http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Steganography based Multi-modal Biometrics System
Go, Hyoun-Joo,Chun, Myung-Geun Korean Institute of Intelligent Systems 2007 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.7 No.2
This paper deals with implementing a steganography based multi-modal biometric system. For this purpose, we construct a multi-biometrics system based on the face and iris recognition. Here, the feature vector of iris pattern is hidden in the face image. The recognition system is designed by the fuzzy-based Linear Discriminant Analysis(LDA), which is an expanded approach of the LDA method combined by the theory of fuzzy sets. Furthermore, we present a watermarking method that can embed iris information into face images. Finally, we show the advantages of the proposed watermarking scheme by computing the ROC curves and make some comparisons recognition rates of watermarked face images with those of original ones. From various experiments, we found that our proposed scheme could be used for establishing efficient and secure multi-modal biometric systems.
A Multimodal Emotion Recognition Using the Facial Image and Speech Signal
Hyoun-Joo Go,Yong-Tae Kim,Myung-Geun Chun 한국지능시스템학회 2005 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.5 No.1
In this paper, we propose an emotion recognition method using the facial images and speech signals. Six basic emotions including happiness, sadness, anger, surprise, fear and dislike are investigated. Facial expression recognition is performed by using the multi-resolution analysis based on the discrete wavelet. Here, we obtain the feature vectors through the ICA(Independent Component Analysis). On the other hand, the emotion recognition from the speech signal method has a structure of performing the recognition algorithm independently for each wavelet subband and the final recognition is obtained from the multi-decision making scheme. After merging the facial and speech emotion recognition results, we obtained better performance than previous ones.
A Multimodal Emotion Recognition Using the Facial Image and Speech Signal
Go, Hyoun-Joo,Kim, Yong-Tae,Chun, Myung-Geun Korean Institute of Intelligent Systems 2005 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.5 No.1
In this paper, we propose an emotion recognition method using the facial images and speech signals. Six basic emotions including happiness, sadness, anger, surprise, fear and dislike are investigated. Facia] expression recognition is performed by using the multi-resolution analysis based on the discrete wavelet. Here, we obtain the feature vectors through the ICA(Independent Component Analysis). On the other hand, the emotion recognition from the speech signal method has a structure of performing the recognition algorithm independently for each wavelet subband and the final recognition is obtained from the multi-decision making scheme. After merging the facial and speech emotion recognition results, we obtained better performance than previous ones.
Steganography based Multi-modal Biometrics System
Hyoun-Joo Go,Dae-sung Moon,Ki-young Moon,Myung-Geun Chun 한국지능시스템학회 2007 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.7 No.1
This paper deals with implementing a steganography based multi-modal biometric system. For this purpose, we construct a multi-biometrics system based on the face and iris recognition. Here, the feature vector of iris pattern is hidden in the face image. The recognition system is designed by the fuzzy-based Linear Discriminant Analysis(LDA), which is an expanded approach of the LDA method combined by the theory of fuzzy sets. Furthermore, we present a watermarking method that can embed iris information into face images. Finally, we show the advantages of the proposed watermarking scheme by computing the ROC curves and make some comparisons recognition rates of watermarked face images with those of original ones. From various experiments, we found that our proposed scheme could be used for establishing efficient and secure multi-modal biometric systems.
Steganography based Multi-modal Biometrics System
Go, Hyoun-Joo,Moon, Dae-Sung,Moon, Ki-Young,Chun, Myung-Geun Korean Institute of Intelligent Systems 2007 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.7 No.1
This paper deals with implementing a steganography based multi-modal biometric system. For this purpose, we construct a multi-biometrics system based on the face and iris recognition. Here, the feature vector of iris pattern is hidden in the face image. The recognition system is designed by the fuzzy-based Linear Discriminant Analysis(LDA), which is an expanded approach of the LDA method combined by the theory of fuzzy sets. Furthermore, we present a watermarking method that can embed iris information into face images. Finally, we show the advantages of the proposed watermarking scheme by computing the ROC curves and make some comparisons recognition rates of watermarked face images with those of original ones. From various experiments, we found that our proposed scheme could be used for establishing efficient and secure multi-modal biometric systems.
