The Face Detection Research Based on Multi-Scale and Rectangle Feature

Hong Hai Liu; Xiang Hua Hou

doi:10.4028/www.scientific.net/AMM.198-199.1383

Paper Titles

A Fast Ray-Tracing Algorithm for X-Ray Imaging Simulation
p.1361

Attribute Reduction Algorithm for Fuzzy Decision Table with Membership Degrees and Weights
p.1367

Design and Implement of the Reconfigurable Algorithm Based on uC/OS-II
p.1372

Reach of Key Management Strategy in Digital Television System
p.1378

The Face Detection Research Based on Multi-Scale and Rectangle Feature
p.1383

A Novel Cluster Head Selection Algorithm Based on Energy Consumption for LEACH
p.1389

Shortest Travel Path Searching System Based on Dijkstra Algorithm
p.1395

Orthogonal Wavelet Transform Blind Equalization Algorithm Based on the Optimization of Artificial Fish Swarm Algorithm
p.1399

A Kind of Improved SPRINT Classification Algorithm Adaptive to the Change of Concept Drift
p.1403

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 198-199The Face Detection Research Based on Multi-Scale...

The Face Detection Research Based on Multi-Scale and Rectangle Feature

Abstract:

When extracting the face image features based on pixel distribution in face image, there always exist large amount of calculation and high dimensions of feature sector generated after feature extraction. This paper puts forward a feature extraction method based on prior knowledge of face and Haar feature. Firstly, the Haar feature expressions of face images are classified and the face features are decomposed into edge feature, line feature and center-surround feature, which are further concluded into the expressions of two rectangles, three rectangles and four rectangles. In addition, each rectangle varies in size. However, for face image combination, there exist too much redundancy and large calculation amount in this kind of expression. In order to solve the problem of large amount of calculation, the integral image is adopted to speed up the rectangle feature calculation. In addition, the thought based on classified trainer is adopted to reduce the redundancy expression. The results show that using face image of Haar feature expression can improve the speed and efficiency of recognition.

You might also be interested in these eBooks

Applied Mechanics, Mechatronics Automation & System Simulation

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 198-199)

Pages:

1383-1388

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.198-199.1383

Citation:

Cite this paper

Online since:

September 2012

Authors:

Hong Hai Liu, Xiang Hua Hou

Keywords:

Classified Trainer, Integral Image, Multi-Scale, Rectangle Feature

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] W.F. Zhao: Research on Feature Extraction Methods for Face Recognition (Ph.D. Zhejiang University, China 2009). p.56.

Google Scholar

[2] O. Yamaguchi, K. Fukui, and K. Maeda: Pro. Automatic Face and Gesture Recognition (Nara, Japan, 1998). p.318.

Google Scholar

[3] Z.B. Guo: Research on the Algorithms of Fast Face Detection and Feature Extraction (Ph.D. Nanjing University of Science and Technology, China 2007). p.66.

Google Scholar

[4] M. Nishiyama, O. Yamaguchi and K. Fukui: Pro. Audio- and Video-Based Biometric Person Authentication (NewYork, USA, 2005). pp.71-78.

Google Scholar

[5] J.W. Li,Y. H. Wang and T.N. Tan: Pro. the 5th Chinese Conference on Biometric Recognition (Guangzhou, China, 2004). p.224.

Google Scholar

[6] L.H. Zhao: Research and Realization in Face Detection and Recognition Algorithms (Ph.D. Northeastern University, China 2006). p.32.

Google Scholar

[7] K. Das,S. Osechinskiy and Z. Nenadic: Pro. Medicine and Biology Society (San Jose, California, USA, January 23, 2007). p.6519.

Google Scholar