Skip to main content
25 events
when toggle format what by license comment
May 23, 2017 at 12:35 history edited CommunityBot
replaced http://stackoverflow.com/ with https://stackoverflow.com/
Apr 13, 2017 at 12:55 history edited CommunityBot
replaced http://mathematica.stackexchange.com/ with https://mathematica.stackexchange.com/
May 15, 2013 at 21:29 comment added hhh @george2079 that is a totally new question: perhaps some machine-learning algorithms for this kind of things where the user needs to specify first the ambiguities and then the program would learn with it? The sloppy O is easily 6 and 9: any machine learning specialist to ask a question about this? :)
May 15, 2013 at 20:29 comment added hhh @Mr.Wizard there is one thing I cannot understand: when I run your code, it outputs tiny-tiny O, X and ERRs. Is it possible to get the output as ASCII so easier to read or is there some setup in Mathematica to handle the output format?
May 15, 2013 at 18:14 comment added george2079 many of the approaches here will fail if the input is even a little sloppy, not closing the "O".
May 15, 2013 at 16:51 history edited hhh CC BY-SA 3.0
The appending broke the references, fixed one bug...
May 13, 2013 at 0:39 vote accept hhh
May 15, 2013 at 20:28
Apr 22, 2013 at 21:43 vote accept hhh
Apr 22, 2013 at 21:43
Apr 19, 2013 at 14:20 comment added Sjoerd C. de Vries @rm-rf OK, I see. Thanks
Apr 19, 2013 at 13:35 comment added rm -rf @Sjo Most dictionaries (and I mean ones used in, say, Word or browsers and not OED) also have a list of common names from top X countries. I'm sure Dutch names (at least, the more common ones) are in that list. For instance, Chrome does not highlight any word in "Sjoerd de Vries" as a typo when I type it in a box, nor does it for "Heike", "Jeroen", "Johann", etc., but it does highlight "Arnoud" (less common?). Arnoud also mentioned that it uses other heuristics, so perhaps there's more to it such as using a database of common letter combinations for local match and a dictionary for global...
Apr 19, 2013 at 5:22 comment added Sjoerd C. de Vries @rm-rf Good find. What is strange: I have been using TextRecognize successfully to get (Dutch) names from scanned pages in a yearbook. So, I don't quite understand how that chimes with the use of a dictionary.
Apr 19, 2013 at 0:10 comment added rm -rf @SjoerdC.deVries here
Apr 18, 2013 at 21:21 history edited hhh CC BY-SA 3.0
...fixes
Apr 18, 2013 at 21:06 history edited rm -rf CC BY-SA 3.0
appended answer 23566 as supplemental
Apr 18, 2013 at 20:47 comment added Sjoerd C. de Vries As to the failure of TextRecognize: I seem to remember having read somewhere it uses a dictionary approach and it is therefore better in recognizing words than separate characters.
Apr 18, 2013 at 20:22 answer added Niki Estner timeline score: 19
Apr 18, 2013 at 19:56 history tweeted twitter.com/#!/StackMma/status/324974635944927233
Apr 18, 2013 at 19:38 history edited hhh CC BY-SA 3.0
added 7 characters in body
Apr 18, 2013 at 19:37 answer added Mr.Wizard timeline score: 33
Apr 18, 2013 at 19:24 history edited Mr.Wizard
edited tags
Apr 18, 2013 at 19:19 history edited hhh CC BY-SA 3.0
I added an example upon the request about a bit harder case: this requires more preprocessing such as smoothing/rotating, finding the squares, etc.
Apr 18, 2013 at 19:10 comment added Niki Estner In general, ImageCorrelate and ComponentMeasurements might be worth a try.
Apr 18, 2013 at 19:09 answer added Dr. belisarius timeline score: 10
Apr 18, 2013 at 19:08 comment added Niki Estner Can you add a few sample images, so potential answerers can test their answers?
Apr 18, 2013 at 18:57 history asked hhh CC BY-SA 3.0