Title :
Face Recognition Method Based on FLPP
Author :
Liu, Yang ; Sun, Jin-guang
Author_Institution :
Dept. of Electron. & Inf. Eng., Liaoning Techinical Univ., Huludao, China
Abstract :
In view of the problems of features in face recognition, a new face image feature extraction and recognition method----Fractal Locality Preserving Projections (FLPP) is proposed in this paper. FLPP first gets the high order statistic information by calculating the fractal codes of face images. Based on manifold learning theories, LPP takes into account the inter-class information, and extract the discriminat features of face image for recognition. This method has been tested in the ORL face database and Yale face database, using the nearest neighborhood algorithm to construct classified. The results show that the FLPP has good performance even if illumination, pose, face expression change.
Keywords :
face recognition; feature extraction; fractals; FLPP; ORL face database; Yale face database; face recognition method; fractal codes; fractal locality preserving projection; image feature extraction; image recognition; manifold learning theories; nearest neighborhood algorithm; Databases; Face; Face recognition; Feature extraction; Fractals; Image recognition; Manifolds; LPP; dimension reduction; face recognition; features extraction; fractal encoding;
Conference_Titel :
Electronic Commerce and Security (ISECS), 2010 Third International Symposium on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-4244-8231-3
Electronic_ISBN :
978-1-4244-8231-3
DOI :
10.1109/ISECS.2010.72
