• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.4
• /
• pp.54-64
• /
• 1999

This paper proposes an efficient handwritten English word recognition scheme which can be applied practical applications. To effectively use the lexicon which is available in most handwriting related applications, the lexicon entries are introduced in the early stage of the recognition. Dynamic programming is used for matching between over-segmented character segments and letters in the lexicon entries. Character segmentation statistics which can be obtained while the training is being performed are used to adjust the matching window size. Also, the matching results between the character segments and the letters in the lexicon entries are cached to avoid repeat of the same computation. In order to verify the effectiveness of the proposed methods, several experiments were performed using thousands of word images with various writing styles. The results show that the proposed methods significantly improve the matching speed as well as the accuracy.

• Journal of Computing Science and Engineering
• /
• v.10 no.2
• /
• pp.39-50
• /
• 2016

In this paper, we present a comparative study of spatial domain features for writer identification and verification with different ink width conditions. The existing methods give high error rates, when comparing two handwritten images with different pen types. To the best of our knowledge, we are the first to design the feature with different ink width conditions. To address this problem, contour based features were extracted using a chain code method. To improve accuracy at higher levels, we considered histograms of chain code and variance in bins of histogram of chain code as features to discriminate handwriting samples. The system was trained and tested for 1,000 writers with two samples using different writing instruments. The feature performance is tested on our newly created dataset of 4,000 samples. The experimental results show that the histogram of chain code feature is good compared to other methods with false acceptance rate of 11.67%, false rejection rate of 36.70%, average error rates of 24.18%, and average verification accuracy of 75.89% on our new dataset. We also studied the effect of amount of text and dataset size on verification accuracy.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1114-1135
• /
• 2018

A multiple classification system based on a new boosting technique has been approached utilizing different biometric traits, that is, color face, iris and eye along with fingerprints of right and left hands, handwriting, palm-print, gait (silhouettes) and wrist-vein for person authentication. The images of different biometric traits were taken from different standard databases such as FEI, UTIRIS, CASIA, IAM and CIE. This system is comprised of three different super-classifiers to individually perform person identification. The individual classifiers corresponding to each super-classifier in their turn identify different biometric features and their conclusions are integrated together in their respective super-classifiers. The decisions from individual super-classifiers are integrated together through a mega-super-classifier to perform the final conclusion using programming based boosting. The mega-super-classifier system using different super-classifiers in a compact form is more reliable than single classifier or even single super-classifier system. The system has been evaluated with accuracy, precision, recall and F-score metrics through holdout method and confusion matrix for each of the single classifiers, super-classifiers and finally the mega-super-classifier. The different performance evaluations are appreciable. Also the learning and the recognition time is fairly reasonable. Thereby making the system is efficient and effective.

• The Journal of Churna Manual Medicine for Spine and Nerves
• /
• v.11 no.1
• /
• pp.85-95
• /
• 2016

Objectives : The purpose of the this study is to report the improvement after Chuna manual therapy about patient with essential tremor. Methods : The patient of essential tremor was treated by Myofascial Release Technique(MRT) and Chuna manual therapy with acupuncture, cupping, Transcutaneous electrical nerve stimulation(TENS), herbal medicine therapy. Results : According to evaluation of Handwriting test and VAS, The patient has shown improvement aftert Chuna Manual Therapy. Conclusions : This study suggest that Chuna manual therapy with other treatment would be effective for patient of essential tremor.

• Journal of the Korean Society of Food Culture
• /
• v.27 no.3
• /
• pp.304-315
• /
• 2012

"Japji" was an old cookbook written in 1721. There are 27 types of foods recorded in "Japji"; 10 descriptions of Byeonggwaryu (rice cakes and cookies): Yakgwa, Junggye, Mandugwa, Chaesugwa, Umujeonggwa, Dongajeonggwa, Baekjapyeon, Aengdupyeon, Toranbyeong, and Yeot; and 16 descriptions of Chanpumryu (side dishes): Jinjumyeon, Jeunggyetang, Geumjungtang, Eoreumtang, Changjajjim, Gajijjim, Oejjim, Dubuseon, Dubuneureumi, Geneureumi, Gesanjeok, Hodojaban, Jeonyak, Seokryutang, Sungeojuak, and Yangmandu. There is also a description of Gugija (Chinese wolfberry) liquor. Here, comparative analysis based on culinary science was carried out on the Korean foods recorded in "Japji" as well as the similar foods recorded in "Gyuhapchongseo" (Women's Encyclopedia) written around 1815. Of the 27 types of Korean foods recorded in "Japji", 13 were also found recorded in "Gyuhapchongseo". The time period for "Japji" can be assumed to be 1721 based on the fact that it is written in a cursive handwriting style of Hangeul, that chili was never used as an ingredient, and that the word "Shinchuknyeon (辛丑年)" was transcribed at the beginning of the book. The dating method also included considerations of whether Neureumi was used or not as well as changes in its cooking style.

