About
AMP Lab Projects
Downloads
Publications
People Links
Project -
Portable 3D Faces for Field Identification of Suspects
Top
of
this page
- Construct a 3D face model based on 2D
images or video captured
by low-resolution surveillance cameras.
- Display a 3D face model with face images rendered at
different
poses, under
various illumination conditions, and with different surroundings so as
to
ease suspect identification.
- Manipulate the 3D face model to create
different facial
expressions,
to simulate the aging process, to add or remove facial hairs, or to
change
hairstyles or other decorations.
Top
of
this page
- Stage I: Train generic
(i.e., prior) face
model using many examples:
- 3D mesh model
- Collect
face images from various poses
· · · · ·
- Gather
subjects' 3D
information by using stereo vision techniques on above poses (or by
using
laser range scans)
- Build generic 3D mesh
- 2D
texture model
- Collect
face image textures for both high and low resolutions
- Build generic model (e.g., Markov
random
field, MRF) for generating texture's missing high-frequency information.
- 3D mesh & 2D texture
Overlay generic 2D texture
onto generic 3D mesh
- Stage II:
Synthesize face model from single subject's image(s)
- Adapt
generic 3D mesh using
marked points on subject's low-resolution image
- Enhance low-resolution 2D texture
using trained model from Stage I (simulated)
- Overlay enhanced 2D texture onto
adapted 3D mesh
Top
of
this page
Any suggestions or comments are
welcome. Please send them to Todd
Stephenson.
Top
of
this page
|