• Share
  • Email
  • Embed
  • Like
  • Save
  • Private Content
Real-time Face Detection and Recognition
 

Real-time Face Detection and Recognition

on

  • 1,033 views

Code:

Code:

https://github.com/amitra93/FaceRecognition

Statistics

Views

Total Views
1,033
Views on SlideShare
1,033
Embed Views
0

Actions

Likes
0
Downloads
4
Comments
0

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

    Real-time Face Detection and Recognition Real-time Face Detection and Recognition Document Transcript

    • Zelun Luo, Anarghya MitraMentor: Jia-Bin Huang. Advisor: Narendra Ahuja.Department of Electrical and Computer EngineeringUniversity of Illinois at Urbana-ChampaignMake a robust system capable of identifying multiple faces with alearning algorithm for identifying faces not in its database.Integral ImageCascade ArchitectureHaar-like Features• Very few faces in an image• Most sub-windows rejectedearly since they are notfaces• Each successive classifieris trained only on thoseselected samples whichpass through thepreceding classifiers.s(1) = As(2) = A + Bs(3) = A + Cs(4) = A + B + C + DThe sum within D can becomputed as:s(4)+s(1)-s(2)-s(3).(x, y)A BC D1 23 4The value of the integral imageat point (x, y) is the sum of allthe pixels above and to the leftof x, y, inclusive:where s(x, y) is the integralimage and i(x, y) is the originalimage.• The area around theeyes is lighter thanthe eyes itself – i.e.the nose is brighterthan the eyes on anormalized graph.• The area on top andbelow the eyes islighter than theeyes.Our face can be used to controlcomputers. One example is agame we can play with ournose acting as the mouse.Main ideas -• Very few faces in an image => cascade structure of weakclassifiers• Evaluate haar-like features in O(1) time using integralimage• Select discriminative features with Adaboost[Viola & Jones, 2004] Viola, P. & Jones, M. J. (2004). Robust real-time facedetection. International journal of computer vision, 57(2), 137–154.[Yang, 2002] Yang, M.-H. (2002). Kernel eigenfaces vs. kernel fisherfaces:Face recognition using kernel methods. In Proceedings of the Fifth IEEEInternational Conference on Automatic Face and Gesture RecognitionOriginal images• Eigenfaces encode the variationin the training set.• Each image can be representedusing a linear combination ofeigenfaces.Can be used in identityverification along withfingerprint and iris recognitionsystems.Reconstructionusing eigenfaces