japan, Taiwan, China and other countries, investment in LEDs has been strengthened, and productivity has become an important issue. However, as the size of the parts becomes smaller, the inconsistent inspection by the human eye becomes a problem of reliability, so that the automatic inspection process becomes an essential issue in the field of LED module inspection. In this paper, we investigate defects in visual inspection process using computer vision technology. The inspection of the LED frame is made quickly and accurately, thereby improving the efficiency of the process and shortening the inspection time. As a result of applying the inspection system to the field, we confirmed that it is possible to inspect quickly and accurately.

• Journal of Digital Contents Society
• /
• v.4 no.1
• /
• pp.11-21
• /
• 2003

In computer vision, the goal of stereopsis is to determine the surface structure of real world form two or more perspective views of scene. It is similar to human visual system. We can avoid obstacles, recognize objects, and manipulate machine using three-dimensional information. Until recently, only gray-level images have been used as input to computation for depth determination, but the availability of color can further enhance the performance of computational stereopsis. There are many models to provide efficient color system. The simplest model, RGB model treats color as if it were composed of separate entities. Each color channel is processed individually by the same stereopsis module as used in the gray-level model. His Model decouples intensity component from color information. So it can deal with color properties without defect intensity information. Opponent color model is based on human visual system. In this model, the red-green-blue colors are combined into three opponent channels before further processing.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.12
• /
• pp.71-83
• /
• 1996

This paper describes facial component detection and skew correction algorithm for face recognition. We use a priori knowledge and models about isolated regions to detect eye location from the face image captured in natural office environments. The relations between human face components are represented by several rules. We adopt an edge detection algorithm using sobel mask and 8-connected labelling algorith using array pointers. A labeled image has many isolated components. initially, the eye size rules are used. Eye size rules are not affected much by irregular input image conditions. Eye size rules size, and limited in the ratio between gorizontal and vertical sizes. By the eye size rule, 2 ~ 16 candidate eye components can be detected. Next, candidate eye parirs are verified by the information of location and shape, and one eye pair location is decided using face models about eye and eyebrow. Once we extract eye regions, we connect the center points of the two eyes and calculate the angle between them. Then we rotate the face to compensate for the angle so that the two eyes on a horizontal line. We tested 120 input images form 40 people, and achieved 91.7% success rate using eye size rules and face model. The main reasons of the 8.3% failure are due to components adjacent to eyes such as eyebrows. To detect facial components from the failed images, we are developing a mouth region processing module.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.2
• /
• pp.41-46
• /
• 2009

This research measures EEG signals which are generating on head skin and extracts brain concentration level related with brain activity. We develop concentration wireless transmission system for controlling hardware by using this signal. Two channels are used for measuring EEG signal on front head and Biopac system with MP100 and EEG100C was used for measuring EEG signal, amplifying and filtering the signal. LabView 8.5 was also used for FFT transformation, frequency and spectrum analysis of the measured EEG signals. As a result, SMR wave, Mid-Bata wave, $\Theta$ wave classified. We extracted the concentration index by adapting concentration extraction algorithm. This concentration uldex was transferred into logo automobile device by wireless module and applied for BCI application.

• Journal of Intelligence and Information Systems
• /
• v.14 no.4
• /
• pp.89-101
• /
• 2008

The most used tool for quality control is control chart in manufacturing industry. But it has limitations at current situation where most of manufacturing facilities are automated and several manufacturing processes have interdependent relationship such as CCM assembly line. To Solve problems, we propose quality management system based on data mining that are consisted of monitoring system where it monitors flows of processes at single window and feature extraction system where it predicts the yield of final product and identifies which processes have impact on the quality of final product. The quality management system uses decision tree, neural network, self-organizing map for data mining. We hope that the proposed system can help manufacturing process to produce stable quality of products and provides engineers useful information such as the predicted yield for current status, identification of causal processes for lots of abnormality.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.776-788
• /
• 2020

In this paper, a vehicle type recognition system using deep learning and a license plate recognition system are proposed. In the existing system, the number plate area extraction through image processing and the character recognition method using DNN were used. These systems have the problem of declining recognition rates as the environment changes. Therefore, the proposed system used the one-stage object detection method YOLO v3, focusing on real-time detection and decreasing accuracy due to environmental changes, enabling real-time vehicle type and license plate character recognition with one RGB camera. Training data consists of actual data for vehicle type recognition and license plate area detection, and synthetic data for license plate character recognition. The accuracy of each module was 96.39% for detection of car model, 99.94% for detection of license plates, and 79.06% for recognition of license plates. In addition, accuracy was measured using YOLO v3 tiny, a lightweight network of YOLO v3.

