• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.29-35
• /
• 2021

License plate recognition plays a key role in intelligent transportation systems. Therefore, it is a very important process to efficiently detect the number and character areas. In this paper, we propose a method to effectively detect license plate number area by applying deep learning and semantic image segmentation algorithm. The proposed method is an algorithm that detects number and text areas directly from the license plate without preprocessing such as pixel projection. The license plate image was acquired from a fixed camera installed on the road, and was used in various real situations taking into account both weather and lighting changes. The input images was normalized to reduce the color change, and the deep learning neural networks used in the experiment were Vgg16, Vgg19, ResNet18, and ResNet50. To examine the performance of the proposed method, we experimented with 500 license plate images. 300 sheets were used for learning and 200 sheets were used for testing. As a result of computer simulation, it was the best when using ResNet50, and 95.77% accuracy was obtained.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.416-421
• /
• 2022

In this study, we present a fully automated system that combines camera technology with liquid crystal technology to create a polarization camera capable of detecting the partial linear polarization of light reflected from an object. The use of twisted nematic (TN) liquid crystals that electro-optically modulate the polarization plane of light eliminates the need to mechanically rotate the polarizing filter in front of the camera lens. Images obtained using these techniques are imaged by computer software. In addition, liquid crystal panels have been produced in a square shape, but many camera lenses are usually round, and lighting or other driving units are installed around the lens, so space is optimized through the application of a circular liquid crystal display. Through the development of this technology, an electrically switchable and space-optimized liquid crystal polarizer is developed.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.87-93
• /
• 2023

In this paper, we propose a system that accurately and efficiently determines forward head posture based on network learning by analyzing the user's skeletal posture. Forward head posture syndrome is a condition in which the forward head posture is changed by keeping the neck in a bent forward position for a long time, causing pain in the back, shoulders, and lower back, and it is known that daily posture habits are more effective than surgery or drug treatment. Existing methods use convolutional neural networks using webcams, and these approaches are affected by the brightness, lighting, skin color, etc. of the image, so there is a problem that they are only performed for a specific person. To alleviate this problem, this paper extracts the skeleton from the image and learns the data corresponding to the side rather than the frontal view to find the forward head posture more efficiently and accurately than the previous method. The results show that the accuracy is improved in various experimental scenes compared to the previous method.

• 재활복지
• /
• v.16 no.3
• /
• pp.421-437
• /
• 2012

The goal of this study is to provide the basic information for improvement of domestic standards on the powered scooter and the electric wheelchair considering using environments in the nation. The international standards and domestic standards have been analyzed and compared, in order to propose improved domestic standards. Based on the research, the items and standards for general and functional recommendations, electric features, and other suggestions have been reexamined so that the improvements on test item and standards have been identified, corrected, and summarized including max. speed, brake system, lights and so on. We have been preparing the reference data for the improvement of standards on the powered scooter and the electric wheelchair through the comparison & analysis on the international and domestic standards.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.180-182
• /
• 2022

As various crimes such as theft, assault, and sex crimes are increasing, each local government is installing CCTVs to prevent them, and operating and managing control centers for emergency response. When the control center detects a dangerous situation in the field, it responds immediately in connection with the police or 911. However, since it is managed by humans, the response speed is anomalous and the reality is that it is mainly used for post-processing. Therefore, through the artificial intelligence LED signage, it notifies the emergency situation at the site, and it serves as a warning function before getting help from passers-by or an accident occurs. In this paper, we design and research a warning system such as changing the lighting color of the LED signboard or making a sound by reflecting the artificial intelligence algorithm. We intend to contribute to public safety and social safety through this study.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.10
• /
• pp.865-878
• /
• 2017

To realize the healthy life of human, mental, physical, and environmental factors must be managed continuously and stably. In order to manage human health, the 21st century healthcare field is essential ongoing interactions and convergence with ICT technologies. Such demands have created a convergence of technologies (fusion technology) in combination with the heterogeneous technologies. And, with the convergence of medical technology and ICT technologies, the development of personalized therapy environments is created. Advances in ICT-converged healthcare services are progressing due to the development of diverse wearable devices. Such ICT fusion system is exponentially increasing the complexity of the ICT convergence healthcare system and is resulting in various technical, institutional, environmental, and cultural issues. This study explores the status of developments in ICT healthcare technologies from the past to date, identifies major technology and policy issues to address these challenges. Finally it will recommend healthcare policies and a future road-map.

