• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.4
• /
• pp.149-157
• /
• 2019

In case of reading passport using a smart phone in contrast with a dedicated passport reading system, MRZ(Machine Readable Zone) character recognition can be hard when the character strokes were broken, touched or blurred according to the lighting condition, and the position and size of MRZ character lines were varied due to the camera distance and angle. In this paper, the effective recognition algorithm of the passport MRZ information using a combined neural network recognizer of CNN(Convolutional Neural Network) and ANN( Artificial Neural Network), is proposed under the various sized and skewed passport images. The MRZ line detection using connected component analysis algorithm and the skew correction using perspective transform algorithm are also designed in order to achieve effective character segmentation results. Each of the MRZ field recognition results is verified by using five check digits for deciding whether retrying the recognition process of passport MRZ information or not. After we implement the proposed recognition algorithm of passport MRZ information, the excellent recognition performance of the passport MRZ information was obtained in the experimental results for PC off-line mode and smart phone on-line mode.

• Journal of the Korean Society for Precision Engineering
• /
• v.6 no.2
• /
• pp.47-57
• /
• 1989

This paper aims at describing a series development of the electrical machine, by using the Similarity Theory. The character of the electrical machine defined as the Four Terminal Network of the electrical and mechanical energy transmission system, and the analogy theory of the modelmachine can be developed by the Four Termianl System. Also the Restriction Parameter and Disturbance Parameter can be founded by the comparative data of the developed machine that is the character of the theory and measurement.

• Korea Science and Art Forum
• /
• v.37 no.3
• /
• pp.125-134
• /
• 2019

This study was conducted to organize a program to classify and analyze the characteristics of images for the automation of background music selection in the video content production process. The results and contents of the study are as follows: video characteristics are selected as subject category, emotion, pixel motion speed, color, and character material. Subject categories and feelings were extracted using Microsoft's Azure Video Indexer, Pixel Movement Speed was an Optional flow, Color was an Image Histogram for Image, and character materials was CNN(Convolutional Neural Network). The results of this study are significant in that video analysis was conducted to match background music in the recent content production process of 'Internet One-person Broadcasting Creators'.

• Current Research on Agriculture and Life Sciences
• /
• v.25
• /
• pp.13-18
• /
• 2007

The aim of this research is to set improvement guidance a character analysis of woodland edge to cope with the ecological dysfunction of woodland which was caused by massive development project and thoughtless development in country areas. The summary of research result are as follows. 1) From the result of landscape ecology characteristic analysis of woodland in all seven research sites, to begin with, in proportion of appearance by vegetation layer and condition of composition, site 5 showed to be most satisfactory. 2) A width of woodland edge was revealed 7.5m as a minimum, 17.0m as a maximum, and 11.4m as a average and minimum edge was set as 10m according to integrated analysis on each example place. 3) As a result of flexibility analysis, site 1, 2 and 5 was shown high value 3, and it is thought that curve rather than linearity should be maintained in order to increase the ecological function. Also, a phenomenon of straight was prominent, and as a woodland edge, green network and buffering system showed to be somewhat unsatisfactory. 4) Based on the result of character analysis of landscape ecology, main guidelines for improvement of woodland edge were categorized into five in parallel structure and three in vertical structure respectively. The guidelines for improvement of woodland edge suggested by the research has a deep meaning in that it is used as a basic material to induce for controling more systematically or landscape-friendly the defamed forest problems caused by road construction, various development projects, and enlargement of agricultural lands.

