L10(FacRec)

L10(FacRec) - An Overview of Face Recognition Using...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
1 April 2004 Eigenfaces 1 An Overview of Face Recognition Using An Overview of Face Recognition Using Eigenfaces Eigenfaces Acknowledgements: Original Slides from Prof. Matthew Turk -- also notes from the web -Eigenvalues and Eigenvectors -PCA -Eigenfaces Outline Outline ± Why automated face recognition? ± Eigenfaces and appearance-based approaches to recognition – Motivation – Review ± Why Eigenfaces? ± Why not Eigenfaces? ± Where shall we go from here?
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Why Automated Face Recognition? Why Automated Face Recognition? ± It is a very vital and compelling human ability – Faces are important to us – Severe social problem for people who lack this ability ± It’s fun to work on – Better than recognizing tanks and sprockets ± Good, paradigmatic vision problem ± It may actually be useful – Biometrics, HCI, surveillance, … ± They can do it in the movies! Commercial Interest Commercial Interest ± Image and video indexing ± Biometrics, e-commerce – Visionics, Viisage, eTrue, … ± Surveillance – Casinos, Super Bowl, Tampa, FL
Background image of page 2
3 Automated Face Recognition Automated Face Recognition ± Typical formulations: – Given an image of a face, who is it? (recognition) – Is this an image of Joe Schmoe? (verification) ± Why isn’t this easy? The Problem The Problem ± The human face is an extremely complex object, highly deformable, with both rigid and non-rigid components that vary over time, sometimes quite rapidly and sometimes quite slowly ± The “object” is covered with skin, a non- uniformly textured material that is difficult to model either geometrically or photometrically
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 The Problem The Problem ± Time-varying changes include: – The growth and removal of facial hair, wrinkles and sagging of the skin brought about by aging, skin blemishes, changes in skin color and texture caused by exposure to sun, etc. ± Plus many common artifact-related changes: – Glasses, makeup, jewelry, piercings, cuts and scrapes, bandages, etc. ± Not to mention facial expressions, changes in hairstyle, etc. The Problem The Problem ± In general, object recognition is difficult because of the immense variability of object appearance ± Several factors are all confounded in the image data – Shape, reflectance, pose, occlusion, illumination ± Human faces add more factors – Expression, facial hair, jewelry, etc. ± So… one may argue that face recognition is harder than most object recognition tasks
Background image of page 4
5 The Problem The Problem ± Overcoming these difficulties will be a significant step forward for the computer vision community ± So, face recognition has been considered a challenging problem in computer vision for some time now ± The amount of effort in the research community devoted to this topic has increased significantly over the years.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 18

L10(FacRec) - An Overview of Face Recognition Using...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online