DocumentCode :
2478124
Title :
Establishing point correspondence using multidirectional binary pattern for face recognition
Author :
Zhao, Sanqiang ; Gao, Yongsheng
Author_Institution :
Sch. of Eng., Griffith Univ., Griffith, QLD, Australia
fYear :
2008
fDate :
8-11 Dec. 2008
Firstpage :
1
Lastpage :
4
Abstract :
This paper presents a new Multidirectional Binary Pattern (MBP) for face recognition. Different from most Local Binary Pattern (LBP) related approaches which cluster LBP occurrences from whole image or partitioned subimage patches and use single or concatenated histogram measurement for recognition, MBP is applied on a sparse set of shape-driven points. The new representation is designed for describing both global structure and local texture, and also significantly reduces the high dimensionality of LBP histogram description. Composed of binary patterns from multiple directions, MBP is capable of extracting more discriminative features than LBP. The experiments on face recognition demonstrated the effectiveness of the proposed algorithm against expression and lighting variations.
Keywords :
data reduction; face recognition; feature extraction; image representation; image texture; pattern clustering; shape recognition; concatenated histogram measurement; discriminative feature extraction; face recognition; high dimensionality reduction; image representation; image texture; local binary pattern occurrences clustering; multidirectional binary pattern; point correspondence; shape-driven point; sparse set; Computational efficiency; Data mining; Face detection; Face recognition; Feature extraction; Histograms; Image databases; Image edge detection; Pixel; Spatial databases;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2008. ICPR 2008. 19th International Conference on
Conference_Location :
Tampa, FL
ISSN :
1051-4651
Print_ISBN :
978-1-4244-2174-9
Electronic_ISBN :
1051-4651
Type :
conf
DOI :
10.1109/ICPR.2008.4761248
Filename :
4761248
Link To Document :
بازگشت