• Journal of the Korea Convergence Society
• /
• v.11 no.6
• /
• pp.1-6
• /
• 2020

In this study, research on character recognition, which is one of the fields of computer vision, was conducted. Optical character recognition, which is one of the most widely used character recognition techniques, suffers from decreasing recognition rate if the recognition target deviates from a certain standard and format. Hence, this study aimed to address this limitation by applying deep learning techniques to character recognition. In addition, as most character recognition studies have been limited to English or number recognition, the recognition range has been expanded through additional data training on Korean text. As a result, this study derived a deep learning-based character recognition algorithm for Korean text recognition. The algorithm obtained a score of 0.841 on the 1-NED evaluation method, which is a similar result to that of English recognition. Further, based on the analysis of the results, major issues with Korean text recognition and possible future study tasks are introduced.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.231-238
• /
• 2017

Today, as a means of online communication, the use of emoticons is activated in SNS. Emoticon is an important element to share impact effects and fun together with various content design attempts. In this paper, we analyze the expression patterns changed through development process of emoticons, and analyze characteristics and effects of emoticons which are combined with traditional culture among the types of emoticons currently used.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.33-50
• /
• 1990

Recently, neural networks have been proposed as computaional models for hard prlblems that the brain appears to solve easily. This paper proposes a hierarchical network which practically recognizes printed Hangul characters based on the various psychological stueies. This system is composed of a type classification netwotk and six recognition networks. The former clessifier input character images into one of the six thper by their overall sturcture, and the latter further classify them into character code. Extperiments with most frequently used 990 printed hangul characters conform the superiority of the propsed system. After all, neural nework approach turns out to be very reasonable through a comparison with statistical classifier and an analysis of mis-classification and generalization capability.

• Human Ecology Research
• /
• v.56 no.6
• /
• pp.603-617
• /
• 2018

This study analyzed research trends in the field of Practical Arts (Technology & Home Economics) education. From 958 articles published between 2010 and 2018 in the Journal of Korean Practical Arts Education (JKPAE), Journal of Korean Home Economics Education Association (JHEEA), and Korean Journal of Technology Education Association (KJTEA), 958 keywords were extracted and analyzed using NetMiner 4. When the general network structure was analyzed, keywords such as practical arts education, curriculum, textbook, home economics education, and students were high in the degree centrality and closeness centrality, and textbook, practical arts education, curriculum, student, home economics education, and invention were high in the node betweenness centrality. The cluster analysis showed that a four-cluster solution was most appropriate: cluster 1, technology and experiential learning activities; cluster 2, curriculum studies and practical problem; cluster 3, relationships; and cluster 4, creativity and character education. The three journals showed differences in the knowledge network structure: The topics of JKPAE and JKHEEA focused on general content knowledge and curriculum, while the topics of KJTEA were spread across invention and creativity education, and curriculum studies.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.491-494
• /
• 2004

Neural Oscillator can be applied to oscillatory systems such as the image recognition, the voice recognition, estimate of the weather fluctuation and analysis of geological fluctuation etc in nature and principally, it is used often to pattern recoglition of image information. Conventional BPL(Back-Propagation Learning) and MLNN(Multi Layer Neural Network) are not proper for oscillatory systems because these algorithm complicate Learning structure, have tedious procedures and sluggish convergence problem. However, these problems can be easily solved by using a synchrony characteristic of neural oscillator with PLL(phase-Locked Loop) function and by using a simple Hebbian learning rule. And also, Recognition velocity of Korean Character can be improved by using a Neural Oscillator's learning accelerator factor η$\_$ij/

• Journal of Korean Library and Information Science Society
• /
• v.12
• /
• pp.1-33
• /
• 1985

This study has been aimed to analyze the following three points which are believed to be the most important in establishing efficient library networks. The writers have done the research into the literature and references concerning the networks of library, as they are considered crucial functions in cooperative administration between the libraries. The following are the findings from the survey: 1) The established networks in foreign countries have been compared with those of Korea, basing upon the data and present situations in both areas and the definition and agreed viewpoint of the networks are presented. 2) The relations between the existing Library system and Consortia were clarified in view of the current trend, thus showing the scope and integral aspects of them. 3) Finally, we have classified the types of network into four categories, such as search service network, customized service network, service center/network and state local networks, and made through analysis of the character, organization and management of each realm.