首頁 > 網路資源 > 大同大學數位論文系統

Title page for etd-0211119-124817


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 indicate access worldwide
    Date of Defense 2019-01-25 Date of Submission 2019-02-11


    Browse | Search All Available ETDs