• Nuclear Engineering and Technology
• /
• v.36 no.3
• /
• pp.219-228
• /
• 2004

[1] and [2] present an approach to diagnosing possible defects in the mechanical systems of a nuclear power plant. In this paper, by using a fault library as a database and training data, we develop a diagnostic algorithm 1) to decide whether an Air Operated Valve system is sound or not and 2) to identify the defect from which an Air-Operated Valve system suffers, if any. This algorithm is composed of three stages: a neural net stage, a non-neural net stage, and an integration stage. The neural net stage is a simple perceptron, a pattern-recognition module, using a neural net. The non-neural net stage is a simple pattern-matching algorithm, which translates the degree of matching into a corresponding number. The integration stage collects each output and makes a decision. We present a simulation result and confirm that the developed algorithm works accurately, if the input matches one in the database.

• Journal of Information Processing Systems
• /
• v.16 no.3
• /
• pp.629-638
• /
• 2020

In this paper, an unmanned automation system for harvesting chili peppers through image recognition in the color space is proposed. We developed a cutting-edge technology in terms of convergence between information and communication technology (ICT) and agriculture. Agriculture requires a lot of manpower and entails hard work by the laborers. In this study, we developed an autonomous application that can obtain the head coordinates of a chili pepper using image recognition based on the OpenCV library. As an alternative solution to labor shortages in rural areas, a robot-based chili pepper harvester is proposed as a convergence technology between ICT and agriculture requiring hard labor. Although agriculture is currently a very important industry for human workers, in the future, we expect robots to have the capability of harvesting chili peppers autonomously.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.119-126
• /
• 2019

As interest in augmented reality has increased recently, attempts have been made to incorporate augmented reality into various fields. In implementing augmented reality, the method by which markers are used is to extract feature points of markers to recognize 3D coordinates and, in some cases, it is necessary to recognize multiple markers simultaneously. Therefore, this paper proposes optimization methods for recognising multiple markers at the same time. Unity 3D and augmented reality library Vuforia are used to implement the experimental environment. The augmented reality program produced was implemented in an application form and tested using a mobile camera. We looked for optimization methods for manufacturing markers directly and for recognizing multiple markers through changes in the experimental environment. The results of the experiment can provide a higher recognition rate in an environment where multiple marker recognition is required later.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.327-329
• /
• 2019

In this paper, we propose an automatic attendance management system for classrooms using OpenCV and machine learning technology. When a face photograph is input at the entrance of the classroom using a general purpose camera for PC, the attendance is checked by comparing the similarity of the face of the already stored student. In this study, the prototype was implemented using the machine learning library dlib, and about 10% of the students had a recognition rate of about 70%.

• Journal of the Korean Society for Library and Information Science
• /
• v.52 no.3
• /
• pp.171-192
• /
• 2018

With the spread of the maker movement and matching of the standards for the 21st century learners and the maker competencies, there is a social and temporal need for makerspaces building and maker education in school libraries, Prior to the establishment of the school library makerspaces, we intended to investigate the awareness of the school librarian on the creation and operation of the school library makerspaces. For this purpose, a questionnaire was constructed based on the theoretical review and the response data of 171 school librarians were collected through a web survey. Technical statistics, cross-analysis, and ANOVA were conducted using SPSS window 19.0 and content analysis was conducted on open-ended questions. The Questionnaires consisted of questions about whether the school library makerspace was installed or not and necessity, reason, and difficulty in creating and operating the makerspace. As a result of the study, it was found that the establishment of the school library makerspace was very low at 2.3%, and the recognition of the makerspace of the school librarian was below the normal level. On the other hand, the perception of necessity appeared to be more than normal, and the school library was generally considered to be a suitable place for the makerspace installation. However, negative opinions about the school library makerspaces were also raised in various aspects.

