• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.900-904
• /
• 1991

In this paper, our study for the recognition of Hand-written Korean characters, Arabic numbers and alphabets by neural netwoks. This System extracts feature of character by using the MESH feature point of handwritten character, Arabic numbers and alphabets. To reduce the input image data, features are extracted from each input images. A MLP(multi-layer perceptron) with one hidden layer was trained with a modified BEP(back error propagation) algorithm. This method extracts feature sets of the characters directly from the scanner and can enhance computation speed without using the special preprocesses such as size normalization, smoothing, and thinning.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.186-190
• /
• 1998

정상 피험자에 있어서 수행 성적의 차이를 보이는 음소적 단어 생성과 의미적 단어생성에 관련한 대뇌 피질의 활동양상의 차이를 밝히기 위해 피험자에게 단어 생성의 과제를 주면서 기능적 자기공명 영상술(functional magnetic resonance imaging, fMRI)을 시행하였다. 모두 7명의 정상인에서 음소 단서에 의한 단어생성은 의미 범주 단어에 의한 단어생성보다 광범위한 피질 영역의 활성화를 보였는데, 특히 bilateral posteroinferior temporal cortices, left premotor cortex, right cerebellum, bilateral superior parietal lobules에서 더 높은 활성화를 보였다. 이에 반하여 의미적 단어생성은 주로 bilateral posterior cingulate gyri에서 더 높은 활성화를 보였다. 이런 결과는 음소적 생성은 가능한 자모를 조합하여 어휘를 생성한 후 작업기억에 일시 저장시켜 놓고 verbal rehearsal 과정을 사용하여 단어 여부를 판별하는 것을 시사하며, 의미적 생성은 mental imagery를 통하여 시각적 인출 단서를 찾은 후, 의미 기억으로부터 단어를 직접 인출하는 것으로 보인다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.3
• /
• pp.401-408
• /
• 1986

In optical pattern recognition, incorrect discrimination may result from a relatively high cross correlation peak between similary shaped objects. In this paper, a new modified matched CGH(computer generated hologram) filter is proposed for reducing the cross-correlation without reducing the autocorrelation. Computer simulation and experimental results show that this new method can be used efficiently for optical Korean alphabets recognition. The signal to noise characteristics are analyzed on the correlation distdribution diagram.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.368-372
• /
• 2019

맞춤법 교정이란 주어진 문장에서 나타나는 철자 및 맞춤법 오류들을 올바르게 교정하는 것을 뜻하며 맞춤법 교정 시스템이란 컴퓨터가 이를 자동으로 수행하는 것을 의미한다. 본 논문에서는 맞춤법 교정을 기계번역의 관점으로 바라보고 문제를 해결하였다. 소스문장에 맞춤법 오류문장, 타겟 문장에 올바른 문장을 넣어 학습시키는 방법을 제안한다. 본 논문에서는 단일 말뭉치로 한국어 맞춤법 병렬 말뭉치를 구성하는 방법을 제안하며 G2P(Grapheme to Phoneme)를 이용한 오류 데이터 생성, 자모 단위 철자 오류데이터 생성, 통번역 데이터 기반 오류 데이터 생성 크게 3가지 방법론을 이용하여 맞춤법 오류데이터를 생성하는 방법론을 제안한다. 실험결과 GLEU 점수 65.98의 성능을 보였으며 44.68, 39.55의 성능을 보인 상용화 시스템보다 우수한 성능을 보였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.507-513
• /
• 2018

Steganography is a technique that uses hidden messages to prevent anyone apart from knowing the existence of a secret message, except the sender and trusted recipients. This paper applies 24 bit color image as cover medium. And a 24-bit color image has three components corresponding to red, green and blue. This paper proposes an image steganography method that uses Triple-A algorithm to hide the secret (Hangul) message by arbitrarily selecting the number of LSB bits and the color channel to be used. This paper divides the secret character into the chosung, jungsung and jongsung, and applies crossover, encryption and arbitrary insertion positions to enhance robustness and confidentiality. Experimental results of the proposed method show that insertion capacity and correlation are excellent and acceptable image quality level. Also, considering the image quality, it was confirmed that the size of LSB should be less than 2.