• Journal of the Korean Geographical Society
• /
• v.38 no.1
• /
• pp.127-140
• /
• 2003

This study attempts to summarize the progress of Journalistic Cartography and to investigate the quantitative growth and the transition of the forms and contents of the media maps in Korean newspapers. And this study examines the characteristics of media maps with the technological development. The results of this study are summarized as follows. First, 'Jigujeondo' in Hanseongsunbo in 1880s is the first media map in Korea. Secondly, the number of the media maps in Korean newspapers is influenced by the political and economic environments. As the time goes, the contents of the media maps have been raried. Thirdly, the representation of the media maps has their own special characteristics according to the technological developments from the handwriting to CTS.

• Journal of the Korean Society of Costume
• /
• v.61 no.8
• /
• pp.32-44
• /
• 2011

This study will explore the application of the Korean alphabet 'Hangul' and its calligraphy on fashion design. Hangul is well known for its great formative characteristics. Its calligraphy has unique features that express the implicative meaning of the Korean language while simultaneously displays beautiful shapes that draw the viewer's eye. When Hangul calligraphy is applied on the pattern design, it can be an excellent opportunity to demonstrate the visual beauty of Hangul. The purpose of this study is to develop the pattern designs that utilize the Hangul calligraphy and apply them in various fields of fashion. The detailed concepts of this study are as follows. First, the theoretical concepts and characteristics of both Hangul calligraphy and pattern design will be understood. Second, the aesthetic characteristics of calligraphy will be drawn by case analysis on the artworks of famous calligraphers such as Kim Jong-geon, Kang Byeong-in, Lee Sang-hyeon, Lee Gyu-bok and other representative calligraphers who design the beauty of Korean calligraphy by handwriting and brush-writing. The obtained results will be used to explore the desirable direction of fashion design. Third, eight pattern motif fashion works that utilize Hangul calligraphy in accordance with the arrangement of different characteristics of fashion design will be presented.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.2
• /
• pp.1-9
• /
• 2018

Currently, the record of part-timer is mainly written in handwriting or using excel work schedule, paper work recorder, and time attendance program using POS program. And, work table, commute records, paycheck are managed separately. Time-attendance information is not linked and is managed separately, and payment of wages is often not done accurately. And, it is difficult to pay the wages because it is not able to accurately grasp the state of attendance of part-timer. Therefore, it is necessary to have a transparent wage and work management system based on the trust between the owner and the part-timer. In this paper, we design a system that can perform real-time commute check using beacon, transparent wage management, wage calculation by automatic calculation, and smooth communication between owner and the part-timer. We have also implemented a store management mobile application using Android Studio 2.3, Eclipse, Android 5.1 and Beacon devices in a MySQL environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.946-949
• /
• 2019

한 벌의 한글 글자체를 만드는데 일반적으로 많은 제작 비용과 시간이 소요된다. 따라서 폰트 제작의 어려움을 덜기 위해, 사용자가 대표 글자들을 입력하면 그 글자들의 디자인 특성을 딥러닝 기술을 이용하여 학습한 모델이 나머지 글자들을 자동 생성해주는 시스템 구축한다면 폰트 제작이 훨씬 용이해질 뿐만 아니라 저작권 문제로부터 자유로워질 것이다. 이와 관련된 선행연구를 실행하고 분석해 본 결과 데이터 전처리 과정에서 글자가 잘리거나 크기가 맞지 않아 제대로 된 데이터셋이 구축되지 않는 문제가 있음을 발견하였다. 본 논문에서는 이러한 문제를 해결하기 위해 템플릿에서 자동적으로 글자영역을 추출하고 이미지를 보정하는 전처리 과정과 함께 기존 모델에서 새로운 필터를 추가하여 학습 성능을 높이는 방법을 제안한다. 이를 통해 기존 연구에서 측정된 손실값을 낮춘 결과를 확인했으며 결과적으로 실제 글자체와 더욱 유사한 사용자 맞춤형 글자체를 제공할 수 있을 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1000-1003
• /
• 2020

본 논문은 기계학습 기반 온라인 한글 필기 인식 시스템의 첫 구현 결과를 담고 있다. 한글의 글자는 최소한 하나의 모음을 포함하고 있으며, 이 모음은 대개 직선으로 필기한다는 사전 지식을 활용하여 인식에 적용하고자 한다. 이를 위해 사용자가 온라인으로 필기하면 획 데이터를 획득하여 중성에 해당하는 모음을 찾는 알고리즘을 개발하였다. 제안한 알고리즘에서는, 우선 필기한 글자를 포함하는 사각형 R과 각 획을 둘러싸는 사각형 SR을 생성한 후, 직선을 판별하고, 이 직선들이 모음을 구성하는 후보군을 찾는 과정으로 구성되어 있다. 아직 초기 연구이므로, 다양한 경우에 대한 분석이나 실험 결과는 없지만, 이를 활용하여 온라인 필기 인식 모델에 적용하여 인식 성능을 높이기 위한 추후 연구의 기반으로 활용하고자 한다.