Face And Ear Composite Recognition Tool

2,599 views

Published on

My Final year project :) It was used to compare two faces and ears. Used matlab for it.

Published in: Technology, News & Politics
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
2,599
On SlideShare
0
From Embeds
0
Number of Embeds
10
Actions
Shares
0
Downloads
147
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

Face And Ear Composite Recognition Tool

  1. 1. Face and Ear Composite Recognition Tool Abhineet Bhamra (0131322804) Ashish Goel (0181322804) Jaideep Singh (0161322804) Karan Gogna (0361322804)
  2. 2. Contents <ul><li>Project Goals </li></ul><ul><li>Introduction to Biometrics </li></ul><ul><li>Face Biometrics </li></ul><ul><li>Ear Biometrics </li></ul><ul><li>Advantages of Ear Biometrics </li></ul><ul><li>Implementation </li></ul><ul><li>Work completed </li></ul><ul><li>Work to be done </li></ul><ul><li>References </li></ul>
  3. 3. Project Goals <ul><li>To use both face and ear recognition techniques in a single tool for enhanced security and flexibility </li></ul><ul><li>Compare the performance of both biometrics </li></ul><ul><li>Identify common sources of errors for both techniques </li></ul>
  4. 4. Introduction to Biometrics <ul><li>Definition : Automatic identification of a living person based on physiological or behavio u ral characteristics . </li></ul><ul><li>Behavioral </li></ul><ul><ul><li>Voice </li></ul></ul><ul><ul><li>Signature </li></ul></ul><ul><ul><li>Keystrokes </li></ul></ul><ul><li>Physiological </li></ul><ul><ul><li>Fingerprints </li></ul></ul><ul><ul><li>Hand Geometry </li></ul></ul><ul><ul><li>Iris </li></ul></ul><ul><ul><li>Face </li></ul></ul><ul><ul><li>Ear </li></ul></ul>
  5. 5. Face Biometrics <ul><li>Passive physiological method </li></ul><ul><li>Natural method – humans recognize people by looking at their faces </li></ul><ul><li>Fast development of new algorithms </li></ul><ul><li>Still many unsolved problems including compensation of illumination changes and pose invariance </li></ul>
  6. 6. Ear Biometrics <ul><li>Human ears have been used as major feature in the forensic science for many years </li></ul><ul><li>Human ear contains large amount of specific and unique features that allows for human identification </li></ul><ul><li>Ear images can be easily taken from a distance and without knowledge of the examined person </li></ul><ul><li>Suitable for security, surveillance, access control and monitoring applications </li></ul>
  7. 7. Advantages of Ear Biometrics <ul><li>Ear does not change during human life, and face changes more significantly with age than any other part of human body </li></ul><ul><li>Colour distribution is more uniform in ear than in human face, iris or retina </li></ul><ul><ul><li>Not much information is lost while working with the greyscale or binarized images </li></ul></ul><ul><li>Ear is also smaller than face , which means that it is possible to work faster and more efficiently with the images with the lower resolution </li></ul><ul><li>Ear images cannot be disturbed by glasses, beard nor make-up. However, occlusion by hair or earrings is possible </li></ul>
  8. 8. Implementation <ul><li>Acquiring an image of the subject from scanner/digital camera/video recording </li></ul><ul><li>Detect the location of any face or ear in the image </li></ul><ul><li>Analysis of the spatial geometry of distinguishing features of face/ear and generate a template </li></ul><ul><li>Compare the template with those in the database of known faces/ears </li></ul><ul><li>Declare match or mismatch depending on the similarity and security configuration </li></ul>
  9. 9. Work completed <ul><li>Feature extraction and building a database using PCA – eigenfaces and eigenears approach </li></ul><ul><li>Recognition of face and ear images by comparison with face and ear databases respectively and calculation of Euclidean distance </li></ul><ul><li>[Please add some other stuff too that u think we can show] </li></ul>
  10. 10. Work to be done <ul><li>Automatic extraction of face and ear from corresponding images </li></ul><ul><li>Implementation of other algorithms and a comparison of their performance </li></ul><ul><li>Integration of both face and ear recognition in a single tool </li></ul><ul><li>Development of GUI </li></ul><ul><li>Comparison of face and ear as a biometric </li></ul><ul><li>Identify reasons for error/limitations of the tool developed </li></ul>
  11. 11. References (to be updated) <ul><li>John D. Woodward, Jr., Christopher Horn, Julius Gatune, and Aryn Thomas: “ Biometrics - A Look at Facial Recognition ”, RAND Public Safety and Justice, 2003 </li></ul><ul><li>Lammi, Hanna-Kaisa: “ Ear Biometrics ”. Lappeenranta University of Technology, Department of Information Technology, Laboratory of Information Processing, P.O. BOX 20, 53851 Lappeenranta, Finland </li></ul><ul><li>Burge, M. and Burger, W. “ Ear Biometrics in Computer Vision ”. In the 15th International Conference of Pattern Recognition, ICPR 2000. </li></ul><ul><li>Wikipedia: http:// en.wikipedia.org/wiki/Biometrics </li></ul>
  12. 12. Thank You

×