API tools faq
paste
Guest User

Comparison of OCR

a guest
Nov 16th, 2016
300
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 5.15 KB | None | 0 0
raw download clone embed print report
  1. MICROSOFT COMPUTER VISION:
  2. Citrix Access Gateway X Kundeportal
  3.  
  4. x localhost:19696/api/valv x
  5.  
  6.  
  7. X
  8.  
  9. I alhost19696/api/values
  10. https://news.ycombinator.comntem?id=12962135
  11. 'Hacker News new threads comments show ask I •obs submi
  12. A A.I. Experiments (withgoogle.com)
  13. 289 points Sy qdulberger 13 hours ago I Rag I hide I past I web | 35 comments I favorite
  14. add comment
  15. 1 point by gressquel O minutes ago I edit I delete [-1
  16. I would like to mention I have used a similar service by Microsoft.
  17. https : l/www.microsoft.com Icoqn itive-services/en-u s.com puter-.
  18.  
  19. Hans Zimmer LIVE X Al. Experiments I Hacke
  20.  
  21. Microsoft Cognitive Ser
  22.  
  23. ressquei 40
  24.  
  25. j out
  26.  
  27. Would be interesting to for example submit the same blurry image with text to both services and see which one has the best algorithm to extract text.
  28. reply:
  29. A jedberg 9 hours ago
  30. It asked me to draw a tree. I drew a palm tree. It said -palm tree" on the bottom, but then said it failed.
  31. I drew the palm tree because I've studied Al and that's a classic Al mistake.
  32. If you go to Hawaii and ask students to draw a tree, almost all of them will draw a palm tree. Ask them to draw a bird and it looks like a parrot (instead of the robin you see typically in the "lower 48").
  33. It's interesting that this seems to suffer from the same selection bias.
  34. A ythn 8 hurs ago
  35. It seems biased. When it said draw the moon, I drew a circle with a smaller crater shaped circle inside it, and it immediately guessed "the moon". Later when it asked me to draw a cookie, I drew the
  36. same exact shape (circle with smaller circle) and it immediately guessed cookie, not moon. What's going on?
  37. reply
  38. A halfdanj S hours ago
  39. The classifier is returning a set of confidence scores, so if the shape you drew probably had a high confidence of both cookie and moon. (in fact if you draw it, and dick on it in the endgame screen you can
  40. see some details what it saw in the image). We are not hinting the classifier what your task is, so we try not to bias the classifier. Jonas (developer behind quick draw)
  41. replv
  42. Florin_Andre 8 hours ago
  43. Sounds like that drawing satisfies both criteria. (shrug)
  44. ythn 8 hours ago
  45. So it's not really "guessing", it's just seeing if my drawing matches a predetermined bank of answers? Makes sense, since one time it asked me to draw a "police car" and before I had even finished
  46. drawing the chassis of a normal car it had already guessed "police car" and moved on.
  47. Meegu! 8 hours ago
  48. It's probably assigning a number of possibilities with a confidence rating, and as soon as the confidence rating is > than some percentage of what it's asking you to draw, it says it.
  49. reply
  50. evqs 7 hours ago
  51. I'd say it's "guessing" from a predetermined (rather small) bank of answers, since the same guesses appear over and over again.
  52.  
  53.  
  54. GOOGLE COMPUTER VISION:
  55. Access Gatewa x D Kundeporta x local host19696/api/v x n x Hans Zimmer LIVE 20 X IY AL Experiments Hacke x sal host 19696/ap/values C https/ 12962135 Hacker News new I threads l comments l sho l ask l jobs l submit A A.I. Experiments (withgoogle.com) 5 comments I favorite add comment gressquel 0 minutes ago l edit l del I would like to mention I have used a similar service by Microsoft https:LLwww.microsoft.com/cognitive serviceslen-us/com would be interesting to for example submit the same blurry image with text to both services and see which one has the best algorithm to extract text It asked me to draw a tree. I drew a palm tree. It said "palm tree" on the bottom, but then said it failed I drew the palm tree because I've studied AI and that's a dassic AI mistake. If you go to Hawaii and ask students to draw a tree, almost all of them will draw a palm tree. Ask them to draw a bird and it looks like a parrot stead of the robin you see typically in the lower 48 It's interesting that this seems to suffer from the same selection bias. ours ago It seems biased. When it said draw the moon, I drew a circle with a smaller crater shaped circle inside it, and it immediately guessed the moon". Later when it asked me to draw a cookie, Idrew the same exact shape (cirde with smaller circle) and it immediately guessed cookie, not moon. What's going on? hal The classifier is returning a set of confidence scores, so if the shape you drew probably had a high confidence of both cookie and moon. (in fact if you draw it, and dick on it in the endgame screen you can see some details what it saw in the image). We are not hinting the dassifier what your task is, so we try not to bias the classifier. Jonas (developer behind quick draw Sounds like that drawing satisfies both criteria. (shrug) So it's not really "guessing ,it's just seeing if my drawing matches a predetermined bank of answers? Makes sense, since one time it asked me to draw a police car and before I had even finished drawing the chassis of a normal car it had already guessed "police car and moved on It's probably ning a number of possibilities with a confidence rating, and as soon as the confidence rating is than some percentage of what it's ng you to draw, it says it. I'd say it's "guessing" from a predetermined (rather small) bank of answers, since the same guesses appea SAMSUNG gress quel (40) l logout
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!