• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.677-680
• /
• 2005

다국어 입력기에서 한글 입력의 최적화를 위하여 문자별 보편성과 개별성을 밝혀내어서 어떤 문자의 개별성이 다른 문자의 보편성을 헤치지 않도록 충돌 요인을 최대한 낮추어야 한다. 특히 한글은 표음 문자로서 음절 및 음소문자의 특성을 가지고 있고, 한글전용을 하고 있다. 반면에 일본어와 중국어는 음절문자에 해당하며 가나 또는 병음을 입력하여 마지막에는 한자로 바꾸어야 한다. 여기서 훈민정음창제원리를 기본으로 삼아 최적화에 적용하고자 한다.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.117-122
• /
• 2009

We developed a multi-lingual namecard recognizer for building up a global client management systems. At first, we created the Unicode-based character image database for character recognition and learning of multi languages, and applied many color image processing techniques to get more correct data for namecard images which were acquired by various input devices. And by applying multi-layer perceptron neural network, individual character recognition applied for language types, and post-processing utilizing keyword databases made for individual languages, we increased a recognition rate for multi-lingual namecards.

• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.145-153
• /
• 2007

Recently, development in information technology is mainly focused on mobile service, and most of mobile users are using various services based on wireless network. So the importance of system software or middleware, which enables such mobile services, is growing bigger and bigger, and one of those is character input/output system. This paper will introduce an alphabet input system, which decomposes a character to a series of strokes, by its formation principal. It is designed to make a person, who knows the character, to input characters in the way that he/she is actually writing down the character.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.4
• /
• pp.155-162
• /
• 2014

In this study, we developed a server-based mobile multi-lingual name-card recognition system which utilizes smartphone only as a terminal for capturing images of name-card and displaying results of recognition, running server as a recognizer of characters. For efficient processing and transmission of captured images, we corrected the distorted images, removed noises from them, and defined the socket-based protocol for wireless transmission of images between smartphone and the recognizer on server. Various tests for name-cards of five language types show increased recognition rate and speed of the developed system against conventional smartphone-based recognizers.

• Review of Korea Contents Association
• /
• v.2 no.1
• /
• pp.50-62
• /
• 2004

국제적인 규모의 많은 행사, 그리고 전반적인 생활수준의 향상으로 인해 외국을 방문하는 관광객의 수는 비약적으로 늘어났다. 또한 전 세계적인 네트 인프라의 발달로 인해 해외여행 중 어디에서나 인터넷을 쉽게 접할 수 있게 되었다. 그러나, 발달된 컴퓨팅 환경 속에서도 각 나라 별로 쉽게 문서를 작성하는 데는 아직 많은 어려움이 존재한다. 자국어를 포함한 한 두개의 외국어를 이용하여 콘텐츠를 작성하는 것은 어느 정도 가능하다 할지라도 그 숫자가 두세개 이상인 경우는 콘텐츠 작성에 많은 어려움이 존재한다.(중략)한다.(중략)

• Journal of Korea Game Society
• /
• v.7 no.2
• /
• pp.83-90
• /
• 2007

One result of the trend towards globalization is an increased number of projects that focus on natural language processing. Automatic speech recognition (ASR) technologies, for example, hold great promise in facilitating global communications and collaborations. Unfortunately, to date, most research projects focus on single widely spoken languages. Therefore, the cost to adapt a particular ASR tool for use with other languages is often prohibitive. This work takes a more general approach. We propose an International Phoneticizing Engine (IPE) that interprets input files supplied in our Phonetic Language Identity (PLI) format to build a dictionary. IPE is language independent and rule based. It operates by decomposing the dictionary creation process into a set of well-defined steps. These steps reduce rule conflicts, allow for rule creation by people without linguistics training, and optimize run-time efficiency. Dictionaries created by the IPE can be used with the speech recognition system. IPE defines an easy-to-use systematic approach that can obtained 92.55% for the recognition rate of Korean speech and 89.93% for English.