15
Face recognition via sparse representation

Face recognition via sparse representation

  • Upload
    floria

  • View
    45

  • Download
    0

Embed Size (px)

DESCRIPTION

Face recognition via sparse representation. Breakdown. Problem Classical techniques New method based on sparsity Results. Classical Techniques. Eigenfaces Uses PCA for feature extraction Problems faced Extremely intensive Poor results when there’s no frontal view - PowerPoint PPT Presentation

Citation preview

Page 1: Face recognition via sparse representation

Face recognition via sparse representation

Page 2: Face recognition via sparse representation

Breakdown• Problem • Classical techniques• New method based on sparsity• Results

Page 3: Face recognition via sparse representation

Classical Techniques• Eigenfaces

• Uses PCA for feature extraction

• Problems faced• Extremely intensive• Poor results when there’s no frontal view• Poor results with bad lighting• Poor results with noise

Page 4: Face recognition via sparse representation

Classical Techniques• Support Vector Machines

• PCA for feature extraction• Radial Basis function• One versus all classifier

• Problems faced• Extremely intensive• Poor results with bad lighting• Sensitive to noise

Page 5: Face recognition via sparse representation

Via sparse representation• Redundancy• As the number of image pixels is far greater than the number of

subjects that have generated the images

• Robustness from sparsity• Identity of the test image• Nature of occlusion

Page 6: Face recognition via sparse representation

Problem• A w x h image is identified as a vector v ϵ Rm

given by stacking columns• A = [v1 v2 v3 v4,…..,vn] ϵ R mxn

• A test image y = Aixi, assuming no occlusion

where y = test image of the ith object

Page 7: Face recognition via sparse representation

• If ρ is the fraction of pixels occluded, • y = y0 + e = Ax0 + e

Problem statement:

Given A1, A2, A3,…., Ak & y by sampling an image from the ith class & perturbing the values of ρ of its pixels arbitrarily, find the correct class.

Page 8: Face recognition via sparse representation

• ẋ2 = arg min || y – Ax ||2X

• Error is non-Gaussian so this can give a lot of erroneous results

• Exploit sparsity of residue:• X0 = arg min || y – Ax ||0

X

• l1 is same as l0, sometimes.

Page 9: Face recognition via sparse representation

Algorithm• n training samples partitioned into k classes• B = [A1 A1….An I], normalize to have unit l2 norm.

• ẃ1 = arg min ||w||1 S.T Bw = y

w

• Residuals ri(y) = ||y – Aδi(ẋ1) – ê1||2 for i = 1,2,….k.

• Output = arg mini ri(y).

Page 10: Face recognition via sparse representation

Dataset• Extended Yale B dataset• 38 subjects• 717 images for training and 453 for testing

Page 11: Face recognition via sparse representation

RESULTS

Page 12: Face recognition via sparse representation

1. Random pixel corruption

Page 13: Face recognition via sparse representation

2. Random block occlusion

Page 14: Face recognition via sparse representation

Recognition despite disguise

Page 15: Face recognition via sparse representation

THANK YOU