• Journal of Korean Library and Information Science Society
• /
• v.40 no.2
• /
• pp.473-490
• /
• 2009

The purpose of this study was to analyze the recognition of those majoring Library & Information Science on the jobs that they can get and want to work for, employment requirements and their preparation, to identify problems and to suggest how to improve current status. To this end, the jobs and employment rate reported by most of the Depts. of Library & Information Science and the preferred jobs and preparation to those majoring library and information were surveyed with 107 students studying in the Dept. of Library & Information Science in the K University as the subjects. According to the results, 49 jobs were identified as the jobs that those majoring Library & Information Science could get into. In the 1st to 20th job ranking groups, 82.1% of all identified jobs, librarian job took lower ranking as 29.2% while other jobs accounted for 52.9%. However, among the jobs from the 1st to 20th ranking accounting for 96% of all jobs that the subjects wanted to have, the librarian job took 45.8% and other jobs 50.6%, which suggested that the preference on librarian job was slightly increased among the jobs that the subjects wanted to have. Furthermore, the employment requirements were classified into religion, language, scholastic achievement, certification and experience. In accordance with investigation on requirements from employment announcement, 92% were in the generally acceptable level or insufficient level. On the basis of such results, it is suggested to introduce a variety of jobs to students and to provide Case-by-Case employment guidance for improvement of employment rate and social capability of students.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.61-64
• /
• 2013

본 논문에서는 모바일 기반 OpenCV 라이브러리를 이용한 마커리스 객체 인석 성능 향상을 위한 소프트웨어적인 관점의 방법을 제안한다. 기존의 마커리스 기반 알고리즘을 이용하여 테스트를 수행한 후 성능에 저하를 발생시키는 요인들을 분석하고 그에 따른 상황별 적절한 해결책을 제시한다. 이에 따라 크게 프로그램 코드 개선, 마커리스 기반 알고리즘 코드 개선, 센서를 활용한 성능 향상을 도모한다. 프로그램 코드 개선은 테스트 결과를 분석 한 후 수행시간이 가장 많이 소요되는 함수를 최적화하고 또한 최적의 특징점의 수를 제한한다. 마커리스 기반 알고리즘 코드 개선은 병렬 처리가 제공되는 모바일에 한하여 병렬처리기법으로 코드를 수정한다. 마지막 센서를 활용한 성능향상은 실시간 작업 처리 단위를 묶음으로 처리하였을 때 발생하는 품질의 저하를 보정하는 역할을 수행한다. 본 논문에서는 이러한 마커리스 객체 인식 성능 향상 방법을 소프트웨어적인 관점에서 제안하고 이에 대한 결과 모바일 기반 실시간 증강현실 서비스를 위한 성능 향상 면에서 효과적이다.

• Journal of IKEEE
• /
• v.17 no.3
• /
• pp.371-377
• /
• 2013

This thesis propose an efficient parallel structure method for implementing a FAST and BRIEF algorithm based Augmented Reality. SURF algorithm that is well known in the object recognition algorithms is robust in object recognition. However, there is a disadvantage for real time operation because, SURF implementation requires a lot of computation. Therefore, we used a FAST and BRIEF algorithm for object recognition, and we improved Conventional Parallel Structure based on OpenMP Library. As a result, it achieves a 70%~100% improvement in execution time on the embedded system.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1479-1486
• /
• 2016

According to the advancement of display devices, the multi-screen contents display environment is growing to be accepted for the display exhibition area. The objectives of this research are to find communications technology and to design an editor interface of contents delivery system for the larger and adaptive multi-display workspaces. The proposed system can find existence of display devices and get information without any additional tools like marker, and can recognize device layout with only web-cam and image processing technology. The multi-display contents delivery system is composed of devices with three roles; display device, editor device, and fixed server. The editor device which has the role of main control uses UPnP technology to find existence and receive information of display devices. extract appointed color in captured picture using a tracking library to recognize the physical layout of display devices. After the device information and physical layout of display devices are connected, the content delivery system allows the display contents to be sent to the corresponding display devices through WebSocket technology. Also the experimental results show the possibility of our device connection and layout recognition techniques can be utilized for the large spaced and adaptive multi-display applications.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.37-40
• /
• 2021

This paper presents a design of a speech to sign language converter for deaf and hard of hearing people. The device is low-cost, low-power consumption, and it can be able to work entirely offline. The speech recognition is implemented using an open-source API, Pocketsphinx library. In this work, we proposed a context-oriented language model, which measures the similarity between the recognized speech and the predefined speech to decide the output. The output speech is selected from the recommended speech stored in the database, which is the best match to the recognized speech. The proposed context-oriented language model can improve the speech recognition rate by 21% for working entirely offline. A decision module based on determining the similarity between the two texts using Levenshtein distance decides the output sign language. The output sign language corresponding to the recognized speech is generated as a set of sequential images. The speech to sign language converter is deployed on a Raspberry Pi Zero board for low-cost deaf assistive devices.