Chapter 1: Computer Vision Introduction.pptx
- 1. 1 Chapter 1: Computer Vision Introduction
- 2. Materials & Books 2 PDF online: http://szeliski.org/Book/
- 4. Final Exam: 60 presentation : 15 Final Project and report : 25 introduction 4 Requirements and Grading
- 6. What a person sees
- 7. What a computer sees
- 8. Why are we able to interpret this image?
- 9. Vision is the process of discovering what is present in the world and where it is by looking. Vision
- 10. Computer Vision allows the computer to see and understand the scene Computer Vision
- 11. Human perception has its shortcomings Sinha and Poggio, Nature, 1996 (“The Presidential Illusion”)
- 12. But humans can tell a lot about a scene from a little information… What can you see in this image? Human is more efficient than computer Human Tracking in crowded scene, what you think? Computer is more efficient than human
- 14. The goal of computer vision Recognize objects and people Terminator 2, 1991
- 17. The goal of computer vision Forensics Source: Nayar and Nishino, “Eyes for Relighting”
- 18. Source: Nayar and Nishino, “Eyes for Relighting
- 19. Source: Nayar and Nishino, “Eyes for Relighting”
- 20. The goal of computer vision Improve photos (“Computational Photography”) Inpainting / image completion (image credit: Hays and Efros) Super-resolution (source: 2d3) Low-light photography (credit: Hasinoff et al., SIGGRAPH ASIA 2016 Depth of field on cell phone camera (source: Google Research Blog)
- 21. Optical character recognition (OCR) Digit recognition, AT&T labs (1990’s) License plate readers Automatic check processing
- 22. Face detection Nearly all cameras detect faces in real time
- 23. Face Recognition
- 24. Vision-based biometrics “How the Afghan Girl was Identified by Her Iris Patterns” Read the story Source: S. Seitz
- 25. Login without a password Fingerprint scanners on many new smartphones and other devices Face unlock on Apple iPhone X See also http://www.sensiblevision.com/
- 26. Sports Sportvision first down line Nice explanation on www.howstuffworks.com Source: S. Seitz
- 27. Medical imaging 3D imaging (MRI, CT) Skin cancer classification with deep learning https://cs.stanford.edu/people/esteva/nature/
- 28. It’s a good time to do computer vision
- 29. Why is computer vision difficult? Viewpoint variation Illumination Scale
- 30. Why is computer vision difficult? Intra-class variation Background clutter Motion (Source: S. Lazebnik)
- 31. Computer Vision Robotics Neuroscience Graphics Computationa l Photography Machine Learning Medical Imaging Human Computer Interaction Optics Image Processing Feature Matching Recognition
- 32. Project Proposal Written project proposal in pdf format. Submit early for early feedback, but no later than deadline. Proposal must contain: Title Names of all team members. Description of the goals of the project and the work to be carried out (200-400 words). + references. Indication whether you will use an Android device. If proposal is not acceptable, a revision wil4l 8 be requested
- 33. Project group Group project, teams of typically 3-4 students. 49