• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.1
• /
• pp.133-150
• /
• 2021

The purpose of this study is to identify the applicability of machine learning targeting titles in the classification of books in public libraries. Data analysis was performed using Python's scikit-learn library through the Jupiter notebook of the Anaconda platform. KoNLPy analyzer and Okt class were used for Hangul morpheme analysis. The units of analysis were 2,000 title fields and KDC classification class numbers (300 and 600) extracted from the KORMARC records of public libraries. As a result of analyzing the data using six machine learning models, it showed a possibility of applying machine learning to book classification. Among the models used, the neural network model has the highest accuracy of title classification. The study suggested the need for improving the accuracy of title classification, the need for research on book titles, tokenization of titles, and stop words.

• Journal of KIISE:Software and Applications
• /
• v.29 no.8
• /
• pp.573-583
• /
• 2002

Pattern recognition process is made up of the feature extraction in the pre-processing, the pattern clustering by training and the recognition process. This paper presents the F-LVQ (Fuzzy Learning Vector Quantization) pattern classification model which is optimized by the fuzzy membership function for the OCR(Optical Character Recognition) system. We trained 220 numeric patterns of 22 Hangul and English fonts and tested 4840 patterns whose forms are changed variously. As a result of this experiment, it is proved that the proposed model is more effective and robust than other typical LVQ models.

• The Journal of Korean Association of Computer Education
• /
• v.3 no.2
• /
• pp.95-106
• /
• 2000

Educational programming languages help learners to easily understand and use computer system itself. They also enhance the reasoning power and the contemplative faculty of learners. However, in spite of the importance of educational programming languages in education, there has not been much research and development on them compared with general purpose programming languages. In this paper, we propose and examine a new educational programming environment TWo (Turtle World) which is designed for learners to utilize the recent information technologies. Aimed at being used as a learning and working tool for multimedia programming and processing, TWo is a web-based reflective object-oriented Hangul programming environment which provides each learner with the learning environment according to his intellectual ability to learn.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.13-22
• /
• 2024

Currently, with the proliferation of digital devices, the significance of handwritten texts in daily lives is gradually diminishing. As the use of keyboards and touch screens increase, a decline in Korean handwriting quality is being observed across a broad spectrum of Korean documents, from young students to adults. However, Korean handwriting still remains necessary for many documentations, as it retains individual unique features while ensuring readability. To this end, this paper aims to implement an application designed to improve and correct the quality of handwritten Korean script The implemented application utilizes the CRAFT (Character-Region Awareness For Text Detection) model for handwriting area detection and employs the VGG-Feature-Extraction as a deep learning model for learning features of the handwritten script. Simultaneously, the application presents the user's handwritten Korean script's reliability on a syllable-by-syllable basis as a recognition rate and also suggests the most similar fonts among candidate fonts. Furthermore, through various experiments, it can be confirmed that the proposed application provides an excellent recognition rate comparable to conventional commercial character recognition OCR systems.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.147-153
• /
• 1995

In this paper, we propose the position- and size-independent handwritten on-line Korean character recognition system using multilayer neural networks which are trained with error back-propagation learning algorithm and the features of Hanguel consonants and vowels. Starting point, end point, and three vectors from starting point to end point of each stroke of characters inputted from mouse or tablet are applied as inputs of neural networks. If double consonants and vowels are separated by single consonants and vowels, all consonants and vowels have at most four strokes. Therefore, four neural networks learn the consonants and the vowels having each number of strokes. Also, we propose the algorithm of separating the consonants and vowels and constructing a character.

• The Journal of Korean Medical History
• /
• v.24 no.2
• /
• pp.25-55
• /
• 2011

The currently existing "Bonchojeonghwa (本草精華)" is a manuscript without the preface and the epilogue, composed of 2 books in 2 volumes. This book is a quintessence of knowledge on science of medicinal ingredients (medicinal phytology I herbal science) as well as an trial of new development in Chosun medical science. I.e. this book includes surprising change representing medical science in Chosun dynasty as a single publication on science of medicinal ingredients. It holds a value essential to clinician as a specialized book in medicinal ingredients, and Includes richer content on medicinal ingredients than any other books published before. In addition, it is away from boring list-up of superfluous knowledge as seen in "Bonchokangmok(本草綱目)" published in China, and well summarizes essential knowledge which can be used within a range of medicines available in Korea. This book has an outstanding structure that can be even used in today's textbook on science of medicinal ingredients, as it has clear theory, system and classification. Because it handles essential learning points prior to prescription to disease, it is possible to configure new prescription and adjustment of medicinal materials. Moreover, this book can play a good role for linguistic study at the time of publication, because it describes many drugs in Hangul in many parts of the book. "Bonchojeonghwa" includes a variety of animals, plants and mineral resources in Korea, like "Bonchokangmok" which was recently listed in UNESCO. As such, it has a significance in natural history as well as pharmacy in Korean Medicine. It has various academic relationships all in biologic & abiologic aspects. It has importance in sharing future biological resources, building up international potential, setting up the standard for biologic species under IMF system, and becoming a base for resource diplomacy. We should not only see it as a book on medicinal ingredients in terms of Oriental Medicine, but also make an prudent approach to it in terms of study strengthening Korea's national competitiveness. After bibliographical reviewing on the features & characteristics of the only existing copy of "Bonchojeonghwa" housed in Kyujanggak(奎章閣) of Seoul National University, the followings are noted. First, "Bonchojeonghwa" is a specialized book on medicinal ingredients voluntarily made by private hands to distribute knowledge on drugs in the desolate situation after Imjinoeran (Japanese Invasion in 1592), without waiting for governmental help. Second, it raised accessibility and practicality by new editing. Third, it classified 990 different kinds of drugs into plant, animal, and mineral at large, and dassified more in detail into 15 'Bu' and 48 'Ryu' at 258 pages. Fourth, the publication of this book is estimated to be around 1625~1633, at the time of Injo's reign in 17th century. Fifth, it contains the existing & up-to-date knowledge at the time of publication, and it is possible to see the supply-demand situation by Hangul descriptions in 149 places in the book. By the fact that there are many linguistic evidences of 17th century, explains well when the book was published.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.8-12
• /
• 2017