• Journal of the Korean Society of Radiology
• /
• v.17 no.7
• /
• pp.1179-1187
• /
• 2023

Recent advancements in modern transportation have led to the active development of various biomedical signal and medical imaging technologies. Particularly, in the field of cognitive/neuroscience, the importance of electroencephalography (EEG) measurement and the development of accurate EEG measurement technology in moving vehicles represent a challenging area. This study aims to extensively investigate and analyze the trends in technology research utilizing EEG during driving. For this purpose, the Scopus database was used to explore EEG-related research conducted since the year 2000, resulting in the selection of about 40 papers. This paper sheds light on the current trends and future directions in signal processing technology, EEG measurement device development, and in-vehicle driver state monitoring technology. Additionally, a ultra compact 32-channel EEG measurement module was designed. By implementing it simply and measuring and analyzing EEG signals, in-vehicle EEG module's functionality was checked. This research anticipates that the technology for measuring and analyzing biometric signals during driving will contribute to driver care and health monitoring in the era of autonomous vehicles.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.1
• /
• pp.118-129
• /
• 2011

This Study has developed the information system of the rivers based on 3D image GIS by converging the latest information technology of GIS(Geographic Information System), RS(Remote Sensing), GNSS(Global Navigation Satellite System), aerial laser survey(LiDAR) with real time network technology in order to understand the current situation of all the four major rivers and support the administrative management system. The said information system acquires the high resolution aerial photographs of 25cm, aerial laser survey and water depth surveying data to express precise space information on the whole Youngsan River which is the leading project site out of the four river sites. Monitoring the site is made available on the transporting means such as a helicopter, boat or a bus in connection with locational coordinate tracking skill for the moving objects in real time using GNSS. It makes monitoring all the information on the four river job sites available at a glance, which can obtain the reliability of the people to such vast areas along with enhancing the recognition of the people by publicity of four Rivers Revitalizing Project and reports thereof.

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.333-338
• /
• 2012

Human resource management is bringing the various changes with the IT technology. In particular, if HRM is non-scientific method such as group management, physical plant, working hours constraints, personal contacts, etc, the current enterprise human resources management(e-HRM) appeared in the individual dimension management, virtual workspace (for example: smart work center, home work, etc.), working time flexibility and elasticity, computer-based statistical data and the scientific method of analysis and management has been a big difference in the sense. Therefore, depending on changes in the environment, companies have introduced a variety of techniques as RFID card, fingerprint time & attendance systems in order to build more efficient and strategic human resource management system. In this paper, time and attendance, access control management system was developed using multi camera for 2D and 3D face recognition technology-based for efficient enterprise human resource management. We had an issue with existing 2D-style face-recognition technology for lighting and the attitude, and got more than 90% recognition rate against the poor readability. In addition, 3D face recognition has computational complexities, so we could improve hybrid video recognition and the speed using 3D and 2D in parallel.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.4
• /
• pp.106-116
• /
• 2016

MTO (Make to Order) is a manufacturing process in which manufacturing starts only after a customer's order is received. Manufacturing after receiving customer's orders means to start a pull-type supply chain operation because manufacturing is performed when demand is confirmed, i.e. being pulled by demand (The opposite business model is to manufacture products for stock MTS (Make to Stock), which is push-type production). There are also BTO (Build to Order) and ATO (Assemble To Order) in which assembly starts according to demand. Lean manufacturing by MTO is very efficient system. Nevertheless, the process industry, generally, which has a high fixed cost burden due to large-scale investment is suitable for mass production of small pieces or 'mass customization' defined recently. The process industry produces large quantities at one time because of the lack of manufacturing flexibility due to long time for model change or job change, and high loss during line-down (shutdown). As a result, it has a lot of inventory and costs are increased. In order to reduce the cost due to the characteristics of the process industry, which has a high fixed cost per hour, it operates a stock production system in which it is made and sold regardless of the order of the customer. Therefore, in a business environment where the external environment changes greatly, the inventory is not sold and it becomes obsolete. As a result, the company's costs increase, profits fall, and it make more difficult to survive in the competition. Based on the customer's order, we have built a new method for order system to meet the characteristics of the process industry by producing it as a high-profitable model. The design elements are designed by deriving the functions to satisfy the Y by collecting the internal and external VOC (voice of customer), and the design elements are verified through the conversion function. And the Y is satisfied through the pilot test verified and supplemented. By operating this make to order system, we have reduced bad inventories, lowered costs, and improved lead time in terms of delivery competitiveness. Make to order system in the process industry is effective for the display glass industry, for example, B and C groups which are non-flagship models, have confirmed that the line is down when there is no order, and A group which is flagship model, have confirmed stock production when there is no order.