Earticle

초록

영어

To accomplish face recognition more efficiently, a distributed face recognition framework based on MB-LBP features and data fusion is presented in this paper. Firstly, four face regions are interactively marked and the Multi-scale Block Local Binary Patterns are extracted from these regions to achieve both locally and globally informative features. Secondly, a distributed framework is introduced to accelerate the recognition process, in which features of each single face region are utilized to perform face classification in parallel. The final decision is made by a kind of data fusion mechanism based on an artificial neural network (ANN) to make rational use of the confidence information got from the classification of each region. In experiment, the runtime and recognition performance of our system is compared with several other popular face recognition paradigms. The results indicate that the distributed framework presented in this paper can promote the efficiency of face recognition prominently while not losing accuracy in recognition performance.

목차

Abstract
 1. Introduction
 2. Face Database
 3. Feature Extraction
  3.1. MB-LBP
  3.2. Partitions
  3.3. MB-LBP Composite Features
 4. Classification
  4.1. SVM Classification
  4.2. Data Fusion Based on Artificial Neural Network
 5. A Distributed Framework for Face Recognition
 6. Experimental Results
 7. Conclusions and Future Works
 Acknowledgements
 References

키워드

저자

• Zheng Zhang [ College of Computer Science and Software, Tianjin Polytechnic University, Tianjin, China, 300387 ]
• Yan Guo [ School of Computer Software, Tianjin University, Tianjin, China, 300072 ]
• Guozhi Song [ College of Computer Science and Software, Tianjin Polytechnic University, Tianjin, China, 300387 ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Database Theory and Application

• 간기

  격월간

• pISSN

  2005-4270

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605