• Title/Summary/Keyword: Hangul recognition

Search Result 150, Processing Time 0.027 seconds

Grapheme Segmentation Method for Low Quality Printed Hangul Text Recognition (저해상도 인쇄체 한글 영상 인식을 위한 자소 분할 방법)

  • Lee Seong-Hun;Cho Kyu-Tae;Kim Jin-Sik;Kim Jin-Hyung;Jung Cheol-Kon;Kim Sang-Kyun;Moon Young-Su;Kim Ji-Yeun
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2006.06b
    • /
    • pp.382-384
    • /
    • 2006
  • 본 논문에서는 저해상도 한글 영상을 자소 단위로 분리하는 방법을 제안한다. 비디오 자막이나 저해상도 스캔 영상의 경우 자소간 획이 접촉되거나 잡영이 많이 포함되어 기존의 자소 분할 방법으로는 한계가 있다. 한자 문자열을 문자 단위로 분할하는데 사용된 비선형 분할 경로 알고리즘을 한글 낱자 영상에 적용하여 자소 단위로 분할한다. 기존의 분할 경로 알고리즘을 한글 자소 분할에 효과적으로 적용하기 위해서 우세점 탐지 알고리즘을 이용하여 자소간 접촉점을 찾고 이를 바탕으로 생성된 분할 경로에 따라 여러 개의 자소 후보 영상이 생성된다. 자소 영상을 자소 인식기로 인식한 결과 높은 인식률을 보이는 것을 실험을 통하여 확인하였다.

  • PDF

Development of Algorithm for Online Handwriting Hangul Recognition (온라인 한글 필기 인식 알고리즘 개발)

  • Jeong, Dabin;Lee, Kang Eun;Jeong, Min Jin;Moon, Changjin;Kim, Sungsuk;Kim, Jaehyun;Yang, Sun Ok
    • Annual Conference of KIPS
    • /
    • 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.

Perspectives of Korean Modernity from the 18th Century to the Present: Intellectual Struggles for Koreanity in the Age of Globalization

  • Yoon, Ho-Byeong
    • Lingua Humanitatis
    • /
    • v.2 no.2
    • /
    • pp.267-282
    • /
    • 2002
  • For the effective study of Korean modernization from the 18th century to the present, three areas have been investigated in my paper: the age of dawn in recognizing the necessity of modernism, the era of experimentation from recognition to practice, and the development of modernism in literature: from the 1930s to the present. Through whole process of discussing those matters, Koreanity- identifying itself to be Korean - has been emphasized. While the so-called traditional values confronted with the whole turmoil of socio-political demolitions in the name of modernization, westernization, and culturalization, Korean intellectuals tried to emphasize how important it was to keep Korean identities, namely the Koreanity. Such examples can be seen in the activities of Northern School and Moderate School. Though Koreans had to have a short hair cut in contradiction with their traditional morality to be modernized/westernized/cultivated, it was a turning point for them to take a step toward the international world. During the period of Korean modernization through the impact of Western world, Korean language-hangul- has been cultivated to the highest level in comparison with two foreign languages: Japanese and English. Those Korean linguists who were familiar with these two languages made Korean grammar systematic and they understood the importance of preserving Koreanity in the course of pursuing modem western society. In this sense, Korean modernism is related to the cultural glocalism(globalism+ localism), not to the cultural globalism. Through the help of socio-political modernization, Korean literature in modernism has been full bloomed in the early years of 1930s. One of the leading poets was Sang Lee whose poetic heritage is inherited by those groups of 1950s and I 960s. Among many others, Chunsu Kim and Sunghun Lee were the main figures in realizing the fact the poetry is written in Korean which they considered the body, the soul, and the mother land.

  • PDF

Psychological Disturbance caused by Letters in Double lmage and its lmplication on Perceptual Integration (글자의 이중상에 의한 심리적 혼란감과 지각 통합 과정)