• Journal of Internet Computing and Services
• /
• v.22 no.4
• /
• pp.29-49
• /
• 2021

This paper proposes the Hunminjungum Keypad that applied the creation principle of Hunminjungum to the design of keypad. The proposed keypad arranged 28 letters of Hunminjungum to have correlations with each other between consonants, between vowels, and between consonants and vowels. That is, Consonant buttons are arranged by grouping letters of the same sound by sounds of five voices. And the vowel buttons are arranged at the bottom and the right side of the consonant area according to the position where a vowel is attached to the consonant. In the meantime, Hangul keypads have mainly used 12 button keypads in 4 lines and 3 columns. These keypads have structurally disadvantageous in the touch count and moving distance. Recently, keypads with many letter buttons such as QWERTY and single-vowel are also used a lot. If the number of letter buttons provided in the keypad increases, touch count decreases. And If the letter buttons are arranged to have a correlation with each other, the moving distance becomes smaller. The experimental results show that the proposed keypad has high efficiency in all evaluation factors such as touch count, moving distance and input time.

• The Journal of Korean Academy of Sensory Integration
• /
• v.9 no.1
• /
• pp.21-31
• /
• 2011

Objective : This study investigated the relationships of handwriting legibility and perceptual-motor skills, and handwriting speed and perceptual-motor skills. And identified the predictors that most affect the handwriting of preschool children. Methods : Twenty-three typically developing preschool aged children (mean age: 68.61 months, SD=2.04) were selected through the Korean-Denver Developmental Screening Test-2(K-DDST-2). The children were tested with regard to handwriting legibility, visual perception, visual-motor integration and fine-motor coordination. Results : First, a significant relationship was not found among handwriting legibility, visual perception, visualmotor integration and fine-motor coordination. Second, a significant relationship was found among handwriting speed, visual perception and fine-motor coordination. Third, stepwise multiple regression analyses showed that general visual perception were significant predictors for handwriting speed. Conclusion : Occupational therapists should evaluate children's visual perception levels utilizing a standardized test, and focus on general visual perception in order to improve handwriting skill(speed). Also, occupational therapists are expected to play an important role in the management and treatment of children's handwriting skills.

• The Journal of Korean Academy of Sensory Integration
• /
• v.15 no.1
• /
• pp.10-20
• /
• 2017

Objective : The purpose of this study was to investigate the effect of proprioceptive-vestibular based sensory integrative intervention on handwriting and fine motor function in elementary school students in grades 1 to 3. Methods : In this study, eight students in an elementary school in Busan were enrolled. The intervention was conducted twice a week from May to October, 2016, and a total of 14 intervention sessions were conducted. In order to evaluate the writing ability and the fine-motor exercise ability before and after the intervention, the fine-motor movement items of the Korean alphabet writing test and the Bruininks-Oseretsky Test of Motor Proficiency (BOTMP) evaluation were used. Results : There was a statistically significant difference between the total scores of consonant writing and the Korean alphabet writing assessment after the intervention. In BOTMP-Fine motor, the response speed items showed statistically significant difference. Visual-motor control scores increased during intervention, but the statistical significance was not found. Conclusion : Sensory integration interventions might have positive effects on elementary school students' writing skills and fine motor functions.

• Korean Journal of Cognitive Science
• /
• v.9 no.1
• /
• pp.1-11
• /
• 1998

In this paper, the features which are thought to be used by humans based on the psychological experiment of human information processing are applied to character recognition problem. Man will deal with a little large area information as well as pixel by pixel information. Therefore we define the feature that represents a little wide region I information called region feature, and combine the features derived from region feature and pixel by pixel features that have been used by now. The features we used are the result of region feature based preanalysis, mesh with region attributes, cross distance difference and gradient. The training and test data in the experiment are handwritten Korean alphabets, digits and English alphabets, which are trained on neural network using back propagation algorithm and recognition results are 90.27-93.25%, 98.00% and 79.73-85.75%, respectively Experimental results show that the feature we are suggesting in this paper is 1-2% better than UDLRH feature similar in attribute to region feature, and the tendency of misrecognition is more easily acceptable by humans.

• Journal of Information Management
• /
• v.43 no.2
• /
• pp.199-222
• /
• 2012

Due to the increase of international business and activities, Koreans nowadays have higher needs to present their personal identity to the foreigners. In this process, the first requirement is to exchange personal names with foreigners. Therefore, the phonetic translation of Korean names into Roman alphabetic notation is frequently required, in order to deliver Korean personal names to the people who do not understand Korean alphabet. However, some confusions have been witnessed in the way of transforming Korean names into Roman (English) alphabet notation, due to the fact that there are many different ways to put Korean pronunciation into Roman (English) alphabet. This study examines different formats of Romanization of Korean personal names to find and suggest an optimal one. It first examines structures of and differences between Korean and Western personal names and usage patterns, reviews the issues surrounding Romanization of Korean personal names, and patternizes diverse Romanization formats currently used. Based on these examinations and consequent findings, I would like to suggest a format for the Romanization of Korean personal names which is considered to be the best.