• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.1-7
• /
• 2019

Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.

• Journal of Multimedia Information System
• /
• v.8 no.1
• /
• pp.23-30
• /
• 2021

Palmprint has become a popular biometric modality; however, palmprint recognition has not been conducted in video media. Video palmprint recognition (VPR) has some advantages that are absent in image palmprint recognition. In VPR, the registration and recognition can be automatically implemented without users' manual manipulation. A good-quality image can be selected from the video frames or generated from the fusion of multiple video frames. VPR in contactless mode overcomes several problems caused by contact mode; however, contactless mode, especially mobile mode, encounters with several revere challenges. Double-line-single-point (DLSP) assisted placement technique can overcome the challenges as well as effectively reduce the localization error and computation complexity. This paper modifies DLSP technique to reduce the invalid area in the frames. In addition, the valid frames, in which users place their hands correctly, are selected according to finger gap judgement, and then some key frames, which have good quality, are selected from the valid frames as the gallery samples that are matched with the query samples for authentication decision. The VPR algorithm is conducted on the system designed and developed on mobile device.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.33-45
• /
• 2023

This paper proposes an algorithm that automatically converts images into Pipo, painting images using OpenCV-based image processing technology. The existing "purity," "palm," "puzzling," and "painting," or Pipo, painting image production method relies on manual work, so customized production has the disadvantage of coming with a high price and a long production period. To resolve this problem, using the OpenCV library, we developed a technique that automatically converts an image into a Pipo painting image by designing a module that changes an image, like a picture; draws a line based on a sector boundary; and writes sector numbers inside the line. Through this, it is expected that the production cost of customized Pipo painting images will be lowered and that the production period will be shortened.

• The Journal of Churna Manual Medicine for Spine and Nerves
• /
• v.3 no.2
• /
• pp.37-42
• /
• 2008

Objectives : One of the most important cause of spondylolisthesis is it's epidemiological structure and L5's stability takes a significant role. The purpose of this study is to assess the difference of the Tuffier's line among of Spondylolythesis patients. Methods : We analyzed the Anterior view of lumbar spine checked at erect position on 60 patients who had been diagnosed as spondylolythesis. We investigated the Tuffier's Line on X-ray film. Results and Conclusions : Age distribution was 15 to 66 and the average was 47.81. Men were 19 cases(31.6%) and women were 41 cases(68.4%). Compared to men, women were more exposed to spondylolisthesis and for the age distribution, 50's showed the biggest portion. Group of normal people showed proportion of 14.3% at L4, 44% at L4/5 and 41.7% at L5 each. And group of patients showed proportion of 48.4% at L4, 35% at L4/5 and 51.6% at L5 each. Comparing these results, significance probability was 0.004(<0.05) which was significant. As the results of comparing the relation between L4/5 and L5/S1 patients, Normal group showed average of 3.33 which were close to L4/5. When there are spondylolisthesis at L4/5, averege was 3.33, placed at lower part of the vertebra body. When there are spondylolisthesis at L5/S1, averege was 3.566, placed between lower part of the veterbra body of L4 and L4/5. The p value of Normal group and L4/5 spondylolisthesis patient group was 0.022(p<0.05) which was significant. But the p value of Normal group and L5/S1 spondylolisthesis patient group was 0.0239 which was not significant. Also p value of L4/5 spcndylolisthesis patient group and L5/S1 spondylolisthesis patient group was 0.721 which was also not significant.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.870-876
• /
• 2017

In this paper, we proposed the automatic vision inspection system using multi-layer perceptron to detect the defects occurred on rail surface. The proposed system consists of image acquisition part and analysis part. Rail surface image is acquired as equal interval using line scan camera and lighting. Mean filter and dynamic threshold is used to reduce noise and segment defect area. Various features to characterize the defects are extracted. And they are used to train and distinguish defects by MLP-classifier. The system is installed on HEMU-430X and applied to analyze the rail surface images acquired from Honam-line at high speed up to 300 km/h. Recognition rate is calculated through comparison with manual inspection results.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2001.05a
• /
• pp.213-218
• /
• 2001

These days, corrosion condition of a underground objects is measured by the electric potential between the subject and ground. But this method is implemented by means of manual work with analog voltmeter, which is uneconomic and inefficient. So, We developed real-time On-Line cathodic protection monitoring system that is able to detect corrosion potential conditions of metal objects or various steel structures in the ground continuously, display them with the graphic screen, construct a database, and analyze them simultaneously. Since the data of corrosion and corrosion protection of all underground objects is processed automatically, not manually in this system, It is possible to reduce the manipulated error, and perform precise safety management, maintenance and inspection. As as result, this system can not only guarantee long-life operation, reduction of manpower and cost, but prevent large accidents in advance.

