![Pixels can be manipulated I I>100 Conv2(I,[-1 1]) For more on image convolution, please google: “ image convolution gamedev”](https://image.slidesharecdn.com/object-recognition-seminar-s2006e01-22339/85/Object-recognition-seminar-S2006E01-13-320.jpg)
Object recognition seminar S2006E01
- 1. Advanced seminar: Visual Object Recognition Dr. Lior Wolf School of Computer Science , Tel Aviv University
- 2. Credit: www . scholastic . com
- 3. Administrivia Mondays 13:00-15:00, unless.. Dan David classrooms, room 106 A 13 weeks seminar, unless.. Grading: 80% class presentation or class project 20% active participation in class Office hours: Wednesdays 13:00-15:00
- 4. Example tasks: Street scene understanding Face detection Face identification Image categorization Pose estimation Motion and behavior analysis
- 5. Street scene understanding Watch Out! Probably Hanging Out Credit: Stan Bileschi, CBCL
- 6. Face detection Credit: Intel Technology Journal, Volume 09, Issue 01
- 7. Face identification Credit: www . security - lab . com
- 8. Image categorization Images courtesy of Mobileye
- 9. Pose estimation Credit: Thomas Izo, CSAIL
- 10. Motion recognition Ballet turn: Input video: Output: The “Birmingham Royal Ballet” Credit: Eli Shechtman and Michal Irani
- 11. Basic image processing: Basic image operators Template matching Image transformations
- 12. An image is an array of pixels Credit: H. Joel Trussell, Eli Saber, and Michael Vrhel
- 13. Pixels can be manipulated I I>100 Conv2(I,[-1 1]) For more on image convolution, please google: “ image convolution gamedev”
- 14. Template matching Credit: F. Patin, gamedev.net
- 15. Fourier Transform Credit: R. Fisher, S. Perkins, A. Walker and E. Wolfart.
- 16. Major scheme: Image representation: features Object learning: classification Credit: B. Heisele, Y. Ivanov, T. Poggio
- 17. Image features “ The most important element” (?) Example: David Lowe’s SIFT descriptor Credit: David Lowe
- 18. Image features “ The most important element” (?) Example: David Lowe’s SIFT descriptor Credit: David Lowe
- 19. Classification Credit: B. Heisele, Y. Ivanov, T. Poggio
- 20. Challenges: Too many to list..
- 21. Challenges 1: view point variation Michelangelo 1475-1564 slide by Fei Fei, Fergus & Torralba
- 22. Challenges 2: illumination slide credit: S. Ullman
- 23. Challenges 3: occlusion Magritte, 1957 slide by Fei Fei, Fergus & Torralba
- 24. Challenges 4: scale slide by Fei Fei, Fergus & Torralba
- 25. Challenges 5: deformation Xu, Beihong 1943 slide by Fei Fei, Fergus & Torralba
- 26. Challenges 6: background clutter Klimt, 1913 slide by Fei Fei, Fergus & Torralba
- 27. Challenges 7: object intra-class variation slide by Fei-Fei, Fergus & Torralba
- 28. Challenges 8: local ambiguity slide by Fei-Fei, Fergus & Torralba
- 29. Challenges 9: the world behind the image Credit: A. Efros