Computer Vision Research @ UNR

Dr. George Bebis

http://www.cse.unr.edu/CVL

Computer Vision Laboratory (CVL)

• CVL was founded in 1998 to conduct basic and applied research in computer vision.

• Members

- 2 faculty- 7 PhD students- 2 MS students- 6 undergraduate students

Total funding:

$4.2M

Sponsors:

External Collaborators:

LLNL

LANL

Main CVL Research Areas

Biometrics Segmentation

Object detection/tracking

3D object recognition

3D reconstruction

Human action recognition

Applications

Hand-based Authentication/Identification

Hand-based Authentication/Identification (cont’d)

Extensions: use hand geometry forgender, ethnicity, and age classification

G. Amayeh, G. Bebis, A. Erol, and M. Nicolescu, "Hand-Based Verification and Identification Using Palm-Finger Segmentation and Fusion", Computer Vision and Image Understanding, vol 113, pp. 477-501, 2009.

Fingerprint Identification

minutiae small overlapping area

matching

input

ID

Fingerprint Identification (cont’d)

Super-Template Synthesis

matching

ID

super-template

T. Uz, G. Bebis, A. Erol, and S. Prabhakar, "Minutiae-Based Template Synthesis and Matching for Fingerprint Authentication", Computer Vision and Image Understanding, vol 113, pp. 979-992, 2009.

Face Recognition

http://www.face-rec.org/

appearance changes

Face Recognition (cont’d)

• Visible spectrum– High resolution, less sensitive to the presence of

eyeglasses.– Sensitive to changes in illumination direction and facial

expression.

• Thermal IR spectrum– Not sensitive to illumination changes.– Low resolution, sensitive to air currents, face heat

patterns, aging, and the presence of eyeglasses (i.e., glass is opaque to thermal IR).

LWIR

Face Recognition (cont’d)

Feature Extraction

Fusion UsingGenetic Algorithms

Reconstruct Image

FusedImage

G. Bebis, A. Gyaourova, S. Singh, and I. Pavlidis, "Face Recognition by Fusing Thermal Infrared and Visible Imagery", Image and Vision Computing, vol. 24, no. 7, pp. 727-742, 2006.

Face Recognition (cont’d)

Vehicle Detection and Tracking

Ford’s low light camera Ford’s Concept Car

Vehicle Detection and Tracking (cont’d)• Our system can process 10 fps on average.• Classification error is close to 6% (FP + FN)

(a) (b)FN

FP

Z. Sun, G. Bebis, and R. Miller, "Monocular Pre-crash Vehicle Detection: Features and Classifiers", IEEE Transactions on Image Processing , vol. 15, no. 7, pp. 2019-2034, July 2006.

Segmentation

Segmentation (cont’d)

L. Loss, G. Bebis, M. Nicolescu, and A. Skurikhin, "An Iterative Multi-Scale Tensor Voting Scheme for Perceptual Grouping of Natural Shapes in Cluttered Backgrounds", Computer Vision and Image Understanding (CVIU) vol. 113, no. 1, pp. 126-149, January 2009.

More information on Computer Vision

• Computer Vision Home Page http://www.cs.cmu.edu/afs/cs/project/cil/ftp/html/vision.html

• Home Page http://www.cs.unr.edu/CRCD

• UNR Computer Vision Laboratory http://www.cs.unr.edu/CVL