• Journal of Environmental Impact Assessment
• /
• v.14 no.3
• /
• pp.97-107
• /
• 2005

The purpose of this study is to develop a system, which estimates watershed pollutant loading rate through the combination of GIS and computational mode. Also, the applicability of this study was estimated by the application of the above system for Chuncheon City. The detailed results of these studies are as follows; The pollutant loading estimation system was developed for more convenient estimation of pollutant loading rate in watershed, and the system load was minimized by the separation of estimation module for point and non-point source. This system on the basis of GIS is very economical and efficient because it can be applied to other watershed with the watershed map. System modification is not needed. The pollutant loading estimation system for point source was developed to estimate the pollutant loading rate in watershed through the extraction of the proper data from all districts and yearly data and the execution of spatial analysis which is main function of GIS. From the verification result of spatial analysis, real watershed area and the administrative districtarea extracted by spatial analysis were $1,114,893,340.15m^2$ and $1,114,878,683.68m^2$, respectively. It shows that the spatial analysis results were very exact with only 0.001% error. The pollutant loading estimation system for non-point source was developed to calculate the pollutant loading rate through the overlaying of land-use and watershed map after the construction of new land-use map using the land register database with most exact land use classification. Application result for Chuncheon City shows that the proposed system results in one percent land use error while the statistical method results in five percent. More exact nonpoint source pollutant loading was estimated from this system.

• 한국태양에너지학회:학술대회논문집
• /
• 2011.11a
• /
• pp.278-281
• /
• 2011

This system can predict the maximum output about all illumination levels so that the PV system designer can design the system having the best efficiency. For the output prediction exact about the solar cell, that is the device the basis most in the PV system, the basis has to be in order to try this way. The solution based on Lambert W-function are presented to express the transcendental current-voltage characteristic containing parasitic power consuming parameters like series and shunt resistances. A simple and efficient method for the extraction of a single current-voltage (I-V) curve under the constant illumination level is proposed. With the help of the Lambert W function, the explicit analytic expression for I is obtained. And the explicit analytic expression for V is obtained. This analytic expression is directly used to fit the experimental data and extract the device parameters. The I-V curve of the solar cell was expressed through the modeling using Lambert W-function and the numerical formula where there is the difficulty could be logarithmically expressed This method expresses with the I-V curve through the modeling using Lambert W-function which adds other loss ingredients to the equation2 as to the research afterward. And the solar cell goes as small and this I-V curve can predict the power penalty in the system unit.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.6
• /
• pp.70-77
• /
• 2004

In many industrial applications, an unexpected fault of induction motor drive systems can cause serious troubles such as downtime of the overall system heavy loss, and etc. As one of methods to solve such problems, this paper investigates the fault diagnosis for open-switch damages in a voltage-fed PWM inverter for induction motor drive. For the feature extraction of a fault we transform the current signals to the d-q axis and calculate mean current vectors. And then, for diagnosis of different fault patterns, we propose a clustering based diagnosis algorithm The proposed diagnostic technique is a modified ANFIS(Adaptive Neuro-Fuzzy Inference System) which uses a clustering method on the premise of general ANFIS's. Therefore, it has a small calculation and good performance. Finally, we implement the method for the diagnosis module of the inverter with MATLAB and show its usefulness.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.247-258
• /
• 2003

Principal component analysis (PCA) based algorithms form the basis of numerous algorithms and studies in the face recognition literature. PCA is a statistical technique and its incorporation into a face recognition system requires numerous design decisions. We explicitly take the design decisions by in-troducing a generic modular PCA-algorithm since some of these decision ate not documented in the literature We experiment with different implementations of each module, and evaluate the different im-plementations using the September 1996 FERET evaluation protocol (the do facto standard method for evaluating face recognition algorithms). We experiment with (1) changing the illumination normalization procedure; (2) studying effects on algorithm performance of compressing images using JPEG and wavelet compression algorithms; (3) varying the number of eigenvectors in the representation; and (4) changing the similarity measure in classification process. We perform two experiments. In the first experiment, we report performance results on the standard September 1996 FERET large gallery image sets. The result shows that empirical analysis of preprocessing, feature extraction, and matching performance is extremely important in order to produce optimized performance. In the second experiment, we examine variations in algorithm performance based on 100 randomly generated image sets (galleries) of the same size. The result shows that a reasonable threshold for measuring significant difference in performance for the classifiers is 0.10.