Expression-Invariant Face Recognition with Expression Classification

Abstract

Face recognition is one of the most intensively studied topics in computer vision and pattern recognition. Facial expression, which changes face geometry, usually has an adverse effect on the performance of a face recognition system. On the other hand, face geometry is a useful cue for recognition. Taking these into account, we utilize the idea of separating geometry and texture information in a face image and model the two types of information by projecting them into separate PCA spaces which are specially designed to capture the distinctive features among different individuals. Subsequently, the texture and geometry attributes are re-combined to form a classifier which is capable of recognizing faces with different expressions. Finally, by studying face geometry, we are able to determine which type of facial expression has been carried out, thus build an expression classifier. Numerical validations of the proposed method are given. Comparison with related methodsThe adverse effect of facial expressions on the performance of face recognition systems can be mostly attributed

On the Application of the Probabilistic Linear Discriminant Analysis to Face Recognition across Expression

“…To cope with facial expressions, several face recognition approaches have been proposed. The first one is morphing probe images to obtain the same expression as of the gallery images [9][10][11]. With this approach, the lack of texture information (e.g.…”

“…This kind of registration method is quite simple and retains the expressions of the faces. The other way of doing the registration is by applying piece-wise triangular warp as has been done in [9,10]. This registration method convert face shapes into a standard shape thereby removing the expressions posed by the faces.…”

A novel optimised face recognition application based on modified shuffled frog leaping algorithm

“…Recently, multiple feature extraction techniques and various classification approaches have been developed in order to resolve FR difficulties such as pose variety, multi-expressions, illumination problems and occluded faces. Xiaoxing et al (2006) brought the notion of separating geometric and textured data in 2D images where principal components analysis (PCA) was applied to extract local features from both texture and geometry eigen-spaces. Hyung-Soo and Daijin (2008) employed the idea of face modeling by the generation of active appearance model (AAM) and the appliance of temporal, structural and textural features.…”

Study of automatic prediction of emotion from handwriting samples

“…Reported analyses of predicting human emotions from biometrics have mostly been investigated with respect to the face modality [5][6][7], but also for the voice [8], gait [9] and keystroke [10] modalities.…”