Title :
Illumination Invariant Using DT-CWT and EMD for Face Recognition
Author_Institution :
Sch. of Inf. & Eng., Guangdong Univeristiy of Technol., Guangzhou
Abstract :
In this paper we describe a method to address illumination isolation for face recognition with empirical mode decomposition (EMD) to decompose subimages of dual-tree complex wavelet transform (DT-CWT) firstl. After that, the subimages are reconstructed without illumination distortion components. We then perform face recognition using improved orthogonal neighborhood preserving projections (IONPP). Experimental results reported on the CMU PIE database have shown method proposed outperfoms well.
Keywords :
face recognition; trees (mathematics); wavelet transforms; DT-CWT; EMD; dual-tree complex wavelet transform; empirical mode decomposition; face recognition; illumination invariant; illumination isolation; orthogonal neighborhood preserving projections; Computational intelligence; Databases; Face recognition; Frequency; Image reconstruction; Information security; Lighting; Principal component analysis; Sun; Wavelet transforms;
Conference_Titel :
Computational Intelligence and Security, 2008. CIS '08. International Conference on
Conference_Location :
Suzhou
Print_ISBN :
978-0-7695-3508-1
DOI :
10.1109/CIS.2008.193
