FAR Facial Attribute Recognition Jim Austin Advanced Computer - - PowerPoint PPT Presentation

far facial attribute recognition
SMART_READER_LITE
LIVE PREVIEW

FAR Facial Attribute Recognition Jim Austin Advanced Computer - - PowerPoint PPT Presentation

FAR Facial Attribute Recognition Jim Austin Advanced Computer Architectures Group, University of York Cybula Ltd. FAR project Concerted action with AICP (costs and people shared) Started 1 August 2003 for 2 years. FAR


slide-1
SLIDE 1

FAR – Facial Attribute Recognition

Jim Austin Advanced Computer Architectures Group, University of York Cybula Ltd.

slide-2
SLIDE 2

FAR project

  • Concerted action with AICP (costs and

people shared)

  • Started 1 August 2003 for 2 years.
  • FAR Collaborators

– Cybula Ltd. – QinetiQ – University of York

slide-3
SLIDE 3

People

  • University of York

– Dr. Nick Pears, Academic manager – Prof. Jim Austin – Dr. Mike Freeman, Technical and Amadeus Link

  • Cybula

– Dr. Nick Walton, Technical Lead. – Dr. Sujeewa Alwis, Commercial manager

  • QinetiQ

– Dr. Andy Lewin, Technical Lead.

slide-4
SLIDE 4

Motivation

  • Many applications where recognising a face

(or hand etc.) would be valuable.

  • Present systems are expensive, large and

power hungry

  • A low cost camera, aimed primarily at face

recognition would be highly beneficial.

  • Cybula/UofY has a system that this can be

based on

slide-5
SLIDE 5

Aims

  • To build a low cost 3D camera to primarily

support facial biometrics.

– Selection and evaluation of camera technology – Development of embeddable camera software

  • Camera calibration
  • 3D image generation
slide-6
SLIDE 6

Technology

Cybula Camera CM-2

Stereo Lenses Projector Texture lens

slide-7
SLIDE 7

Technology

  • QinetiQ camera

– Special spot projector – Very low power (USB power) – Potential low cost

slide-8
SLIDE 8

Reconstruction

Objects Stereo camera 1 Stereo camera 2

slide-9
SLIDE 9

Typical Images

slide-10
SLIDE 10

Image correction

  • Radial Distortion correction

After Before

slide-11
SLIDE 11

3D reconstruction

  • Next stage

– Finding correspondences in the two images – Helped by the spot projector – Must be as fast as possible – Must fit on DSP/FPGA as a core

slide-12
SLIDE 12

Conclusions

  • Camera technology identified
  • First problem solved – camera calibration
  • Next stage is 3D reconstruction
  • Port to hardware