Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition

Abstract

Abstract. Two Empirical Mode Decomposition (EMD) based face recognition schemes are proposed in this paper to address variant illumination problem. EMD is a data-driven analysis method for nonlinear and non-stationary signals. It decomposes signals into a set of Intrinsic Mode Functions (IMFs) that containing multiscale features. The features are representative and especially efficient in capturing high-frequency information. The advantages of EMD accord well with the requirements of face recognition under variant illuminations. Earlier studies show that only the low-frequency component is sensitive to illumination changes, it indicates that the corresponding high-frequency components are more robust to the illumination changes. Therefore, two face recognition schemes based on the IMFs are generated. One is using the high-frequency IMFs directly for classification. The other one is based on the synthesized face images fused by high-frequency IMFs. The experimental results on the PIE database verify the efficiency of the proposed methods.

Facial emotion recognition using empirical mode decomposition

“…Recent studies show that EMD algorithm was used to detect epileptic seizure using EEG signals (Kaleem, Guergachi, & Krishnan, 2013;Orosco, Lacia, Correa, Torres, & Graffigna, 2009;Pachori, 2008) and diagnose Alzheimer disease (Gallix, Gorriz, Ramirez, & Lang, 2012). Also, EMD algorithm is extended into bi-dimensional EMD (BEMD) and has been used for texture analysis (Nunes, Bouaoune, Delechelle, Niang, & Bunel, 2003), image compression (Linderhed, 2005), skeletonization pruning (Krinidis & Krinidis, 2013), image fusion (Hariharan, Koschan, Abidi, Gribok, & Abidi, 2006), face recognition (Bhagavatula & Savvides, 2007;Zhang & Tang, 2009) and facial pose-estimation (Qing, Jiang, & Yang, 2010). EMD is a multi-resolution decomposition technique suitable for nonlinear data has been used to decompose any complicated signal into frequency components called IMFs.…”