DocumentCode :
3579893
Title :
A New Compressive Sensing Method for Face Recognition
Author :
Lijia Wang ; Hua Zhang ; Zhenjie Wang ; Junting Li
Author_Institution :
Inf. Eng. & Autom. Dept., Hebei Coll. of Ind. & Technol., Shijiazhuang, China
Volume :
1
fYear :
2014
Firstpage :
529
Lastpage :
532
Abstract :
We propose a compressive sensing based method to recognize face with pose variations. The face recognition framework includes two issues: feature extraction and classification. For feature extraction, we present a random measurement matrix to compress an image from high dimensional space to a low dimensional space. The compressive feature has a powerful discrimination because it can preserve most salient information of the image. Meanwhile, the random measurement matrix requires only a uniform random generator. Consequently, the computational complexity is very low. For face classification, we adopt a gradient projection approach considering the Barzilai-Borwein steps and adaptive nonmonotone line searching method. The approach can not only guarantee global convergence but also keep the gradient projection´s performance. Finally, our method is conducted on the ORL face database. The results illustrate that our method can handle the variations pose and perform well in term of computing time and recognition rate.
Keywords :
compressed sensing; computational complexity; convergence; face recognition; feature extraction; gradient methods; image classification; matrix algebra; search problems; visual databases; Barzilai-Borwein steps; ORL face database; adaptive nonmonotone line searching method; compressive sensing method; computational complexity; computing time; face recognition framework; feature classification; feature extraction; global convergence; gradient projection approach; high dimensional space; low dimensional space; pose variations; random measurement matrix; recognition rate; uniform random generator; Compressed sensing; Face; Face recognition; Feature extraction; Image coding; Principal component analysis; Sparse matrices; compressive sensing; face recognition; gradient projection; random measurement matrix;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence and Design (ISCID), 2014 Seventh International Symposium on
Print_ISBN :
978-1-4799-7004-9
Type :
conf
DOI :
10.1109/ISCID.2014.73
Filename :
7064249
Link To Document :
بازگشت