Seminar on Media Technology Computer Vision Albert Alemany Font.

30
Seminar on Media Technology Computer Vision Albert Alemany Font

Transcript of Seminar on Media Technology Computer Vision Albert Alemany Font.

Page 1: Seminar on Media Technology Computer Vision Albert Alemany Font.

Seminar on Media Technology

Computer Vision

Albert Alemany Font

Page 2: Seminar on Media Technology Computer Vision Albert Alemany Font.

Outlines Introduction

• What is computer vision and why this topic

History of computer vision and related disciplines

Applications

• Face/smile detection, OCR, object recognition, medical imaging, ...

Conclusions References

Page 3: Seminar on Media Technology Computer Vision Albert Alemany Font.

What is computer vision?

Traffic scene Number of vehicles Type of vehicles Location of closest

obstacle Assessment of

congestion Location of the scene

captures ...

Given an image or more, extract properties of the 3D

world

Page 4: Seminar on Media Technology Computer Vision Albert Alemany Font.

Related disciplines

Page 5: Seminar on Media Technology Computer Vision Albert Alemany Font.

History of computer vision 1950′s – Two dimensional imaging for statistical

pattern recognition developed

1960′s – Roberts begins studying 3D machine vision

1970′s – MIT’s Artificial Intelligence Lab opens a "Computer Vision" course

1980’s – New theories and concepts emerging. Shift toward geometry and increased mathematical rigor

1990’s – Face recognition. Statistical analysis in vogue

2000’s – Broader recognition. Large annotated datasets available. Video processing starts

Page 6: Seminar on Media Technology Computer Vision Albert Alemany Font.

Finding people in images"Yes"

instances

Page 7: Seminar on Media Technology Computer Vision Albert Alemany Font.

Finding people in images"No"

instances

Page 8: Seminar on Media Technology Computer Vision Albert Alemany Font.

Face detection

The camera detects faces in a scene and then automatically focus (AF) and optimizes exposure (AE) and, if needed, flash output

Face detection in digital cameras

Page 9: Seminar on Media Technology Computer Vision Albert Alemany Font.

Smile detection

Page 10: Seminar on Media Technology Computer Vision Albert Alemany Font.

Optical character recognition (OCR)

Technology to convert scanned docs to text

Page 11: Seminar on Media Technology Computer Vision Albert Alemany Font.

Vision-based biometrics

http://www.cl.cam.ac.uk/~jgd1000/afghan.html

Photographer: Steve McCurry

How the Afghan girl was identified by her iris pattern:

1984 - Right eye processed image

2002 - Right eye processed image

Page 12: Seminar on Media Technology Computer Vision Albert Alemany Font.

Object recognition

Google goggles

Query image

Webpage

Matching image

Lincoln Microsoft Research

Page 13: Seminar on Media Technology Computer Vision Albert Alemany Font.

Mimic human behaviour?

Page 14: Seminar on Media Technology Computer Vision Albert Alemany Font.

Limits of human vision

Page 15: Seminar on Media Technology Computer Vision Albert Alemany Font.

Limits of human vision

Page 16: Seminar on Media Technology Computer Vision Albert Alemany Font.

Vision evolution

Google reCaptcha

Page 17: Seminar on Media Technology Computer Vision Albert Alemany Font.

Making the invisible visible

Eulerian Video Magnification for Revealing Subtle Changes in the WorldSIGGRAPH

2012http://people.csail.mit.edu/mrub/

vidmag/

Raw version

Page 18: Seminar on Media Technology Computer Vision Albert Alemany Font.

Making the invisible visible

Eulerian Video Magnification for Revealing Subtle Changes in the Worldhttp://people.csail.mit.edu/mrub/

vidmag/

Magnified version

SIGGRAPH 2012

Page 19: Seminar on Media Technology Computer Vision Albert Alemany Font.

Smart cars

www.mobileye.com

Page 20: Seminar on Media Technology Computer Vision Albert Alemany Font.

Medical imaging

Image guided surgery

3D Imaging

Page 21: Seminar on Media Technology Computer Vision Albert Alemany Font.

Special effects: shape capture

The Matrix movies, ESC Entertainment

Page 22: Seminar on Media Technology Computer Vision Albert Alemany Font.

Special effects: shape capture

Page 23: Seminar on Media Technology Computer Vision Albert Alemany Font.

Special effects: motion capture

Pirates of the caribbean, Industrial Light and Magic

Page 24: Seminar on Media Technology Computer Vision Albert Alemany Font.

Video-based interaction: gaming

Sony Eyetoy

Microsoft Natal

Page 25: Seminar on Media Technology Computer Vision Albert Alemany Font.

Image mosaic

3D from multiple images 3D from one image "Big" image from other

images/video

Page 26: Seminar on Media Technology Computer Vision Albert Alemany Font.

Image mosaic

Page 27: Seminar on Media Technology Computer Vision Albert Alemany Font.

Supermarket scanner

Page 28: Seminar on Media Technology Computer Vision Albert Alemany Font.

Conclusions

Page 29: Seminar on Media Technology Computer Vision Albert Alemany Font.

References

Richard Szeliski (2010). Computer Vision: Algorithms and Applications. Springer-Verlag.

Gérard Medioni and Sing Bing Kang (2004). Emerging Topics in Computer Vision. Prentice Hall.

Pedram Azad, Tilo Gockel, Rüdiger Dillmann (2008). Computer Vision – Principles and Practice. Elektor International Media BV.

http://people.csail.mit.edu/mrub/vidmag/

http://www.cvpapers.com/

Page 30: Seminar on Media Technology Computer Vision Albert Alemany Font.

Thank you for your attention