0
FACIAL FEATURES
EXTRACTION USING PHASED
BASEDVIDEO AMPLIFICATION
Coutino Minguez, Mario Alberto
University of Calgary
Summ...
OBJECTIVE
• Detection and tracking of
facial features in video
sequences in an automatic
manner.
Wednesday, August 28, 13
PROPOSAL
• Subtle motion is produced in specific facial features during the
normal human’s breathing.
• Amplifying the pres...
APPROACH
Wednesday, August 28, 13
APPROACH
Wadhwa et. al 2013
Wednesday, August 28, 13
METHODOLOGY
Wednesday, August 28, 13
PARTIAL RESULTS
• Face’sTracking Results
• Eyebrows’ Detection Results
Wednesday, August 28, 13
FACE DETECTOR
Comparison:Viola-Jones (left) Proposed method (right)
Partial faces results using proposed method
!
Comparis...
FACE DETECTOR
Experiments over Honda/UCSD Video Database [1] [2]
Proposed method (left)Viola-Jones (right)
[1] K.C. Lee J....
FACE DETECTOR
!
!
[3] Y. Wong, S. Chen, S. Mau, C. Sanderson, B.C. Lovell Patch-based probabilistic image quality assessme...
FACIAL FEATURES
EXTRACTION
Wednesday, August 28, 13
FACIAL FEATURES
EXTRACTION
Wednesday, August 28, 13
CURRENT RESULTS
• Complex FaceTracking
• Facial FeaturesTracking
Wednesday, August 28, 13
DISCUSSION
• Time/Breathing constraint
• Quality of the Breathing information
• [Low / High] Resolution
• Current approach...
Thanks...
Wednesday, August 28, 13
Upcoming SlideShare
Loading in...5
×

Facial Features Extraction

245

Published on

Final Presentation of my Summer Research Internship in the Biometrics Technologies Laboratory at the University of Calgary, Canada. Scholarship granted by MITACS Globalink program.

Published in: Technology, News & Politics
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
245
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
12
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Transcript of "Facial Features Extraction"

  1. 1. FACIAL FEATURES EXTRACTION USING PHASED BASEDVIDEO AMPLIFICATION Coutino Minguez, Mario Alberto University of Calgary Summer 2013 Wednesday, August 28, 13
  2. 2. OBJECTIVE • Detection and tracking of facial features in video sequences in an automatic manner. Wednesday, August 28, 13
  3. 3. PROPOSAL • Subtle motion is produced in specific facial features during the normal human’s breathing. • Amplifying the present in the face using the Phase - Based Motion Amplification method [Wadhwa et al. 2013] deliver useful information to estimate the position of nose, eyebrows, eyes and mouth. • Statistical analysis of the data to improve accuracy over time. Wednesday, August 28, 13
  4. 4. APPROACH Wednesday, August 28, 13
  5. 5. APPROACH Wadhwa et. al 2013 Wednesday, August 28, 13
  6. 6. METHODOLOGY Wednesday, August 28, 13
  7. 7. PARTIAL RESULTS • Face’sTracking Results • Eyebrows’ Detection Results Wednesday, August 28, 13
  8. 8. FACE DETECTOR Comparison:Viola-Jones (left) Proposed method (right) Partial faces results using proposed method ! Comparison: Proposed method (right)Viola-Jones (right) Wednesday, August 28, 13
  9. 9. FACE DETECTOR Experiments over Honda/UCSD Video Database [1] [2] Proposed method (left)Viola-Jones (right) [1] K.C. Lee J. Ho M.H. Yang and D. Kriegman. Video-based face recognition using probabilistic appearance manifolds. IEEE Conf. On Computer Vision and Pattern Recognition, 1:313–320, 2003. [2] K.C. Lee J. Ho M.H. Yang and D. Kriegman. Visual tracking and recognition us- ing probabilistic appearance manifolds. Computer Vision and Image Understanding, 2005. Wednesday, August 28, 13
  10. 10. FACE DETECTOR ! ! [3] Y. Wong, S. Chen, S. Mau, C. Sanderson, B.C. Lovell Patch-based probabilistic image quality assessment for face selection and improved video- based face recognition Computer Vision and Pattern Recognition Workshops (CVPRW), pages 74 - 81, 2011. [4] T. Baltrušaitis, P. Robinson, and L.P. Morency 3D Constrained Local Model for Rigid and Non-Rigid Facial Tracking in IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, June 2012 Results extracted from Choke Point Database [3] Results extracted from ICT 3D HeadPose Database [4] Wednesday, August 28, 13
  11. 11. FACIAL FEATURES EXTRACTION Wednesday, August 28, 13
  12. 12. FACIAL FEATURES EXTRACTION Wednesday, August 28, 13
  13. 13. CURRENT RESULTS • Complex FaceTracking • Facial FeaturesTracking Wednesday, August 28, 13
  14. 14. DISCUSSION • Time/Breathing constraint • Quality of the Breathing information • [Low / High] Resolution • Current approach • Face: Ellipse fitting • Facial Features: Gradient-based Wednesday, August 28, 13
  15. 15. Thanks... Wednesday, August 28, 13
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×