• 대한전자공학회논문지SP
• /
• 제41권6호
• /
• pp.155-164
• /
• 2004

최근 지능형 로봇에 대한 관심이 모아지고 있다. 지능형 로봇의 가장 큰 특징은 사용자를 추적, 인식하고 그 결과를 기반으로 상호활동적인 대응을 할 수 있다는 점이다. 얼굴인식이 다른 생채인식과의 비교에서 장점을 가질 수 있는 점은 비 강제성과 비 접촉성을 들 수 있다. 그러나 얼굴인식은 얼굴 취득단계부터 차원의 감소가 발생하고 인식하고자 하는 얼굴 및 주변 환경 변화가 매우 심하기 때문에 다른 생체인식에 비하여 인식률이 낮다. 얼굴인식의 성능을 저하시키는 요인들로는 조명변화, 포즈변화, 표정변화, 카메라와의 거리 등을 들 수 있다. 본 논문에서는 실제 환경에서 얼굴 인식 성능에 가장 많은 영향을 미치는 포즈변화에 대응하기 위하여 새로운 선형이동 능동형 카메라를 개발하여, 정면 얼굴에 근접한 영상을 취득하고 주성분 분석 및 Hidden Markov Model 알고리듬을 이용하여 인식률을 개선하고자 한다. 제한된 방법은 지능형 보안시스템 및 모바일 로봇에 적용하는 것을 목표로 개발 되었지만, 높은 정확도의 얼굴인식을 요구하는 응용분야에 널리 적용할 수가 있다.

• ETRI Journal
• /
• 제29권3호
• /
• pp.399-401
• /
• 2007

With a growing emphasis on human identification, iris recognition has recently received increasing attention. Iris recognition includes eye imaging, iris segmentation, verification, and so on. In this letter, we propose a novel and efficient iris recognition method which employs a cumulative-sum-based grey change analysis. Experimental results demonstrate that the proposed method can be used for human identification in efficient manner.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2263-2266
• /
• 2003

Three-dimensional face recognition algorithm using curvature information representing characteristics of surface form is suggested. The experiment showed more than 90 percent of recognition for the noses which had definite change value of data, and contained much information about surface curvature. Recognition ratio using a contour taken from the remaining part other than the eyes, noses, mouths which are the main components of faces showed the important role, which could be used as the important index information in the three-dimensional face recognition.

• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.174-182
• /
• 1996

In continuous speech recognition system, it is possible to implement the system which can handle unlimited number of words by using limited number of phonetic units such as phonemes. Dividing continuous speech into the string of tems of phonemes prior to recognition process can lower the complexity of the system. But because of the coarticulations between neiboring phonemes, it is very difficult ot extract exactly their boundaries. In this paper, we propose the algorithm ot extract short terms which can represent each phonemes instead of extracting their boundaries. The short terms of lower spectral change and higher spectral chang eare detcted. Then phoneme changes are detected using distance measure with this lower spectral change terms, and hgher spectral change terms are regarded as transition terms or short phoneme terms. Finally lower spectral change terms and the mid-term of higher spectral change terms are regarded s the represent each phonemes. The cepstral coefficients and weighted cepstral distance are used for speech feature and measuring the distance because of less computational complexity, and the speech data used in this experimetn was recoreded at silent and ordinary in-dorr environment. Through the experimental results, the proposed algorithm showed higher performance with less computational complexity comparing with the conventional segmetnation algorithms and it can be applied usefully in phoneme-based continuous speech recognition.

• 한국환경교육학회지:환경교육
• /
• 제22권2호
• /
• pp.56-78
• /
• 2009

Currently, climate change is regarded as one of the most important environmental issues in the 21st century. However, climate change education is not seriously carried out in schools. This study is concerned about enhancing students' recognition about climate change and actions responding to climate change through an history discipline. More specifically, this study tried to identify the effect of history lessons on environmental education, especially focused on climate change, by performing an experiment. The experiment was designed based on Solomon four-group design and carried out in one high school in Gwangmyeong city. Findings of the experiment are as follows. First, students who had taken the reorganized history lesson based on climate change - that is, students with experimental treatments - gained higher understanding of climate change than before and students of control groups. Second, students with experimental treatments gained higher understanding about relationship between history and climate change. Third, students with experimental treatments showed higher possibility of taking responding actions to climate change. In conclusion, history lessons reorganized with environmental issues, for instance climate change, have big potential for environmental education since they contribute to enhancing environmental recognition and prompting responding actions through exploration the effects of existing historical facts. Interdisciplinary approach like that taken in this study will provide students with more comprehensive and extended prism for the environment.

• 대한음성학회지:말소리
• /
• 제51호
• /
• pp.1-16
• /
• 2004

The aim of this paper is to analyze vowels in voice imitation and disguised voice, and to find the invariable phonetic features of the speaker. In this paper we examined the formants of monophthongs /a, u, i, o, {$\omega},{\;}{\varepsilon},{\;}{\Lambda}$/. The results of the present are as follows : $\circled1$ Speakers change their vocal tract features. $\circled2$ Vowels /a, ${\varepsilon}$, i/ appear to be proper for speaker recognition since they show invariable acoustic feature during voice modulation. $\circled3$ F1 does not change easily compared to higher formants. $\circled4$ F3-F2 appears to be constituent for a speaker identification in vowel /a/ and /$\varepsilon$/, and F4-F2 in vowel /i/. $\circled5$ Resulting of F-ratio, differences of each formants were more useful than individual formant of a vowel to speaker recognition.

