cameo face recognition year 1 progress and year 2 goals n.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
CAMEO: Face Recognition Year 1 Progress and Year 2 Goals PowerPoint Presentation
Download Presentation
CAMEO: Face Recognition Year 1 Progress and Year 2 Goals

Loading in 2 Seconds...

play fullscreen
1 / 9

CAMEO: Face Recognition Year 1 Progress and Year 2 Goals - PowerPoint PPT Presentation


  • 94 Views
  • Uploaded on

CAMEO: Face Recognition Year 1 Progress and Year 2 Goals. Fernando de la Torre, Carlos Vallespi, Takeo Kanade. Face Recognition from video. How to learn a facial model from the data coming from the face detector?. Face Recognition from video. Challenges :

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'CAMEO: Face Recognition Year 1 Progress and Year 2 Goals' - bern


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
cameo face recognition year 1 progress and year 2 goals

CAMEO: Face RecognitionYear 1 Progress and Year 2 Goals

Fernando de la Torre, Carlos Vallespi, Takeo Kanade

face recognition from video
Face Recognition from video.
  • How to learn a facial model from the
  • data coming from the face detector?
face recognition from video1
Face Recognition from video.
  • Challenges:
    • How to learn INVARIANTLY to spatial transformations?

Simultaneous registration and Subspace computation.

2) How to select the most discriminative features?

3) How to deal with missing data?

face recognition from video2
Face Recognition from video.
  • Register w.r.t a Subspace
  • Selecting the most discriminative samples.
face recognition from video3
Face Recognition from video.
  • - How to exploit temporal redundancy in the recognition process?

B=

A=

Distance between

Sets A and B.

Singular vectors

of A

face recognition from video4
Face Recognition from video.
  • 95 % of recognition rate (11 Subjects and 30 images per subject).
plans year 2
Plans year 2.
  • Why is hard to perform face recognition from

Mosaic images?

    • Small images.
    • Noisy images.
    • Misalignments.
  • But …
    • Temporal redundancy.
    • Recognizing several people (exclusive principle).
    • Superesolution.
learning person specific models
Learning person-specific models.
  • Unsupervised learning from video sequences:
    • Facial appearance models.
    • Behaviour models (e.g. gestures).
  • Learning person-specific models can be useful to identify people, to predict actions?
meeting visualization summarization
Meeting visualization/summarization
  • Input:
    • Set of several videos, with detected and recognized faces.
    • Set of indicators if the person is talking, up, down, etc…
  • Output:
    • Low dimensional visualization of the meeting activity and interaction between people.
    • Learning interaction models between people.