DocumentCode :
3328144
Title :
Face recognition with expression variation via robust NCC
Author :
Zafer, Aliya ; Nawaz, R. ; Iqbal, Jamshed
Author_Institution :
Coll. of EME, Nat. Univ. of Sci. & Technol., Rawalpindi, Pakistan
fYear :
2013
fDate :
9-10 Dec. 2013
Firstpage :
1
Lastpage :
5
Abstract :
We introduce a novel algorithm namely Robust Normalized Cross-correlation Coefficient (RNCC) for 2D frontal face recognition with expression variation. There are thirteen renowned ways to look at the Cross-correlation Coefficient. Our proposed method makes use of the technique named "Correlation as a Rescaled Variance of the Difference between Standardized Scores". It is based on estimating robust correlation via the rejection of outliers which original Normalized Cross-correlation Coefficient (NCC) is not capable of. We tested our technique on 6 renowned databases (AR, Cohn Kanade, Cohn Kan ade plus, Yale Faces, Bosphorus, and Jaffe) and have obtained exceptionally remarkable results. The rigorous testing has been performed using minimum training samples and low dimensionality (13 × 10). The recognition rates for all the tested databases are above 90% and outperform existing techniques.
Keywords :
face recognition; 2D frontal face recognition; RNCC; estimating robust correlation; expression variation; original normalized cross-correlation coefficient; recognition rates; rigorous testing; robust NCC; robust normalized cross-correlation coefficient; standardized scores; Databases; Face; Face recognition; Lighting; Robustness; Testing; Training; Expression Invariance; Extremes Deletion; Face Recognition; Normalized Cross-correlation Coefficient (NCC); Outliers; Robust Estimators;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Emerging Technologies (ICET), 2013 IEEE 9th International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4799-3456-0
Type :
conf
DOI :
10.1109/ICET.2013.6743520
Filename :
6743520
Link To Document :
بازگشت