• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.116-123
• /
• 2007

Despite the number of backlight manufacturer is increased as the market of flat panel display equipments and related development devices is enlarged, the inspection based on the human eye is still used in many backlight production lines. The defects such as particle, spot and scratch on the light emitting surface of the backlight prevent the LCD device from displaying the colors correctly. From that manual inspection it is difficult to maintain the quality of backlight consistently because the accuracy and the speed of the inspection may change with the physical condition of the operater. In this paper we studied on the development of automatic backlight surface defect inspection system. For this, we made up of the computer vision system and we developed the main program with various user interfaces to operate the inspection system effectively. And we developed the image processing module to extract the defect information. Furthermore, we presented the labeling process to reconstruct defect regions using the labeling table and the defect index. From the experimental results, we found that our system can detect all defect regions identified from human eye and it is sufficient to substitute for the conventional surface inspection.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.31 no.3
• /
• pp.247-255
• /
• 1995

This paper describes a personal computer(PC) based color fish finder to improve some problem of the commercial one. The commercial fish finder has no function of the echo data logging and replaying. The authors developed two types of the PC based color fish finder. One is a master type composed of a PC, a digital input-output board, and analog to digital converting (A/D) board and an ultrasonic transceiver unit, the other is a slave type composed of a PC and an A/D board. To test the performances of the master type experiments were carried out in air and in a water tank. It is found that the designed master type fish finder displays very well an eight-colored echogram by one dot resolution to the left side of the PC monitor. Also, the depth of echo signal was corresponds very well to the range from the transducer to a target. The sampling interval of echo signal is about 0.1m and the time of A/D conversion is 30 $\mu$sec. On the other hand, to test the performances of the slave type a raw data of echo signals from a data logger was supplied directly or via RF transceivers to the slave type one. From this experiment, it is confirmed the slave type is useful to replay the echo signal from the data logger or a telesounder.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1575-1583
• /
• 2008

Wireless sensor network has merit of low-power, low-cost and self-organization network, so there are many researches substituted for existing wire network. As structure reinforcement work need a high accuracy, many sensors are installed in structure and connected with data logger for monitoring. However this wire data logger method takes a long time to install wires and installed wires obstruct to work. Additionally, wire data logger method represent sensor data by only numeric and graph, it is not able to support a rapid decision-making for working. To resolve wiring problem and support decision-making, we designed and implemented the monitoring system based in wireless sensor network. For verifying performance, accuracy and availability, we simulated and tested our system in real field. Consequently, wireless sensor network method is easier to install and deploy than wire data logger method, user is able to monitor instinctively and overall by 3D representation of structure and sensors, and it show not only accuracy but also performance for many sensors.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.55-65
• /
• 2022

Recently, deep learning-based automated systems for identifying and detecting landmarks have been proposed. In order to train such a deep learning-based model without overfitting, a large amount of image and labeling data is required. Conventionally, an experienced reader manually identifies and labels landmarks in a patient's image. However, such measurement is not only expensive, but also has poor reproducibility, so the need for an automated labeling method has been raised. In addition, in the X-ray image, since various human tissues on the path through which the photons pass are displayed, it is difficult to identify the landmark compared to a general natural image or a 3D image modality image. In this study, we propose a geometric data augmentation technique that enables the generation of a large amount of labeling data in X-ray images. In addition, the optimal attention mechanism for landmark detection was presented through the implementation and application of various attention techniques to improve the detection performance of 16 major landmarks in the skull. Finally, among the major cranial landmarks, markers that ensure stable detection are derived, and these markers are expected to have high clinical application potential.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.3
• /
• pp.667-675
• /
• 2018

Increasing emissions regulations and demand of high-efficiency cars that travels a lot of distance with less fuel, there is growing interest in Energy Consumption Efficiency. Korean energy consumption efficiency compute combined Fuel Economy by driven city & highway driving mode and present final Energy Consumption Efficiency as using 5-cycle correction formula. Energy consumption efficiency is computed Carbon-balance-method, when used burning fuel play a key role in vehicle performance & Energy Consumption Efficiency. In Korea, vehicle fuel is circulate by Petroleum and Petroleum Alternative Business Act, there is property difference in quality standard because petroleum sector's refine method or type of crude oil. It does not appear a big difference according to fuel, because it sets steady quality standard, it may affect the performance of automobile. Thus, in research We purchase a few diesel fuel which circulated in the market in summer season though directly-managed-gas station by petroleum sector, resolve property each of fuel, we compute Fuel Economy each of them. We analyze into change depend on applying for property as nowadays utilizing Energy Consumption Efficiency calculating formula of gasoline and diesel fuel. As result, Density each of sample fuel has a maximum difference roughly 0.9%, net heat value each of sample fuel has difference 1.6%, result of current Energy Consumption Efficiency each of sample fuel has a difference roughly 1% at city drive mode, 1.4% at highway drive mode. Result of use gasoline calculator formula shows less 6% result than nowadays utilizing Energy Consumption Efficiency calculating formula, each of sample's Energy Consumption Efficiency shows maximum roughly 1.4% result in city & highway drive mode.

