Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0211119-124817 Statistics This thesis had been viewed 108 times. Download 0 times. Author Ting-Ren Jian Author's Email Address No Public. Department Electrical Engineering Year 2018 Semester 1 Degree Master Type of Document Master's Thesis Language English Page Count 27 Title Face Recognition Based on Convolutional Neural Network and 3DLBP Feature Keyword Support Vector Machines 3D Local Binary Patterns Convolutional Neural Network Face Recognition Face Recognition Convolutional Neural Network 3D Local Binary Patterns Support Vector Machines Abstract In recent years, many face recognition methods using depth images are presented, because RGB face recognition is not effective to deal with the variations of posture and illumination. However, depth face recognition still suffers some situations that can’t be handled, such as a large number of expression changes. In this thesis, we propose a RGB-D face recognition method and compare the recognition results with the RGB face recognition method and the depth face recognition method. The proposed method used Convolutional Neural Network (CNN) to extract facial RBG features by training, and used the technique of 3D Local binary patterns (3DLBP) to extract facial depth features. Finally, by combing with RBG features and depth features, Support Vector Machines (SVM) was applied for face recognition. Our RGB-D face recognition method was implemented using Python and the experiments were carried out utilizing the EURECOM Face Dataset. Advisor Committee Shuenn-Shyang Wang - advisor
Chau-Yun Hsu - co-chair
Kuo-Ho Su - co-chair
Files Date of Defense 2019-01-25 Date of Submission 2019-02-11