본 연구에서는 딥러닝을 이용해 3300종에 이르는 다양한 한글 폰트를 인식하였다. 폰트는 디자인 분야에 있어서 필수적인 요소이며 문화적으로도 중요하다. 한글은 영어권 언어에 비해 훨씬 많은 문자를 포함하고 있기 때문에 한글 폰트 인식은 영어권 폰트 인식보다 어렵다. 본 연구에서는 최근 다양한 영상 인식 분야에서 좋은 성능을 보이고 있는 CNN을 이용해 한글 폰트 인식을 수행하였다. 과거에 이루어진 대부분의 폰트 인식 연구에서는 불과 수 십 종의 폰트 만을 대상으로 하였다. 최근에 이르러서야 2000종 이상의 대용량 폰트 인식에 대한 연구결과가 발표되었으나, 이들은 주로 문자의 수가 적은 영어권 문자들을 대상으로 하고 있다. 본 연구에서는 CNN을 이용해 3300종에 이르는 다양한 한글 폰트를 인식하였다. 많은 수의 폰트를 인식하기 위해 두 가지 구조의 CNN을 이용해 폰트인식기를 구성하고, 실험을 통해 이들을 비교 평가하였다. 특히, 본 연구에서는 3300종의 한글 폰트를 효과적으로 인식하면서도 학습 시간과 파라미터의 수를 줄이고 구조를 단순화하는 방향으로 모델을 개선하였다. 제안하는 모델은 3300종의 한글 폰트에 대하여 상위 1위 인식률 94.55%, 상위 5위 인식률 99.91%의 성능을 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.8-12
• /
• 2017

본 연구에서는 딥러닝을 이용해 3300종에 이르는 다양한 한글 폰트를 인식하였다. 폰트는 디자인 분야에 있어서 필수적인 요소이며 문화적으로도 중요하다. 한글은 영어권 언어에 비해 훨씬 많은 문자를 포함하고 있기 때문에 한글 폰트 인식은 영어권 폰트 인식보다 어렵다. 본 연구에서는 최근 다양한 영상 인식 분야에서 좋은 성능을 보이고 있는 CNN을 이용해 한글 폰트 인식을 수행하였다. 과거에 이루어진 대부분의 폰트 인식 연구에서는 불과 수 십 종의 폰트 만을 대상으로 하였다. 최근에 이르러서야 2000종 이상의 대용량 폰트 인식에 대한 연구결과가 발표되었으나, 이들은 주로 문자의 수가 적은 영어권 문자들을 대상으로 하고 있다. 본 연구에서는 CNN을 이용해 3300종에 이르는 다양한 한글 폰트를 인식하였다. 많은 수의 폰트를 인식하기 위해 두 가지 구조의 CNN을 이용해 폰트인식기를 구성하고, 실험을 통해 이들을 비교 평가하였다. 특히, 본 연구에서는 3300종의 한글 폰트를 효과적으로 인식하면서도 학습 시간과 파라미터의 수를 줄이고 구조를 단순화하는 방향으로 모델을 개선하였다. 제안하는 모델은 3300종의 한글 폰트에 대하여 상위 1위 인식률 94.55%, 상위 5위 인식률 99.91%의 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.142-146
• /
• 2015

본 논문은 뜻풀이를 통해 한글단어를 맞추는 앱 어플리케이션인 '떴다 한글'의 구현에 대하여 논한다. 학습적인 요소와 게임적인 요소를 기반으로 만들어진 이 앱을 통하여 누구나 쉽게 이용하고 한글 단어를 학습할 수 있는 안드로이드 앱 어플리케이션이다. '떴다 한글'은 4가지 특징을 가진다. 첫 번째는 한글의 사전적인 의미를 제공하여 게임이 진행되기 때문에 사용자가 자신이 사용하는 언어의 정확한 뜻을 알 수 있게 하였다. 두 번째는 난이도를 선택할 수 있어 모든 연령대 사람들과 한글에 관심이 많은 외국인 사용자들이 쉽게 이용할 수 있다. 세 번째는 게임적 요소로 중요한 동적인 움직임과 함께 문제를 풀게 하여 사용자가 오랜 시간동안 지루하지 않게 하였다. 네 번째는 순위를 볼 수 있게 하여 자신의 점수를 등록하면 다른 사람들과 경쟁을 할 수 있도록 하여 더욱 이 앱에 관심을 갖도록 하였다. 이러한 특징들은 교육적 측면으로서 좋은 특징을 가지고 있다. 그 외에도 떴다 한글은 데이터베이스 파일을 중심으로 작동하기 때문에 파일의 구조와 입력 정보를 변경하여 여러 버전(헷갈리기 쉬운 단어, 순수우리말, 사자성어 등)의 게임으로 응용이 가능하다는 산업 및 기술적 측면의 모습도 볼 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.2
• /
• pp.477-483
• /
• 2011

These days, smart phones are being widely used and accordingly, a larger number of consumers have become interested in them, thus many applications are being developed with a variety of forms. There are various fields in it, such as multimedia, games, information and education, as per users' disposition and characteristics. As for the current contents for language education in mobile environment, the market is dominated by contents for learning foreign language such as English, Japanese and Chinese, while contents for educating Korean language are minuscule. In this paper, thus, we design and implement a elementary Korean language educational contents for foreign beginners who can use the contents at their smart phones with Android OS.