  • Park, Sang-Ho;Chung, Chan-Sup
    • Korean Journal of Cognitive Science
    • /
    • v.6 no.1
    • /
    • pp.47-71
    • /
    • 1995
  • A psychological disturbance caused by letters in double image was termed as'letter sickness'.The effects of stimulus exposure time and letter familiarity on the letter sickness were measured to test a hypothesis that disturbances in eye movement and recognition stages is the cause of letter sickness.Letter sickness incteased significantly as stimulus exposure time lengthened from 50ms,100ms,to 3000ms.It was also significantly higher with familiar Hangul letters as compared with less familiar foreign letters and meaningless words as compared with meaningful words,respectively.These experimental findings imply that letter sickness is caused by the failure of adjusting eye movements to dismiss the double images.that the more familiar the letters.the more strongly the letter-identification process is commotted,resulting in the increased effect of disturbance from double image.and that the disturbance effect of double image is amplified when it is hard to extract the meaning from familiar letters.An experiment where subjects were made to learn Braille-like symbols consisting of 6 dots to test the hypothesis that the stronger the tendency to process the meaning of a symbol,the stronger becomes letter sickness due to double image,also showed that letter sickness significantly increased as a function of learning.

  • PDF

Development of the Rule-based Smart Tourism Chatbot using Neo4J graph database

  • Kim, Dong-Hyun;Im, Hyeon-Su;Hyeon, Jong-Heon;Jwa, Jeong-Woo
    • International Journal of Internet, Broadcasting and Communication
    • /
    • v.13 no.2
    • /
    • pp.179-186
    • /
    • 2021
  • We have been developed the smart tourism app and the Instagram and YouTube contents to provide personalized tourism information and travel product information to individual tourists. In this paper, we develop a rule-based smart tourism chatbot with the khaiii (Kakao Hangul Analyzer III) morphological analyzer and Neo4J graph database. In the proposed chatbot system, we use a morpheme analyzer, a proper noun dictionary including tourist destination names, and a general noun dictionary including containing frequently used words in tourist information search to understand the intention of the user's question. The tourism knowledge base built using the Neo4J graph database provides adequate answers to tourists' questions. In this paper, the nodes of Neo4J are Area based on tourist destination address, Contents with property of tourist information, and Service including service attribute data frequently used for search. A Neo4J query is created based on the result of analyzing the intention of a tourist's question with the property of nodes and relationships in Neo4J database. An answer to the question is made by searching in the tourism knowledge base. In this paper, we create the tourism knowledge base using more than 1300 Jeju tourism information used in the smart tourism app. We plan to develop a multilingual smart tour chatbot using the named entity recognition (NER), intention classification using conditional random field(CRF), and transfer learning using the pretrained language models.

A Study on Hangul Handwriting Generation and Classification Mode for Intelligent OCR System (지능형 OCR 시스템을 위한 한글 필기체 생성 및 분류 모델에 관한 연구)

  • Jin-Seong Baek;Ji-Yun Seo;Sang-Joong Jung;Do-Un Jeong
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.23 no.4
    • /
    • pp.222-227
    • /
    • 2022
  • In this paper, we implemented a Korean text generation and classification model based on a deep learning algorithm that can be applied to various industries. It consists of two implemented GAN-based Korean handwriting generation models and CNN-based Korean handwriting classification models. The GAN model consists of a generator model for generating fake Korean handwriting data and a discriminator model for discriminating fake handwritten data. In the case of the CNN model, the model was trained using the 'PHD08' dataset, and the learning result was 92.45. It was confirmed that Korean handwriting was classified with % accuracy. As a result of evaluating the performance of the classification model by integrating the Korean cursive data generated through the implemented GAN model and the training dataset of the existing CNN model, it was confirmed that the classification performance was 96.86%, which was superior to the existing classification performance.

The influence of syllable frequency, syllable type and its position on naming two-syllable Korean words and pseudo-words (한글 두 글자 단어와 비단어의 명명에 글자 빈도, 글자 유형과 위치가 미치는 영향)

  • Myong Seok Shin;ChangHo Park
    • Korean Journal of Cognitive Science
    • /
    • v.35 no.2
    • /
    • pp.97-112
    • /
    • 2024
  • This study investigated how syllable-level variables such as syllable frequency, syllable (i.e. vowel) type, presence of final consonants (i.e. batchim) and syllable position influence naming of both words and pseudo-words. The results of the linear mixed-effects model analysis showed that, for words, naming time decreased as the frequency of the first syllable increased, and when the first syllable had a final consonant. Additionally, words were named more accurately when they had vertical vowels compared to horizontal vowels. For pseudo-words, naming time decreased and accuracy rate increased as the frequency of the first or the second syllable increased. Furthermore, pseudo-words were named more accurately when they had vertical vowels compared to horizontal vowels. These results suggest that while the frequency of the second syllable had differential effects between words and pseudo-words, the frequency of the first syllable and the syllable type had consistent effects for both words and pseudo-words. The implications of this study were discussed concerning visual word recognition processing.

