• Title/Summary/Keyword: Korean Sign Language

Search Result 159, Processing Time 0.025 seconds

A Design of Sign Language-Text Translation System Using Deep Learning Vedio Recognition (딥러닝 영상인식을 이용한 수화-텍스트 번역 시스템 설계)

  • Lee, JongMyeong;Kim, Kang-Gyoo;Yoo, Seoyeon;Lee, SeungGeon;Chun, Seunghyun;Beak, JeongYoon;Ha, Ok-Kyoon
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2022.07a
    • /
    • pp.475-476
    • /
    • 2022
  • 본 논문에서는 청각장애인의 사회참여성 증진 및 사회적 차별감소를 목적으로 딥러닝 영상인식 기반으로 MediaPipe 기술을 활용한 수화-텍스트 번역시스템을 설계한다. 제시하는 시스템은 실시간으로 수집된 수화 사용자의 영상정보를 통해 동작과 표정을 인식하여 텍스트로 번역함으로써 장애인과 비장애인의 원활한 의사소통 서비스를 제공하는 것을 주 목적으로한다. 향후 개선된 수화 인식 및 문장 조합을 통해 일상에서 청각장애인과 일반인의 자유로운 커뮤니케이션을 제공하는 서비스로 확장하고자한다.

  • PDF

Beyond Alan Colquhoun's Architectural Hermeneutics of Tradition - from 'conceptural displacement of the past' to 'the reactivation of the past'- (앨런 코쿤(Ahin Colquhoun)의 전통건축 해석학을 넘어서 -'과거를 개념으로 대체(displacement)하기'에서 '과거를 재활성화(reactivation) 하기'로-)

  • Lee, Dong-Eon
    • Journal of architectural history
    • /
    • v.7 no.4 s.17
    • /
    • pp.49-60
    • /
    • 1998
  • The first aim of this paper is to investigate and analyze Alan Colquhoun's architectural hermeneutics of tradition, 'conceptual displacement of the past.' The second aim is to overcome the limit of it, and to suggest new architectural hermeneutics of tradition, 'the reactivation of the past.' The architectural work is reduced by Colquhoun to typology or arbitrary language because he believes that without arbitrary language natural language is not able to work effectively. However, he ignores that two languages cannot be separable. When they are separated the key to natural language is understood to be an unverifiable similarity between a sense perception and its correspondence in the architectural object, while the key to arbitrary language becomes mere artificial agreement on the value and function of the linguistic sign. Therefore, natural language is appropriate only when it permits spontaneous combinations of sensory data within complex structures which emerge from, and support, complex human interaction and communication(the shining of the world and of the possibility of creative being in each individual thing). Only when architecture is translated into this kind of language, can it reactivate the world's past, and become poetic.

  • PDF

Detecting and Resolving Syntactic Ambiguity for Automatic Korean-Korean Sign Language Translation (한국어-수화 자동 변환 과정에서 발생하는 통사적 중의성 파악 및 해소)

  • Chung, Jin-Woo;Park, Jong C.
    • Annual Conference on Human and Language Technology
    • /
    • 2010.10a
    • /
    • pp.55-62
    • /
    • 2010
  • 수화는 농인 사회에서 주로 사용되는 시각언어로서 음성언어인 한국어와 통사적인 측면에서 많은 차이를 보인다. 특히 수화에서는 조사와 어미가 거의 사용되지 않기 때문에 한국어 문장에서 기존의 방법대로 이들을 제거한 후 어순을 고려하지 않은 채 문장 성분의 기본형을 그대로 나열하여 수화문을 생성할 경우 문장 성분 간의 통사적 관계가 애매해질 수 있다. 본 논문에서는 통사적 중의성이 한국어 문장을 수화문으로 변환하는 과정에서 추가적으로 나타나게 되는 특정 통사구조에 의해 발생하는 것으로 보고, 이러한 통사구조를 기본논항구조, 한정수식구조, 병렬구조, 서술구조로 분류하여 각각을 파악하고 그에 따라 통사적 중의성을 해소하는 방법을 제시한다.

  • PDF

Analysis and Computational Processing of Sentences in Korean for Automatic Sign Language Generation (수화 자동 생성을 위한 한국어 문장 분석과 처리)

  • Choi, Ji-Won;Park, Jong-Chul
    • Annual Conference on Human and Language Technology
    • /
    • 2003.10d
    • /
    • pp.219-226
    • /
    • 2003
  • 한국 수화는 한국어에 대한 기본적인 유사성을 가지고 있지만, 교착어이자 청각-음성 체계 언어인 한국어와는 달리 고립어이자 시각-운동 체계 언어로서의 특성을 동시에 나타내고 있다. 그러므로 텍스트 형태의 한국어 문장으로부터 수화를 자동 생성하기 위해서는 한국어를 위해 미리 정의된 문법에 수화 표현을 무리하게 연계시키려고 하기 보다, 수화 고유의 의미 전달 체계를 분석하고 활용하여야 할 필요가 있다. 본 논문에서는 수화 표현상의 언어학적 특징을 재현 생략 변형 이동의 네 가지로 구분하여 분석하고 결합범주문법을 이용한 이 같은 형상의 처리 방법 및 구현 방안에 대하여 논의한다.

