지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 高漢錫
- 발행연도
- 2020
- 저작권
- 고려대학교 논문은 저작권에 의해 보호받습니다.
이용수0
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Recently, the development of the robot industry has begun to focus mutual communication between humans and robots, beyond the manual work and the simple labor that provides physical assistance to humans.
The ability to recognize facial expressions is a vital component of the interaction between humans and robots. It will be possible to communicate more smoothly between humans and robots.
Facial expressions are one of the most important features of human emotion perception. The emotion can be determined based on visual information of a face that changes visually according to the emotion change.
In this paper, we propose a method for facial emotions recognition based on convolution neural network using visual feature information fusion of faces that appear according to human emotion changes. In addition, we proposed a method to determine facial expression more accurately than when using only simple face information by fusion of various feature information obtained from facial expressions, for example, mouth, eyes, and face landmarks information.
Experimental results show that the proposed scheme is more accurate than previous research.
The ability to recognize facial expressions is a vital component of the interaction between humans and robots. It will be possible to communicate more smoothly between humans and robots.
Facial expressions are one of the most important features of human emotion perception. The emotion can be determined based on visual information of a face that changes visually according to the emotion change.
In this paper, we propose a method for facial emotions recognition based on convolution neural network using visual feature information fusion of faces that appear according to human emotion changes. In addition, we proposed a method to determine facial expression more accurately than when using only simple face information by fusion of various feature information obtained from facial expressions, for example, mouth, eyes, and face landmarks information.
Experimental results show that the proposed scheme is more accurate than previous research.
목차
1. 서론 11.1. 연구배경 11.2. 논문 구성 32. 관련 연구 42.1. 특징점 기반의 정보 이용법 42.2. 합성곱 신경망 네트워크(Convolution Neural Network) 83. 제안 기법 193.1. 네트워크 구조 193.2. 얼굴 인식 알고리즘 223.3. Landmarks 및 특징 데이터 획득 244. 실험 및 결과 분석 254.1. 훈련 데이터 구성 254.2. 실험 환경 294.3. 학습 모델에 따른 예측 결과 304.4. 실시간 감정 인식 시스템 425. 결론 및 향후 연구 방향 455.1. 결론 455.2. 향후 연구 방향 46참고문헌 47
최근 본 자료
댓글(0)
0