Face Recognition at a Distance (FRAD)

Introduction:

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.

 

Goal:

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.

 

Problem Definition:

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.

 

Illustrations:

 

The trilogy of the of the face recognition at a distance in CVIP Lab

The trilogy of the FRAD in CVIP Lab: image acquisition: capturing objects in the field of view of the sensor; reconstruction: mapping the captured objects into a form suitable for the final recognition step; which identifies the detected objects by correspondence with a dynamic database

Illustration of captured images

Illustration of captured images: (a) 15-meter (b) 30-meter, (c) 50-meter, and (d) 80-meter.

Research Team:

Publications:

  1. H. Rara, S. Elhabian, A. Ali, M. Miller, T. Starr, and A. Farag, Face Recognition at-a-Distance using Texture and Sparse-Stereo Reconstruction, IEEE Fourth International Conference on Biometrics: Theory, Applications and Systems (BTAS), Sept. 27-29, 2010.
  2. H. Rara, A. Ali, S. Elhabian, T. Starr, and A. Farag, Face Recognition at-a-Distance using Texture, Dense- and Sparse-Stereo Reconstruction, Proceedings of the International Conference on Pattern Recognition (ICPR-2010), August 23-26, 2010, Istanbul, Turkey.
  3. H. Rara, S. Elhabian, A. Ali, T. Gault, M. Miller, T. Starr, and A. Farag, A Framework for Long Distance Face Recognition using Dense- and Sparse-Stereo Reconstruction, 5th International Symposium on Visual Computing (ISVC09), Nov. 30 – Dec. 2, 2009, Las Vegas, Nevada, USA.
  4. H. Rara, S. Elhabian, A. Ali, M. Miller, T. Starr, and A. Farag, Face recognition at a distance based on sparse-stereo reconstruction, IEEE CVPR Biometrics Workshop, 2009.
  5. Ham Rara, Shireen Elhabian, Thomas Starr, and Aly Farag, “3D Face Recovery from Intensities of General and Unknown Lightning Using Partial Least Squares,” Proc. of 2010 IEEE International Conference on Image Processing (ICIP), pp. 4041-4044, 2010.
  6. H. Rara, S. Elhabian, T. Starr, and A. Farag, ―Model-Based Shape Recovery From Single Images Of General And Unknown Lighting,‖ 2009 IEEE International Conference on Image Processing (ICIP), Nov. 7 – Nov. 10, 2009, Cairo, Egypt

 


News