메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
HaoBiao (Dong-A University) Dae-Seong Kang (Dong-A University)
저널정보
한국정보기술학회 JOURNAL OF ADVANCED INFORMATION TECHNOLOGY AND CONVERGENCE Journal of Advanced Information Technology and Convergence Vol.7 No.1
발행연도
2017.7
수록면
55 - 63 (9page)
DOI
10.14801/jaitc.2017.7.1.55

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Deep learning has been developing rapidly in the field of image process and has achieved very good results in the field of image recognition. Before the rise of deep learning, the SVM(Support Vector Machine) algorithm was the best way to achieve image recognition. The emergence of convolution neural network makes weights share, and make the complexity of computing greatly reduce, but the accuracy of the image recognition has been improved. The CNN(convolution neural network) can avoid the complex feature extraction steps in the previous machine learning and change into that input the image data to neural network directly. Because of CNN’s high accuracy CNN has been received widespread attention by people and replaced the status of SVM(support vector machine) quickly. Expression can reflect a person"s emotions well. If we can identify the expression well it has a good effect to perform psychological reasoning and understand each other"s psychological ideas. So I research the facial expression recognition. The CNN is VGG convolution neural network in this research. In this paper the main purpose is that through training input data to test the experimental data and classify into 7 types expression of anger, sadness, fear, disgust, surprise, happy and quiet. This research uses the tensorflow library to construct deep learning network. At the end of the paper the experimental result of using CNN(convolution Neural Network) compare with the Result of using SVM. Finally we find that the express recognition accuracy of using convolution neural network is higher than the accuracy of using SVM(support vector machine).

목차

Abstract
1. Introduction
2. Correlation Theory
3. Structure Design of Neural Network
4. Experimental Results
5. Conclusions
6. Acknowledgments
7. References

참고문헌 (8)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2018-004-001173794