Facial recognition technology is effective in human computer communication. Robustness for facial recognition is necessary because face views change in many ways due to position, expression, and light. We propose a facial recognition system robust for facial scale variations, which is mainly composed of our flexible feature matching and rapid parallel estimation of facial position and scale.

A number of computer vision problems such as facial age estimation, crowd counting and pose estimation can be solved by learning regression mapping on low-level imagery features. We show that visual regression can be substantially improved by two-stage regression where imagery features are first mapped to an attribute space which explicitly models latent correlations across continuously-changin...

Determination of stature from fragmented human remains is vital part of forensic investigation for the purpose of identification. The present study was aimed to modelling the stature both for male and female separately on the basis of craniofacial dimensions. The study was conducted on 150 young and healthy students (75 males and 75 females) in the age group ranging from 20 to 28 years. The sta...

BACKGROUND Short palpebral fissure lengths (PFL) are one of three facial features that define the unique facial phenotype of fetal alcohol syndrome (FAS). Published PFL growth charts vary greatly in both rate and magnitude of growth, placing their accuracy and validity in question. New PFL growth charts were recently published to reflect a racial/ethnic cross section of Canadian girls and boys ...

This work presents a framework for emotion recognition, based in facial expression analysis using Bayesian Shape Models (BSM) for facial landmarking localization. The Facial Action Coding System (FACS) compliant facial feature tracking based on Bayesian Shape Model. The BSM estimate the parameters of the model with an implementation of the EM algorithm. We describe the characterization methodol...

Recognizing a face from a novel view point poses major challenges for automatic face recognition. Recent methods address this problem by trying to model the subject specific appearance change across pose. For this, however, almost all of the existing methods require a perfect alignment between a gallery and a probe image. In this paper we present a pose invariant face recognition method centere...

Pose problem presents a challenge to face recognition methods because the shapes and features of the human face with large pose angle often appear quite different from the template. One approach to overcome this problem involves the estimation of the angle to which the face is rotated and then matches it to templates with the same pose. Another approach involves aligning the key facial features...

The purpose of this research work is focused on occlusion conditions in the face like wearing sunglasses and scarf in the eyes and mouth positions of the facial image. The proposed work has three stages. The first stage was based on Decision Tree Induction C5.0 algorithm to classify the occluded part and non occluded part in the facial image. The Second stage was face verification using Local B...