  • PDF

XML-based Single Sign-On Scheme for Internet Protocol TV(IPTV)Services (IPTV 서비스 제공을 위한 XML 기반의 단일인증 구조)

  • Lee, Seung-Hun;Shin, Dong-Il;Shin, Dong-Kyoo
    • Journal of Broadcast Engineering
    • /
    • v.14 no.4
    • /
    • pp.463-474
    • /
    • 2009
  • By employing the subscriber concept in broadcasting services, IPTV (Internet Protocol Television) operators provide various grades of services to subscribers based on the billing level of the subscribers. With the income from subscribers for a basis, IPTV operators plan to provide high quality services. Since Web browser-based IPTV provides T-commerce and E-commerce services as well as television services, users may frequently visit other service domains to buy goods or content. To provide the user with charged or private services, these service domains request authentication of user. The existing authentication system is not appropriate for the IPTV service environment because the environment unavoidably forces the user to cross from one authentication-based service domain to another. Single sign-on provides a user with transparent authentication services by enabling an authenticated user to move between authentication-based service domains without any re-authentication. Like this distributed environment, since the IPTV service environment also provides a variety of authentication-based services, transparent authentication service needs to be provided to subscribers who want to access charged or private services. In this paper, we propose a new user authentication scheme for the IPTV environment. This scheme integrates the Security Assertion Markup Language (SAML), which is a standard for XML-based single sign on. We validate this scheme using a simple use case scenario.

Legibility & Recognition of Signs for Train Station (철도역 사인의 가독성과 픽토그램의 인지성 증대에 관한 연구)

  • 한석우;진미자
    • Journal of the Korean Society for Railway
    • /
    • v.6 no.1
    • /
    • pp.66-72
    • /
    • 2003
  • Railway sign(graphic sign, diagraphics) designs require good recognition with universality to transmit accurate and speedy information as they connect people around the station and other transport systems. An important point of signs is how to design and deliver the contents to the viewers as a communication service tools. It needs to establish design guidelines with standardization and unified system to show their contents and images clearly like common language with visuality, attractivity and generality. These requisites are important for both aesthetics legibility and unified standards to maximize the effectiveness of pictograms for the use of the general public, who require systematic suggestion and management.

Legibility & Recognition of Signs for Train Station (철도역을 위한 사인의 가독성과 픽토그램의 의미작용에 관한 연구)

  • Han Suk-Woo;Jin Mi-Ja
    • Proceedings of the KSR Conference
    • /
    • 2003.05a
    • /
    • pp.176-184
    • /
    • 2003
  • Railway sign(graphic sign, diagraphics) designs require good recognition with universality to transmit accurate and speedy information as they connect people around the station and other transport systems. An important point of signs is how to design and deliver the contents to the viewers as a communication service tools. It needs to establish design guidelines with standardization and unified system to show their contents and images clearly like common language with visuality, attractivity and generality. These requisites are important for both aesthetics legibility and unified standards to maximize the effectiveness of pictograms for the use of the general public, who require systematic suggestion and management.

  • PDF

A Field Research on Multi-Language Sign System in Hospital at the Point of View in Convergent Study - Focused on General Hospital in Busan and South Gyeongsang Province - (융합적 관점에서 본 병원 사인시스템 다중언어 표기 현황 조사 - 부산 및 경남지역 의료기관을 중심으로 -)

  • Park, Han Na;Paik, Jin Kyung
    • Korea Science and Art Forum
    • /
    • v.37 no.1
    • /
    • pp.87-97
    • /
    • 2019
  • The study began in recent years with the aim of grasping the nation's medical status following the fast-growing trend of international medical tourism and attracting foreign patients, among other things, Busan, which ranks second in attracting foreign patients after the nation's capital, Seoul, has been highly active in the past eight years, with foreign patients rising by about 426 percent, and Russian patients entering the sea. In addition, Gimhae and Changwon, the Busan-based Gyeongsangnam-do region, ranked first and second in number of foreign residents, and are inhabited by a variety of foreign workers. Medical institutions, such as hospitals, should be able to find directions within hospitals. It is also a space where information in various languages, including Korean, English, Chinese, or Russian, must be delivered in a single medium. Based on this research, the purpose of this research is to provide converged information that helps foreigners who are not familiar with Korean language easily understand the proposed recognition system when visiting hospitals. Therefore, this paper is applied to a multi-language survey of six medical institutions (A, B, C, D, E, F) at the university hospital in Busan, and 10 medical institutions (R, J) in Gimhae, South Gyeongsang Province with high foreign residents. Research results and contents are as follows. First, the results of analyzing the design of the sinusoidal system show that the font uses colorless Gothic fonts, arrows, and pictograms to introduce the design of a typical hospital sign system. Second, the results of the multi-lingual situation were found to have only two languages in the system, such as Korean and English, and to have four languages, including Korean, English, Chinese, and Russian, according to their geographical location. However, it was judged that most medical institutions currently have only two languages (Korean, English) that may cause some discomfort in terms of language for foreign patients in non-English speaking countries. Based on these findings, it is necessary to propose designs that are considered by Koreans as well as foreign users in the use of multilingual hospital sign systems.

The Extraction of the Shape of Hands in the Sign Language Sequence by using MRF Model (MRF를 이용한 수화 동영상에서의 효율적인 손 형상 추출)

  • 송효섭;양윤모
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2000.10b
    • /
    • pp.395-397
    • /
    • 2000
  • 영상 처리를 통한 수화(手話)의 인식에 있어 가장 중요한 정보는 손의 형상, 위치, 이동방향 등을 들 수 있다. 이 중 손의 형상은 세가지 정보 중 가장 중요하며, 실제로 자음과 모음, 숫자 등을 나타내는 지문자의 경우 손의 형상만으로도 인식될 수 있다. 본 논문에서는 선 처리 모델(Line Process Model)을 3차원으로 확장하여 적용한 Markov Random Field(MRF)를 사용하여 효율적으로 손의 형상을 추출하였다.

  • PDF