Steganography based Multi-modal Biometrics System
Hyoun-Joo Go,Myung-Geun Chun 한국지능시스템학회 2007 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.7 No.2
This paper deals with implementing a steganography based multi-modal biometric system. For this purpose, we construct a multi-biometrics system based on the face and iris recognition. Here, the feature vector of iris pattern is hidden in the face image. The recognition system is designed by the fuzzy-based Linear Discriminant Analysis(LDA), which is an expanded approach of the LDA method combined by the theory of fuzzy sets. Furthermore, we present a watermarking method that can embed iris information into face images. Finally, we show the advantages of the proposed watermarking scheme by computing the ROC curves and make some comparisons recognition rates of watermarked face images with those of original ones. From various experiments, we found that our proposed scheme could be used for establishing efficient and secure multi-modal biometric systems.
Gabor Wavelet과 Fuzzy LDA을 이용한 홍채인식
고현주 ( Hyoun-joo Go ),유병진 ( Byoung-jin You ),전명근 ( Myung-geun Chun ) 한국정보처리학회 2005 한국정보처리학회 학술대회논문집 Vol.12 No.1
사람의 홍채는 태어날 때 한번 정해지면 평생 변화하지 않는 특성을 가지고 있으며, 개개인별로 모양이 모두 다른 것으로 알려져 있다. 이에, 본 논문에서는 홍채영상 취득시 조명에 의한 동공의 크기 변화에 민감하지 않은 2차원의 홍채패턴을 취득하여, 2D Gabor Wavelet과 Fuzzy LDA를 이용하여 특징 벡터를 추출한다. 인식과정에서는 correlation 계수를 이용하여 서로 다른 홍채의 특징 값에 대해 유사도를 측정하고 유사도가 가장 큰 대상을 찾게 된다. 이때, 4개 방향의 Gabor Wavelet을 거쳐 얻어진 영상에 대해 최고의 값을 인식 대상자로 인정하므로 오 인식 될 확률을 최소화 할 수 있다. 제안한 알고리듬의 유용성을 확인하기 위해 대상자 50명에 대하여 각각 6회씩 촬영한 두 가지 데이터베이스(CASIA, CBNU)를 이용하였으며, 실험 결과 90% 이상의 높은 인식률을 얻었다.
균등화 및 분류기에 따른 다중 생체 인식 시스템의 성능 평가
고현주(Hyoun-Joo Go),우나영(Na-Young Woo),신용녀(Yong-Nyuo Shin),김재성(Jae-Sung Kim),김학일(Hak-Il Kim),전명근(Myung-Geun Chun) 한국정보과학회 2007 정보과학회논문지 : 소프트웨어 및 응용 Vol.34 No.4
본 연구는 다중 생체 인식 기법을 이용하여 개인 확인 및 인증을 구현한 것으로, 단일생체인식에서 많이 사용되어 지고 있는 생체 정보 중 얼굴과 지문, 홍채를 이용하여 상호 비교하고 구현하였다. 이를 위한 결합방식으로 단일 생체인식에서 얻은 유사도를 이용하는 방식인 유사도 단계에서의 결합방식을 적용하였으며, 이때의 각 유사도가 동일한 범위가 되도록 하는 여러 가지 균등화 방법에 대하여 연구하였다. 결합방법으로는 가중치 합, Support Vector Machine, Fisher 분류기, 베이시안 분류기를 사용하여 비교하였다. 다양한 실험결과, 사용되는 다중생체인식 조합에 따라 우수한 성능을 보이는 균등화 방법 및 분류기가 다르게 나타남을 알 수 있었다. In this paper, we propose a multi-modal biometric system based on face, iris and fingerprint recognition system. To effectively aggregate two systems, we use statistical distribution models based on matching values for genuine and impostor, respectively. And then, We performed reveal fusion algorithms including weighted summation, Support Vector Machine(SVM), Fisher discriminant analysis, Bayesian classifier. From the various experiments, we found that the performance of multi-modal biometric system was influenced with the normalization methods and classifiers.