earticle

논문검색

Surveillance Face Super-Resolution via Shape Clustering and Subspace Learning

초록

영어

In a learning-based super-resolution algorithm, suitable prior from the training database is a key issue. A novel face hallucination algorithm based on shape clustering and subspace learning for adaptive prior is proposed in this paper. We define face shape metrics with point distribution model by Hausdorff Distance, then a framework of adaptive prior and subspace learning is proposed to enhance the performance of surveillance face super-resolution. Linear regression is used to learn the relationship between low and high image systhesis coefficients. Experiments show that the face super-resolution algorithm based on shape classification can improve the subjective and objective quality of the input low-resolution face images and outperform many state-of-the-art global-based face super-resolution methods.

목차

Abstract
 1. Introduction
 2. Face Shape Metrics based on Hausdoff Distance
  2.1 Points Distribution Model
  2.2 Shape Metrics based on Hausdoff Distance
 3. Adaptive Prior Face Super-resolution based on Subspace Learning
  3.1 Clustering of Training Database
  3.2 Subspace Learning based Super-resolution
  3.3 Coefficients Transformation by Linear Regression
 4. Experiments
 5. Conclusion
 Acknowledgements
 References

저자정보

  • Lu Tao National Engineering Research Center on Multimedia Software, Wuhan University, Hubei Province Key Laboratory of Intelligent Robot, College of Computer Science and Engineering Wuhan Institute of Technology
  • Hu Ruimin National Engineering Research Center on Multimedia Software, Wuhan University, School of Computer, Wuhan University
  • Han Zhen National Engineering Research Center on Multimedia Software, Wuhan University, School of Computer, Wuhan University
  • Xia Yang National Engineering Research Center on Multimedia Software, Wuhan University
  • Gao Shang National Engineering Research Center on Multimedia Software, Wuhan University

참고문헌

자료제공 : 네이버학술정보

    ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

    0개의 논문이 장바구니에 담겼습니다.