Face recognition by independent component analysis

Abstract

Abstract-A number of current face recognition algorithms use face representations found by unsupervised statistical methods. Typically these methods find a set of basis images and represent faces as a linear combination of those images. Principal component analysis (PCA) is a popular example of such methods. The basis images found by PCA depend only on pairwise relationships between pixels in the image database. In a task such as face recognition, in which important information may be contained in the high-order relationships among pixels, it seems reasonable to expect that better basis images may be found by methods sensitive to these high-order statistics. Independent component analysis (ICA), a generalization of PCA, is one such method. We used a version of ICA derived from the principle of optimal information transfer through sigmoidal neurons. ICA was performed on face images in the FERET database under two different architectures, one which treated the images as random variables and the pixels as outcomes, and a second which treated the pixels as random variables and the images as outcomes. The first architecture found spatially local basis images for the faces. The second architecture produced a factorial face code. Both ICA representations were superior to representations based on PCA for recognizing faces across days and changes in expression. A classifier that combined the two ICA representations gave the best performance.Index Terms-Eigenfaces, face recognition, independent component analysis (ICA), principal component analysis (PCA), unsupervised learning.

Robust Face Recognition Based on Part-Based Localized Basis Images

“…ICA is a widely used subspace projection technique that projects data from a highdimensional space to a lower-dimensional space [2][3][4]. This technique is a generalization of PCA that decorrelates the high-order statistics in addition to the second-order moments.…”

“…Therefore, the performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images. Among popularly used techniques are PCA, ICA and FLD [1][2][3][4][5]. ICA can be applied to face recognition in two different representations: ICA architecture I and II [2].…”

“…Among popularly used techniques are PCA, ICA and FLD [1][2][3][4][5]. ICA can be applied to face recognition in two different representations: ICA architecture I and II [2]. The goal of this research is to develop an optimal set of basis images for face recognition robust to partial occlusions and local distortions.…”

Correction of Spectral Interference of Ethanol and Glucose for Rice Wine Evaluation

“…As an approach to evaluate multiple components in the spectrum of a mixture, signal separation has been developed [11], [12]. Independent component analysis (ICA) is the most popular signal separation method, which separates the signal of a mixture into statistically independent signals.…”

“…ICA is a blind source separation method and does not require prior knowledge for signal decomposition. ICA has been applied to electroencephalograms (EEGs) for removing blink and muscle artifacts [11] and facial images for face recognition [12]. Recently, ICA has been applied to NIR and MIR spectra to decompose their spectra into statistically independent spectra [13], [14].…”