Your SlideShare is downloading. ×
0
Applying Computer
Vision to Art History
John Resig - http://ejohn.org/research/
Visiting Researcher, Ritsumeikan Universit...
What “Works” Today
Reading license plates, zip codes, checks
Optical Character
Recognition
• Tesseract
• https://

code.google.com/
p/tesseract-ocr/
What “Works” Today
Face recognition
Face Matching

• OpenBR
• http://openbiometrics.org/
What “Works” Today
Recognition of flat, textured, objects
Computer Vision
• Unsupervised (requires no labeling):
• Comparing an entire image
• Categorizing an image
• Supervised (r...
Unsupervised Training
• Requires little-to-no prepping of data
• Can just give the tool a set of images and
have it produc...
Supervised Training
• Need lots of training data
• Needs to be pre-selected/categorized
• Think: Thousands of images.
• If...
Image Similarity
• imgSeek (Open Source)
• http://www.imgseek.net/
• TinEye’s MatchEngine
• http://services.tineye.com/Mat...
imgSeek
• Compares entire
image.

• Finds similar images,
not exact.

• Does not find parts of
an image.

• Color sensitive...
• Compares

portions of
images.

• Finds exact
matches.

• Finds images
inside other
images.

• Color
Ukiyo-e.org (Using M...
Anonymous Italian Art (Frick PhotoArchive)
Using MatchEngine
Conservation
Copies
Image Portion

Partial Image vs. Much Larger Image
Image Categorization
• Deep neural networks
• Requires minimal categorization
• Very little user-input required.
• Ersatz
...
Requires a lot of training
data (thousands of images)
Takes a lot of computers
(Not cheap)
The less categories you
have, t...
General Computer
Vision
• Ideal for some supervised training problems
• CCV
• http://libccv.org/
• https://github.com/liul...
Object Detection
Training Caveats
• Requires thousands (if not 10s of
thousands) of images

• Will take at least a week to run on a very
po...
Learn More about
Computer Vision
• Learn more:
• http://cs.brown.edu/courses/csci1430/
• Just published paper on Frick Com...
Applying Computer Vision to Art History
Applying Computer Vision to Art History
Applying Computer Vision to Art History
Applying Computer Vision to Art History
Applying Computer Vision to Art History
Applying Computer Vision to Art History
Applying Computer Vision to Art History
Upcoming SlideShare
Loading in...5
×

Applying Computer Vision to Art History

1,086

Published on

From the February 11th 2014 THATCamp CAA session on applying computer vision techniques to art history research, facilitated by John Resig.

Published in: Technology
0 Comments
3 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total Views
1,086
On Slideshare
0
From Embeds
0
Number of Embeds
5
Actions
Shares
0
Downloads
8
Comments
0
Likes
3
Embeds 0
No embeds

No notes for slide

Transcript of "Applying Computer Vision to Art History"

  1. 1. Applying Computer Vision to Art History John Resig - http://ejohn.org/research/ Visiting Researcher, Ritsumeikan University
  2. 2. What “Works” Today Reading license plates, zip codes, checks
  3. 3. Optical Character Recognition • Tesseract • https:// code.google.com/ p/tesseract-ocr/
  4. 4. What “Works” Today Face recognition
  5. 5. Face Matching • OpenBR • http://openbiometrics.org/
  6. 6. What “Works” Today Recognition of flat, textured, objects
  7. 7. Computer Vision • Unsupervised (requires no labeling): • Comparing an entire image • Categorizing an image • Supervised (requires labeling): • Finding parts of an image • Finding and categorizing parts of an image
  8. 8. Unsupervised Training • Requires little-to-no prepping of data • Can just give the tool a set of images and have it produce results • Extremely easy to get started, results aren’t always as interesting.
  9. 9. Supervised Training • Need lots of training data • Needs to be pre-selected/categorized • Think: Thousands of images. • If your collection is smaller than this, perhaps it may not benefit. • Or you may need crowd sourcing. • Results can be more interesting: • “Find all the people in this image”
  10. 10. Image Similarity • imgSeek (Open Source) • http://www.imgseek.net/ • TinEye’s MatchEngine • http://services.tineye.com/MatchEngine • Both are completely unsupervised. No training data is required.
  11. 11. imgSeek • Compares entire image. • Finds similar images, not exact. • Does not find parts of an image. • Color sensitive.
  12. 12. • Compares portions of images. • Finds exact matches. • Finds images inside other images. • Color Ukiyo-e.org (Using MatchEngine) insensitive.
  13. 13. Anonymous Italian Art (Frick PhotoArchive) Using MatchEngine
  14. 14. Conservation
  15. 15. Copies
  16. 16. Image Portion Partial Image vs. Much Larger Image
  17. 17. Image Categorization • Deep neural networks • Requires minimal categorization • Very little user-input required. • Ersatz • http://ersatz1.com/
  18. 18. Requires a lot of training data (thousands of images) Takes a lot of computers (Not cheap) The less categories you have, the better.
  19. 19. General Computer Vision • Ideal for some supervised training problems • CCV • http://libccv.org/ • https://github.com/liuliu/ccv • OpenCV • http://opencv.org/
  20. 20. Object Detection
  21. 21. Training Caveats • Requires thousands (if not 10s of thousands) of images • Will take at least a week to run on a very powerful computer • Does not work with 3D objects
  22. 22. Learn More about Computer Vision • Learn more: • http://cs.brown.edu/courses/csci1430/ • Just published paper on Frick Computer Vision work: • http://ejohn.org/research/
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×