Spatial frequency (SF) components encode a portion of the affective value expressed in face images. The aim of this study was to estimate the relative weight of specific frequency spectrum bandwidth on the discrimination of anger and fear facial expressions. The general paradigm was a classification of the expression of faces morphed at varying proportions between anger and fear images in which...

It is often assumed that upright faces are represented in a holistic fashion, while representations of inverted faces are essentially part-based. To assess this hypothesis, we recorded event-related potentials (ERPs) during a sequential face identity matching task where successively presented pairs of upright or inverted faces were either identical or differed with respect to their internal fea...

In this paper, we present a parallel face recognition algorithm based on \eigenfaces", which are known as the signiicant features because they are the eigenvec-tors(principal components) of a set of face images. Our work is composed of two phases: eigenface construction and face recognition. For the construction of eigenfaces, a solution of eigenvalue/eigenvector problem using parallel Jacobi t...

In the present study we examined the influence of spatial filtering on the N170-effect, a relatively early face-selective ERP difference associated with face detection. We compared modulation of the N170-effect using spatially filtered stimuli that either facilitated feature analysis or impeded configural analysis. The salience of inner face components was enhanced by presenting them in isolati...

This paper presents a method for face detection in the wild, which integrates a ConvNet and a 3D mean face model in an end-to-end multi-task discriminative learning framework. There are two components: i) The face proposal component computes face proposals via estimating facial key-points and the 3D transformation parameters for each predicted keypoint w.r.t. the 3D mean face model. ii) The fac...

We present a component-based, trainable system for detecting frontal and near-frontal views of faces in still gray images. The system consists of a two-level hierarchy of Support Vector Machine (SVM) classifiers. On the first level, component classifiers independently detect components of a face. On the second level, a single classifier checks if the geometrical configuration of the detected co...

In this paper, we propose a fast and accurate gaze recognition method by using the correlation of a small amount of computation facial components. The proposed method detects the face, eyes, nose and mouth. In the detected face region, using the Haar-like features, the center point of the detected area, the distance between each of the components, and each of the components was extracted throug...

As a computational bridge between the high-level a priori knowledge of object shape and the low-level image data, active contours (or snakes) are useful models for the extraction of deformable objects. We propose an approach for manipulating multiple snakes iteratively, called interacting snakes, that minimizes the attraction energy functionals on both contours and enclosed regions of individua...

There is growing interest in achieving age invariant face recognition due to its wide applications in law enforcement. The challenge lies in that face aging is quite a complicated process, which involves both intrinsic and extrinsic factors. Face aging also influences individual facial components (such as the mouth, eyes, and nose) differently. We propose a component based method for age invari...