• Korean Journal of Agricultural Science
• /
• v.13 no.2
• /
• pp.265-278
• /
• 1986

This study was attempted to improve the thermal efficiency of 6 kW water-cooled diesel engine on power tiller. The engine performance tests were conducted to find out the effect of cooling water capacity of 2700cc, 2800cc, 2900cc, 3000cc, 3100cc on power, brake specific fuel consumption (BSFC), torque, temperature of cooling water and lubricating oil and friction losses of the engine with D. C. dynamometer. The results obtained in the study are summarized as follows: 1. The performance of the engine tested was adequated to Korea Industrial Standard but actual economy power was 10% higher than the labeled rated power of the engine. The BSFC of the engine tested 297.8g/kW-h which is belong a little higher level than hreign products. The temperature of cooling water was $101^{\circ}C$ which is higher than SAE standard ($88^{\circ}C$) 2. The friction losses of engine tested was 3.656 kW at 2200 rpm of rated rpm (piston speed 6.97m/sec) and is higher than those of foreign products. 3. When the cooling water capacity was increased from 2700cc to 3100cc the power output of the engine was increased from 6.7 kW to 7.13 kW at the rate of 6.4% and also the torque of the engine was increased from 28.85 N.m to 30.76 N.m at the rate of 6.39%. 4. When the cooling water capacity was increased from 2700cc to 3100cc, the BSFC was decreased 6.9g/kW-h from 310.9g/kW-h to 304.1g/kW-h, and after one half hour operation with full load, the temperature of cooling water was decreased $13^{\circ}C$ from $101^{\circ}C$ to $88^{\circ}C$ and also the temperature of lubricant oil was decreased $6.4^{\circ}C$ from $76.7^{\circ}C$ to $70.4^{\circ}C$. 5. The mechanical efficiency was increased from 70.08% to 71.08% when the cooling water capacity was increased from 2700cc to 3100cc.

• Journal of radiological science and technology
• /
• v.36 no.1
• /
• pp.1-10
• /
• 2013

IEC publications have applied in many countries all over the world such as Europe or Japan and these also have been published as in dustrial standards (KS) and notifications of Korea Food and Drug Administration (KFDA) in Korea. As the general standard of IEC 60601 series for medical electric (ME) equipment was revised as $3^{rd}$ edition in 2005, additional and particular standards have been revised or established newly. Under these circumstances, it is importance for manufacturing and assembling companies or authorized testing companies to understand the trend for revisions of IEC publications. Therefore in this study, the latest version of 3 IEC standards related to medical X-ray equipment : IEC 60601-2-44 for X-ray equipment for computed tomography (CT), IEC 60601-2-45 for mammographic X-ray equipment and IEC 60601-2-54 for X-ray equipment for radiography or radioscopy were covered and analyzed for trends and features accompanied by revision based on IEC 60601-1 $3^{rd}$ Ed. As KFDA notifications in force have referred to the particular standards based on 2nd edition of IEC 60601-1, those revised version of 3 particular standards were compared to KFDA notifications in force. The features of the latest standards applying IEC 60601-1 $3^{rd}$ Ed were shown as following: 1) Requirements for mechanical hazards, especially (motorized) moving parts were emphasized. 2) Indication and recording of patient dose were required. 3) Risk management process was introduced and enabled to monitor potential risks systematically. 4) DR system (digital radiography system) as well as analogue system (film-screen system) was included in the scope. Presently, KFDA will revise the notifications applying the particular standards based on IEC 60601-1 $3^{rd}$ Ed in a few years. Therefore the features of particular standards applying IEC 60601-1 $3^{rd}$ Ed was expected to help manufacturers, assemblers or testing companies of medical electric equipment understand IEC publications or KFDA notifications slated to be published.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.1
• /
• pp.191-197
• /
• 2013

Conventional CT and MRI scans produce cross-section slices of body that are viewed sequentially by radiologists who must imagine or extrapolate from these views what the 3 dimensional anatomy should be. By using sophisticated algorithm and high performance computing, these cross-sections may be rendered as direct 3D representations of human anatomy. The 2D medical image analysis forced to use time-consuming, subjective, error-prone manual techniques, such as slice tracing and region painting, for extracting regions of interest. To overcome the drawbacks of 2D medical image analysis, combining with medical image processing, 3D visualization is essential for extracting anatomical structures and making measurements. We used the gray-level thresholding, region growing, contour following, deformable model to segment human organ and used the feature vectors from texture analysis to detect harmful cancer. We used the perspective projection and marching cube algorithm to render the surface from volumetric MR and CT image data. The 3D visualization of human anatomy and segmented human organ provides valuable benefits for radiation treatment planning, surgical planning, surgery simulation, image guided surgery and interventional imaging applications.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.333-340
• /
• 2011

The Human-Computer Interaction(HCI) is a study of the method for interaction between human and computers that merges the ergonomics and the information technology. The intelligent space, which is a part of the HCI, is an important area to provide effective user interface for the disabled, who are alienated from the information-oriented society. In the intelligent space for the disabled, the method supporting information depends on types of disability. In this paper, we only support the hearing-impaired. It is material to the gaze direction detection method because it is very efficient information provide method to present information on gazing direction point, except for the information provide location perception method through directly contact with the hearing-impaired. We proposed the gaze direction detection method must be necessary in order to provide the residence life application to the hearing-impaired like this. The proposed method detects the region of the user from multi-view camera images, generates candidates for directions of gaze for horizontal and vertical from each camera, and calculates the gaze direction of the user through the comparison with the size of each candidate. In experimental results, the proposed method showed high detection rate with gaze direction and foot sensing rate with user's position, and showed the performance possibility of the scenario for the disabled.