Finding images in book page images

Code4Lib 2012 Lighting Talk Presentation

Transcript

1. Finding images in book page images Eric Larson University of Wisconsin-Madison Libraries
2. Warning Hobbyist code here. I’m certain there are better ways to do this.
8. curl
10. imagemagick
11. Processing steps 1. Desaturate the image 2. Boost contrast 3. Convert image to 1pixel wide x image height 4. Sharpen the image 5. Super-duper grayscale conversion 6. Produce the text color list 7. Look for continuous “black” blocks
13. convert
14. convert -colorspace Gray
16. convert \ -contrast -contrast \ -contrast -contrast \ -contrast -contrast \ -contrast -contrast \
18. Convert image to 1px x height
20. Sharpen the image
21. Heavy-handed grayscale conversion => make most grays black => whites are white
22. convert to txt
24. Look for long, continuous blocks of “black”
28. github.com ewlarson/picturepages
29. Don Quixote # (168/169) 99% Accurate http://openlibrary.org/books/OL24150024M/The_history_of_Don_Quixote
32. Paradise Lost # (54/54) 100% Accurate http://openlibrary.org/books/OL14022842M/Paradise_Lost
35. Around the World in Eighty Days # (60/62) 97% Accurate http://openlibrary.org/books/OL7050533M/Around_the_world_in_eighty_days
38. Wanna help do this better? Contact me. elarson@library.wisc.edu