• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.671-674
• /
• 1999

We report the new method for speaker recognition. Until now, many researchers have used HMM (Hidden Markov Model) with cepstral coefficient or neural network for speaker recognition. Here, we introduce the method of speaker recognition using eigenspace. This method can reduce the training and recognition time of speaker recognition system. In proposed method, we use the low rank model of the speech eigenspace. In experiment, we obtain good recognition result.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.55.3-55
• /
• 2001

The implementation of human-like robot has been advanced in various parts such as mechanic arms, legs, and applications of five senses. The vision applications have been developed in several decades and especially the face recognition have become a prominent issue. In addition, the development of computer systems makes it possible to process complex algorithms in realtime. The most of human recognition systems adopt the discerning method using fingerprint, iris, and etc. These methods restrict the motion of the person to be discriminated. Recently, the researchers of human recognition systems are interested in facial recognition by using machine vision. Thus, the object of this paper is the implementation of the realtime ...

• 한국공작기계학회논문집
• /
• 제12권2호
• /
• pp.65-70
• /
• 2003

In this study, researchers developed the estimative algorithm for artificial defect in semiconductor packages and performed it by pattern recognition technology. For this purpose, the estimative algorithm was included that researchers made software with MATLAB. The software consists of some procedures including ultrasonic image acquisition, equalization filtering, Self-Organizing Map and Backpropagation Neural Network. Self-organizing Map and Backpropagation Neural Network are belong to methods of Neural Networks. And the pattern recognition technology has applied to classify three kinds of detective patterns in semiconductor packages : Crack, Delamination and Normal. According to the results, we were confirmed that estimative algerian was provided the recognition rates of 75.7% (for Crack) and 83.4% (for Delamination) and 87.2 % (for Normal).

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2005년도 춘계학술대회 논문집
• /
• pp.91-96
• /
• 2005

In this study, researchers developed the estimative algorithm for artificial defects in semiconductor packages and performed it by pattern recognition technology. For this purpose, the estimative algorithm was included that researchers made software with MATLAB. The software consists of some procedures including ultrasonic image acquisition, equalization filtering, Self-Organizing Map and Backpropagation Neural Network. Self-Organizing Map and Backpropagation Neural Network are belong to methods of Neural Networks. And the pattern recognition technology has applied to classify three kinds of detective patterns in semiconductor packages: Crack, Delamination and Normal. According to the results, we were confirmed that estimative algorithm was provided the recognition rates of $75.7\%$ (for Crack) and $83_4\%$ (for Delamination) and $87.2\%$ (for Normal).

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.25-28
• /
• 2002

This paper introduce a personalized facial expression recognition system. Many previous works on facial expression recognition system focus on the formal six universal facial expressions. However, it is very difficult to make such expressions for normal person without much effort and training. And in these days, the personalized service is also mainly focused by many researchers in various fields. Thus, we Propose a novel facial expression recognition system with fuzzy neural networks and robust image processing.

• 대한음성학회지:말소리
• /
• 제51호
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.

• 사상체질의학회지
• /
• 제23권4호
• /
• pp.514-525
• /
• 2011

1. Objectives This study aims to find out identify the recognition and attitude about the research ethic among Constitutional medicine researchers. 2. Methods This survey was conducted to the 37 researchers who were currently participating in Korea Constitution Multicenter Study guided by Korea institute of Oriental medicine(KIOM). The survey consist of 4 parts that level of acknowledgment about the systems and laws on clinical research ethic, clinical research experiences and education, the level of acknowledgment about Institutional Review Board(IRB) and the recognition about overall research ethic. 3. Results Thirty one questionnaires were collected. Most researchers had low level of acknowledgment about the guidelines of basic research ethic. It was proved that more than 65% of the respondents have never received education for clinical research ethic. Moreover, 70% of them felt the need for education of clinical research ethic. In addition, most of the respondents recognized the fact that IRB is responsible for ethically implementing clinical research. 39% of the researchers thought that they themselves have a firm ethical viewpoint, while the rest of the group showed somewhat difficulty on their own ethical implementation of clinical research. 4. Conclusions Most of researcher had partial awareness of regulations and laws on clinical research ethic. And Educational needs of research ethic was high. Therefore education and Public Relations need to be done to extend research ethic. Moreover, standardized course of education on research ethic should be developed and activated.

• 한국지능시스템학회논문지
• /
• 제17권3호
• /
• pp.322-327
• /
• 2007

심리학 분야의 연구자들은 Electroencephalographic(EEG)을 오래전부터 인간 두뇌의 활동을 측정 기록하는데 사용하였다. 과학이 발달함에 따라 점차적으로 인간의 두뇌에서 감정을 조절하는 기본적인 영역들이 밝혀지고 있다. 그래서 인간의 감정을 조절하는 인간의 두뇌 활동 영역들을 EEG를 이용하여 측정하였다. 손짓이나 고개의 움직임은 사람들 사이에 대화를 위한 인간의 몸 언어로 사용된다. 그리고 그것들의 인식은 컴퓨터와 인간 사이에 유용한 회화수단으로 매우 중요하다. 몸짓에 관한 연구들은 주로 영상을 통한 인식 방법이 주를 이루고 있다. 많은 연구자들의 기존 연구에서는 생체신호나 몸짓중 한 가지만을 이용하여 감정인식 방법 연구를 하였다. 본 논문에서는 EEG 신호와 몸짓을 같이 사용해서 사람의 감정을 인식하였다. 그리고 인식의 대상자를 운전자라는 특정 대상자를 설정하고 실험을 하였다. 실험 결과 생체신호와 몸짓을 같이 사용한 실점의 인식률이 둘 중 한 가지만을 사용한 것보다 높은 인식률을 보였다. 생체신호와 몸짓들의 특징 신호들은 강화학습의 개념을 이용한 IFS(Interactive Feature Selection)를 이용하여 특징 선택을 하였다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 한국지능시스템학회논문지
• /
• 제16권6호
• /
• pp.772-776
• /
• 2006

얼굴 표정인식에 관한 연구는 대부분 얼굴의 정면 화상을 가지고 연구를 한다. 얼굴 표정인식에 큰 영향을 미치는 대표적인 부위는 눈과 입이다. 그래서 표정 인식 연구자들은 눈, 눈썹, 입을 중심으로 표정 인식이나 표현 연구를 해왔다. 그러나 일상생활에서 카메라 앞에서는 대부분의 사람들은 눈동자의 빠른 변화의 인지가 어렵다. 또한 많은 사람들이 안경을 쓰고 있다. 그래서 본 연구에서는 눈이 가려진 경우의 표정 인식을 Principal Component Analysis (PCA)를 이용하여 시도하였다.