• Journal of Environmental Science International
• /
• v.10 no.1
• /
• pp.13-19
• /
• 2001

An on-line digestion system based on the flow injection analysis technique was presented for the determination of total phosphorus. The system converts condensed and organic phosphoruses into orthophosphate that can be analyzed spectrophotometically. The reaction between orthophosphate and ammonium molybdate in a strong acid medium forms the yellow complex of phosphomolybdate which is next reduced to a molybdic blue complex by stannous chloride. The quantitation of orthophosphate is based on the absorbance of the molybdic blue. To determine total phosphorus, the digestion system was installed between the sample injector and the reaction coil with the added lines of digestion solution(potassium persulfate+sulfuric acid) and the $H_2O$ carrier. The system has shown that the digestion efficiencies were greater than 95% for the typical condensed and organic phosphoruses. When tripolyphosphate standards were used, the calibration data showed that the linear dynamic range extended to a concentration of 1.5ppm with the detection limit of 25ppb total phosphorus. The typical relative standard deviation was less than 2%. The proposed system was successfully applied to lake water, wastewater, and streamwater. The analytical variables such as digestion efficiency, analysis time, and reproducibility were evaluated and compared with the manual digestion method.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.608-610
• /
• 2004

In continuous annealing line (CAL), POSCO, the center position control (CPC) is an essential technique that renders the steel-strip to pass at the center of a roll in order to prevent the strip from skewing or breaking. The CPC algorithm currently installed on the steering roll in the heating section of CAL is to control the strip position by using the reverse phase of error from the center position, without considering the dynamics of strip horizontal movement. Such algorithm may, unfortunately, require a manual operation occasionally when the range of strip input becomes wide, causing the dynamics 0 be dominant. Other PID-type control is rarely used in automatic operation because the excess of response may occur when the discontinuous points such as welding joints pass through rolls. In this paper, we identify the CPC system by using off-line data and design a compensator for the excessive dynamics by using the adaptive inverse control. Simulation result depicts the improved reliability of the proposed CPC system.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.22 no.1
• /
• pp.71-76
• /
• 2016

Background: The objective of this research is to provide base line data on Korea Baseball rehabilitation treatment by presenting the distribution of upper extremity surgeries according the surgical sites of Korean professional baseball players. Methods: The targets of this research are 561 players from nine Korean baseball clubs. The number of players that have undergone surgery was investigated. In other words, the frequency of shoulder joint surgeries, elbow joint surgeries, and wrist and hand surgeries per each baseball club was investigated. Results: The number of the players who have had surgeries was 151, but among the players, there were some who have had repeated surgeries for which the total number of surgery experience was 162. The result showed that elbow joint surgeries were the most frequently enacted, followed by shoulder joint surgeries, and wrist and hand surgeries. From the nine clubs, Samsung was the club with the highest frequency of surgeries. Conclusions: This research shows that Korean professional baseball players need special training centers with systematic rehabilitation programs. Another conclusion suggests that urgent need for rehabilitation program of upper arm which particularly focused on elbow joint is existing. On the basis of this research, we expect more studies on the specific rehabilitation programs which is categorized by injury areas.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.12 no.1
• /
• pp.43-52
• /
• 1994

This paper outlines a new approach to the line generalization when preparing small scale map on the basis of existing large scale digital map. Line generalizations are conducted based on Douglas algorithm using 1/25,000 scale topographic maps of southeastern JEJU island which produced by National Geographic Institute to analyze the fitness to the original and problems of graphical representation. Compare to the same scale map which was generated by manual method, a verity of small, but sometimes significant errors ＆ modification of topological relationship have been detected. The research gives full details of three algorithms that operationalize the smallest visible object method, together with some empirical results. A comparison of the results produced by the new algorithms with those produced by manual generalization and Douglas method of data reduction is provided. Also this paper presents the preliminary results of an relationships between the size of smallest visual object and requiring data storages for each algorithms.