Download Face Detection and Face Recognition PowerPoint Presentation

Login   OR  Register

Share on Social Media


Home / Science & Technology / Science & Technology Presentations / Face Detection and Face Recognition PowerPoint Presentation

Face Detection and Face Recognition PowerPoint Presentation

worldwideweb By : worldwideweb

On : Jan 08, 2015

In : Science & Technology

Embed :

Login / Signup - with account for

  • → Make favorite
  • → Flag as inappropriate
  • → Download Presentation
  • → Share Presentation
  • Slide 1 - Face Recognition: An Introduction
  • Slide 2 - Face
  • Slide 3 - Face Recognition Face is the most common biometric used by humans Applications range from static, mug-shot verification to a dynamic, uncontrolled face identification in a cluttered background Challenges: automatically locate the face recognize the face from a general view point under different illumination conditions, facial expressions, and aging effects
  • Slide 4 - Authentication vs Identification Face Authentication/Verification (1:1 matching) Face Identification/Recognition (1:N matching)
  • Slide 5 - www.viisage.com  Access Control Applications www.visionics.com
  • Slide 6 -  Video Surveillance (On-line or off-line) Applications Face Scan at Airports www.facesnap.de
  • Slide 7 - Why is Face Recognition Hard? Many faces of Madonna
  • Slide 8 - Face Recognition Difficulties Identify similar faces (inter-class similarity) Accommodate intra-class variability due to: head pose illumination conditions expressions facial accessories aging effects Cartoon faces
  • Slide 9 - Inter-class Similarity Different persons may have very similar appearance Twins Father and son www.marykateandashley.com news.bbc.co.uk/hi/english/in_depth/americas/2000/us_elections
  • Slide 10 - Intra-class Variability Faces with intra-subject variations in pose, illumination, expression, accessories, color, occlusions, and brightness
  • Slide 11 - Sketch of a Pattern Recognition Architecture Feature Extraction Classification Image (window) Object Identity Feature Vector
  • Slide 12 - Example: Face Detection Scan window over image Classify window as either: Face Non-face
  • Slide 13 - Detection Test Sets
  • Slide 14 - Profile views Schneiderman’s Test set
  • Slide 15 - Face Detection: Experimental Results Test sets: two CMU benchmark data sets Test set 1: 125 images with 483 faces Test set 2: 20 images with 136 faces [See also work by Viola & Jones, Rehg, more recent by Schneiderman]
  • Slide 16 - Example: Finding skin Non-parametric Representation of CCD Skin has a very small range of (intensity independent) colors, and little texture Compute an intensity-independent color measure, check if color is in this range, check if there is little texture (median filter) See this as a classifier - we can set up the tests by hand, or learn them. get class conditional densities (histograms), priors from data (counting) Classifier is
  • Slide 17 - Figure from “Statistical color models with application to skin detection,” M.J. Jones and J. Rehg, Proc. Computer Vision and Pattern Recognition, 1999 copyright 1999, IEEE
  • Slide 18 - Face Detection
  • Slide 19 - Face Detection Algorithm Face Localization Lighting Compensation Skin Color Detection Color Space Transformation Variance-based Segmentation Connected Component & Grouping Face Boundary Detection Verifying/ Weighting Eyes-Mouth Triangles Eye/ Mouth Detection Facial Feature Detection Input Image Output Image
  • Slide 20 - Canon Powershot
  • Slide 21 - Face Recognition: 2-D and 3-D 2-D Face Database 2-D Recognition Data Recognition Comparison Prior knowledge of face class
  • Slide 22 - Pose-dependent Algorithms Pose-invariant Pose-dependency Matching features Appearance-based (Holistic) -- Gordon et al., 1995 Feature-based (Analytic) Hybrid Viewer-centered Images -- Lengagne et al., 1996 -- Atick et al., 1996 Object-centered Models -- Yan et al., 1996 -- Zhao et al., 2000 Face representation -- Zhang et al., 2000 PCA, LDA LFA EGBM Taxonomy of Face Recognition
  • Slide 23 - Image as a Feature Vector Consider an n-pixel image to be a point in an n-dimensional space, x Rn. Each pixel value is a coordinate of x.
  • Slide 24 - Nearest Neighbor Classifier { Rj } are set of training images.
  • Slide 25 - Comments Sometimes called “Template Matching” Variations on distance function (e.g. L1, robust distances) Multiple templates per class- perhaps many training images per class. Expensive to compute k distances, especially when each image is big (N dimensional). May not generalize well to unseen examples of class. Some solutions: Bayesian classification Dimensionality reduction
  • Slide 26 - Eigenfaces (Turk, Pentland, 91) -1 Use Principle Component Analysis (PCA) to reduce the dimsionality
  • Slide 27 - How do you construct Eigenspace? [ ] [ ] [ x1 x2 x3 x4 x5 ] W Construct data matrix by stacking vectorized images and then apply Singular Value Decomposition (SVD)
  • Slide 28 - Eigenfaces Modeling Given a collection of n labeled training images, Compute mean image and covariance matrix. Compute k Eigenvectors (note that these are images) of covariance matrix corresponding to k largest Eigenvalues. Project the training images to the k-dimensional Eigenspace. Recognition Given a test image, project to Eigenspace. Perform classification to the projected training images.
  • Slide 29 - Eigenfaces: Training Images [ Turk, Pentland 01
  • Slide 30 - Eigenfaces Mean Image Basis Images
  • Slide 31 - Difficulties with PCA Projection may suppress important detail smallest variance directions may not be unimportant Method does not take discriminative task into account typically, we wish to compute features that allow good discrimination not the same as largest variance
  • Slide 32 - ppt slide no 32 content not found
  • Slide 33 - Fisherfaces: Class specific linear projection An n-pixel image xRn can be projected to a low-dimensional feature space yRm by y = Wx where W is an n by m matrix. Recognition is performed using nearest neighbor in Rm. How do we choose a good W?
  • Slide 34 - PCA & Fisher’s Linear Discriminant Between-class scatter Within-class scatter Total scatter Where c is the number of classes i is the mean of class i | i | is number of samples of i..
  • Slide 35 - PCA & Fisher’s Linear Discriminant PCA (Eigenfaces) Maximizes projected total scatter Fisher’s Linear Discriminant Maximizes ratio of projected between-class to projected within-class scatter 1 2
  • Slide 36 - Four Fisherfaces From ORL Database
  • Slide 37 - Eigenfaces and Fisherfaces
  • Slide 38 - ppt slide no 38 content not found

Description : PowerPoint presentation on Face Detection and Face Recognition, download now ppt of Face Detection and Face Recognition

Tags : Face Detection and Face Recognition