Loading...

Improving the Method of Face Recognition

Rabiepour, Siavash | 2015

698 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 47764 (55)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Vosughi Vahdat, Bijan
  7. Abstract:
  8. Face recognition is one of the best biometrics in computer vision. Although researchers introduced this method many years ago, the most important improvement has occurred in the biometrics last decade. Face recognition was employed in areas such as passport checking, security issues and identification. It facilitates our daily life as we use it in our mobile phones and computers for unlocking our devices. Many approaches were employed in the face recognition applications. Some of them were single-modal like PCA, ICA and LDA and some others were multimodal like Visual + 3D or 3D + IR. Still, most of Face recognition methods suffer from environment changes like variations in illumination and age span. And none of them can recognize faces as well as they should. So we decided to introduce a new method. Hopefully this method scores better recognition rate under the environment changes. This thesis proposes a method for improving face recognition. One of the basic features, which are not employed in face recognition, is the indexing method. By this method you do not need to save or explore large data like most of the face recognition algorithms. In this method, you assign index or indices to the pattern of various faces. How to select these features and how to measure these features is the main concern in this thesis
  9. Keywords:
  10. Face Detection ; Feature Extraction ; Indexing

 Digital Object List