Our current work in the biometrics field builds on our earlier work on face recognition at a distance where we have illustrated the value of 3D face recognition over 2D face recognition systems under controlled acquisition indoor and outdoor environments [1-4].
Unavoidable problems such as pose and illumination are manifested when multiple subjects are captured at a distance under uncontrolled environment. The objective of our ongoing research is to enable multi-object identification at a distance using a smart optical sensor augmented with range, IR, and mobility for image acquisition, and to develop a fast computing engine enabling algorithmic response at frequency up to 10 folds the current state of development by CVIP-UofL team.
The goal of this project is to propose a framework for face recognition at a distance based on texture and sparse-stereo reconstruction. We develop a 3D acquisition system that consists of two CCD stereo cameras mounted on pan-tilt units with adjustable baseline. We first detect the facial region and extract its landmark points.
The face detection problem can be defined as: Given an arbitrary image, the goal of face detection is to determine whether or not there are any faces in the image and, if present, return the image location and extent of each face.
The challenges associated with face detection can be attributed to many factors including pose and partial or whole occlusion of some facial features such as an eye or the mouth due to presence of beards, mustaches, and glasses which has a great deal of variability in shape, color, and size. Also, the appearance of faces is directly affected by a person’s facial expression. Another issue is that faces may be partially occluded by other objects. In an image with a group of people, some faces may partially occlude other faces.