Handwritten Hangul Word Recognition from Small Vocabulary using Grapheme Combination Type (자모 결합 유형을 이용한 적은 어휘에서의 필기 한글 단어 인식)

  • Jin, Yu-Ho;Kim, Ho-Yeon;Kim, In-Jung;Kim, Jin-Hyeong
    • Journal of KIISE:Software and Applications
    • /
    • v.28 no.1
    • /
    • pp.52-63
    • /
    • 2001
  • 필기 단어 인식 방법에는 낱자별 분할 및 낱자 단위 인식을 통해 인식하는 방법과 단어 사전을 이용하여 단어와 영상을 직접 비교하는 방법이 있다. 이 중 후자는 인식 대상이 되는 단어들이 작은 수의 어휘로 제한되었을 대 매우 효과적이다. 본 논문에서는 입력 영상이 주어졌을 때 자모를 순차적으로 탐색하고 그 결과의 최적 조합을 찾아 인식하는 사전을 이용한 필기 한글 단어 인식 방법을 제안한다. 입력 영상은 사전의 각 단어와의 매칭을 통해 인식된다. 단어는 필기 순서로 정렬된 자모열로 표현하고 입력 영상은 획들의 집합으로 표현한다. 단어의 자모들은 입력 영상으로부터 추출된 획들의 집합으로부터 단계적으로 탐색된다. 각 단계에서는 전 단계까지의 매칭 상태와 탐색하려는 자모의 형태로부터 자모가 존재할 것이라고 기대되는 정합 기대 영역을 설정한 후 그 안에서 자모 탐색기를 이용해 자모를 찾는다. 자모 탐색기는 획들의 집합으로 이루어진 복수의 자모 후보와 그 점수를 출력한다. 각 단계마다 생성된 자모 후보들은 최적의 단어 매칭을 찾기 위한 탐색 공간을 이룬다. 본 연구에서는 단어 사전을 trie로 구성하고, 탐색 과정에서 dynamic programming을 이용하여 효과적으로 탐색을 수행하였다. 또한 인식 속도를 향상시키기 위해 산전 축소, 탐색 공간 축소 등 다양한 지식을 이용하였다. 제안하는 방법은 무제약으로 쓰여진 필기 단어도 인식 할 수 있을 뿐 아니라, 동적 사전을 이용하기 때문에 사전의 내용이 변하는 환경에서도 적용할 수 있다. 인식 실험에서는 39개의 단어로 이루어진 사전에 대하여 613개의 단어 영상에 대해 실험한 결과 98.54%의 높은 인식률을 보임으로써 제안하는 방법이 매우 효과적임을 확인하였다. 아니라 곰팡이 균주도 실제 praxis에 적합하게 개발시킬수 있다. 따라서 앞으로 발효육제품제조에 있어 starter culture가 갖는 의미는 매우 중요하며 특히 짧은 숙성기간을 거치는 발효소시지의 제조에 있어서는 필수불가결한 공정의 한 분야로 자리잡게 될 것이다.큰 차이 없었으나 이중포장과 진공포장은 상당히 효과적임을 알 수 있었다.로는 18%에 비하여 22%가 더 적합한 것으로 생각되었다.$0.15{\sim}0.35%$이었다.irc}C$에서 $13.49{\times}10^{-3}$이었다. 이 값들을 Arrhenius식에 대입하여 구한 활성화 에너지는 24.795 kJ/Kmol이었다. 이 값으로부터 결정한 살균 포장약주 명가의 상용 저장 수명은 $10^{\circ}C$에서 2년, $20^{\circ}C$에서 1년 4개월, $25^{\circ}C$에서 1년 2개월 이었다. 서울의 매월 평균 온도를 기준으로 계산할 때 본제품의 상용저장기간은 1년 8개월이었다.로 반죽이 호화되고 가열시간이 그 이상으로 증가할 때도 반죽의 호화가 약간은 진행되지만 $90^{\circ}C$ 이상의 가열온도에서는 가열시간 0.5분 이내에 반죽의 호화가 급속히 일어나고 가열 시간을 증가시켜도 더이상의 호화는 일어나지 않았다. 같은 조건에서는 waxy corn starch 반죽의 호화 속도가 corn starch보다 더 빠른 것으로 나타났다. 대표적으로 52% 수분함량에서 반응속도상수(k)와 가열온도(T)사이의 관계식은 corn starch의 경우 $logk=11.1140-4.1226{\times}10^3(1/T)