• 센서학회지
• /
• 제16권6호
• /
• pp.467-474
• /
• 2007

The real-time monitoring about the activity of the human provides useful information about the activity quantity and ability. The present study implemented a small-size and low-power acceleration monitoring system for convenient monitoring of activity quantity and recognition of emergent situations such as falling during daily life. For the wireless transmission of acceleration sensor signal, we developed a wireless transmission system based on a wireless sensor network. In addition, we developed a program for storing and monitoring wirelessly transmitted signals on PC in real-time. The performance of the implemented system was evaluated by assessing the output characteristic of the system according to the change of posture, and parameters and acontext recognition algorithm were developed in order to monitor activity volume during daily life and to recognize emergent situations such as falling. In particular, recognition error in the sudden change of acceleration was minimized by the application of a falling correction algorithm

• 패션비즈니스
• /
• 제21권3호
• /
• pp.14-28
• /
• 2017

This purpose of this study to analyze effect material properties have on change in QR code recognition rate according to change of materials by comparing recognition rate of color QR code. QR code applied to textile materials has the advantage of being washable and being applicable to lost child prevention goods or clothes or a person with dementia through record of information relating to the material or input of additional information, differently from QR code printed on the conventional paper. An effective method of entering QR code in textile materials is Digital Textile Printing(DTP), that facilitates printing by rapidly applying diverse information, and small quantity production. It is possible to tailor various QR codes according to use. Regarding samples to use, cotton material used in clothing products and Tyvek material recently applied to clothing and related products were selected. Reactive dyes were used for cotton, pigment was used for Tyvek, and QR code was printed with an inkjet printer by direct printing method. Printing methods and surface textures are different between cotton and Tyvek. It was revealed that consequent print results and results of recognition rate were different. Regarding color to be printed, 2015 S/S - 2017 S/S color presented by Pantone was used. Color combination affected recognition rate of color QR code. Understanding color combination, material properties and print characteristics may be helpful in increasing recognition rate of color QR code, and may contribute to usability of color QR code applied to textile materials in the future.

• 한국과학교육학회지
• /
• 제38권6호
• /
• pp.901-917
• /
• 2018

본 연구는 초등예비교사들을 대상으로 과학교육 관련 자기이해와 변화역량에 대한 인식 조사 도구를 개발하고, 이를 활용하여 초등예비교사들이 가지고 있는 자기이해와 자신의 변화역량에 대한 인식을 조사하는 것을 목적으로 하였다. 먼저 선행 연구 검토와 토론 등을 거쳐 초등예비교사들의 자기이해와 변화역량에 대한 인식 조사 도구를 제작하였다. 설문지의 전반부는 자기이해와 관련되는데 '자기개념 명료성', '진로정체성', '자기효능감'을 요인으로 하여, '초등예비교사로서의 자기이해'(12개 문항)와 '초등과학예비교사로서의 자기이해'(12개 문항)에 대한 내용으로 구성하였다. 설문지의 후반부는 '변화감수성', '목표의식', '협력', '성찰', '숙달'을 요인으로 하는 변화역량에 관한 내용으로, '일반적인 변화역량'(17개 문항)과 '초등예비교사로서의 변화역량'(17개 문항), '초등과학예비교사로서의 변화역량'(17개 문항)에 대하여 각각 인식 조사 문항을 작성하였다. 이 조사 도구를 사용하여 153명의 초등예비교사들을 대상으로 자기이해와 변화역량에 대한 인식을 조사한 결과는 다음과 같다. 첫째, 초등예비교사들은 자기이해와 변화역량에 대해 대체로 긍정적인 인식을 가지고 있었지만 초등과학예비교사로서의 자기이해와 변화역량에 대한 인식은 상대적으로 덜 긍정적이었다. 둘째, 초등과학예비교사로서의 자기 이해와 변화역량 요인들은 대체로 유의미한 상관을 가지고 있었으며, 특히 자기이해의 '자기효능감'과 변화역량의 '목표의식', '숙달' 사이에 높은 상관이 있었다. 이러한 결과를 바탕으로 자기이해와 변화역량 관련 과학 교육을 위한 몇 가지 시사점에 대해 논의하였다.

• 전자공학회논문지CI
• /
• 제41권6호
• /
• pp.81-89
• /
• 2004

본 논문에서는 스테레오 영상에서 좌·우측 영상을 입력 받아 거리변화와 임베디드 데이터를 이용해 얼굴인식률을 PCA알고리듬으로 비교한다. 제안된 방법에서는 RGB컬러공간에서 YCbCr컬러공간으로 변환하여 얼굴영역을 검출한다. 또한 거리변화에 따라 추출된 얼굴영상의 확대 및 축소하여 보다 강건한 얼굴영역을 추출한다. 실험을 통하여 제안된 방법은 30cm∼200cm 정도의 거리에서 기준 거리(100cm)를 설정하고, 스케일 변화에 따른 평균적인 인식결과로 99.05%(100cm)의 인식률을 얻을 수 있었다. 정규화된 크기(92×112)에서 특정영역인 슈퍼 상태를 정의하고, 각각 정의된 슈퍼 상태의 내부요소인 임베디드 데이터만을 추출하여 PCA 알고리듬을 통하여 얼굴인식을 수행하였다. 원본영상을 모두 학습하는 것이 아니라 임베디드 데이터만을 학습시키기 때문에 제한된 영상의 크기(92×112)에서 특정 데이터를 받아들일 수 있으며, 평균적으로 92×112크기의 영상에서는 99.05%, 실험1은 99.05%, 실험2는 98.93%, 실험3은 98.54%, 실험4는 97.85%의 얼굴인식률을 보였다. 따라서 실험을 통하여 제안된 방법은 거리변화율을 적용하면 높은 인식률을 얻을 수 있음을 보였으며, 얼굴정보를 축소할 뿐만 아니라 처리속도도 향상되었다.