csPresentation - Face Recognition in the Real World A...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

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

Unformatted text preview: Face Recognition in the Real World: A Compressive Sensing Perspective Face Recognition in the Real World: A Compressive Sensing Perspective Ragib Morshed Advisor: Tzu-Yi Chen April 24, 2009 Face Recognition in the Real World: A Compressive Sensing Perspective Outline 1 What is face recognition? 2 Classical approaches to face recognition 3 Compressive Sensing 4 New face recognition technique 5 Performance of algorithm in the real world 6 Most Likelihood (ML) approach 7 Conclusion and Future Work Face Recognition in the Real World: A Compressive Sensing Perspective What is face recognition? Face recognition What is face recognition? Given a static image (or video), automatically identify faces in the image using a known database of faces and names. Face Recognition in the Real World: A Compressive Sensing Perspective What is face recognition? Face recognition What is face recognition? Given a static image (or video), automatically identify faces in the image using a known database of faces and names. Face Recognition in the Real World: A Compressive Sensing Perspective What is face recognition? Components of a face recognition system Face detection Segmentation of faces Database of faces with names Recognition Each image mapped to an individual present in the database Input image Figure: The different components of a face recognition system Face Recognition in the Real World: A Compressive Sensing Perspective What is face recognition? Flickr Figure: Use of face recognition in Flickr Face Recognition in the Real World: A Compressive Sensing Perspective What is face recognition? Picasa Figure: Use of face recognition in Google’s Picasa Face Recognition in the Real World: A Compressive Sensing Perspective What is face recognition? Problems with such systems Some major issues Occlusion. Corruption with noise. Limited to frontal views. Face Recognition in the Real World: A Compressive Sensing Perspective Classical approaches to face recognition Features Also known as landmarks What constitutes features? Eyes, nose, mouth, cheekbones, jaw, etc. Relative positions, size and/or shape. Face Recognition in the Real World: A Compressive Sensing Perspective Classical approaches to face recognition Classical face recognition techniques Eigenface Dimensionality reduction using Principal Component Analysis (PCA). Support Vector Machine (SVM) Machine learning approach - supervised learning. Learning to differentiate image classes. Face Recognition in the Real World: A Compressive Sensing Perspective Classical approaches to face recognition Problems with classical techniques Problems with Eigenface Computationally intensive....
View Full Document

This note was uploaded on 05/28/2010 for the course EE EE564 taught by Professor Runyiyu during the Spring '10 term at Eastern Mediterranean University.

Page1 / 37

csPresentation - Face Recognition in the Real World A...

This preview shows document pages 1 - 12. Sign up to view the full document.

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