  • PDF

The Effect of Syllable Frequency, Syllable Type and Final Consonant on Hangeul Word and Pseudo-word Lexical Decision: An Analysis of the Korean Lexicon Project Database (한글 두 글자 단어와 비단어의 어휘판단에 글자 빈도, 글자 유형, 받침이 미치는 영향: KLP 자료의 분석)

  • Myong Seok Shin;ChangHo Park
    • Korean Journal of Cognitive Science
    • /
    • v.34 no.4
    • /
    • pp.277-297
    • /
    • 2023
  • This study attempted to find out how lexical decision of two-syllable words or pseudo-words is affected by syllabic information, such as syllable frequency, syllable (i.e. vowel) type, and presence of final consonant (i.e. batchim), through the analysis of the Korean Lexicon Project Database (KLP-DB). Hierarchical regression of RT data showed that lexical decision of words was influenced by the frequency of the first syllable, the syllable type of the first and second syllables, batchim for the first and second syllables, and also by the interaction of the two syllable types and the interaction of syllable frequency and batchim of the second syllable. For pseudo-words lexical decision was influenced by the frequency of the first and second syllables, syllable type of the first syllable, and batchim for the first and second syllables, and also by the interaction of the two syllable frequencies, the interaction of the two syllable types, and the interaction of syllable frequency and batchim of the first syllable. Word frequency had a strong effect on lexical decision of words, while syllabic information had a stable effect on the lexical decision of pseudo-words. These results indicate that syllabic information should be seriously considered in constructing word and pseudo-word lists and interpreting lexical decision time. Understanding the effect of syllabic information will also contribute to the understanding of word recognition process.

The Life Experiences of the Deaf Elderly (농아노인의 생활 경험)

  • Park, Ina;Hwang, YoungHee;Kim, Hanho
    • 한국노년학
    • /
    • v.36 no.3
    • /
    • pp.525-540
    • /
    • 2016
  • The purpose of this study was to investigate what kind of experiences the deaf elderly would have in the course of life. It also aimed to promote the understanding of their living difficulties and culture among people with normal hearing and provide basic data to help them live with others as members of the community. Phenomenological qualitative research was conducted as part of the methodology. The subjects include seven deaf old people. Based on the results of in-depth interview and analysis, the life experiences of the deaf elderly were categorized into "unforgettable wounds," "life in the community," "life with the family," "marriage of the deaf elderly", and "living by adjusting to reality." First, the subcategories of "unforgettable wounds" include "receiving no treatment for fever," "damage by the Korean War," "alienation from the family," and "people's cold eyes." It turned out that the deaf elderly had led a life, suffering from the heart wounds that they could not forget. Second, the subcategories of "life in the community" include "inconvenience in life," "disadvantages in life," and "severed life." The deaf elderly were not only subjected to inconvenience and disadvantages in life, but also suffered loneliness, being cut off from the community. Third, the subcategories of "life with the family" include "not communicating with children," "being abandoned again," "being used by the family," "being lonely even with the family," and "wishing to live independently from the family." The deaf elderly were not supported by their families and were abandoned or used by them, leading a solitary life. Fourth, the subcategories of "marriage of the deaf elderly" include"send as a surrogate mother," "frequent remarriage and divorce," "lean on as a married couple." Deaf elderly form their own culture of the marriage and lean on each other. Finally, the subcategories of "living by adjusting to reality" include "getting help from neighbors," "behaving oneself right in life," "learning Hangul," "living by working," "living freely," "living by missing," and "controlling the impulse to end life," "resorting to religion." The deaf elderly made the most alienated and vulnerable group with no access to benefits due to their limitations as a linguistic and social minority, but they made efforts to form their own culture and adjust to reality for themselves. Based on those findings, the study made the following proposals: first, there is a need for practical approaches to heal the ineffaceable wounds in the hearts of deaf elderly. Second, there is a need for policies to help them experience no inconvenience and disadvantages as members of community and communicate with people with normal hearing. Third, there should be practical approaches to enable them to get recognition and support from their families and share love with them. Finally, there should be practical policy approaches to help people with normal hearing understand the culture of deaf elderly and assist the deaf elderly to receive supports from the community and live with others within the community.