Group Abstract Group Abstract

Message Boards Message Boards

10
|
21.3K Views
|
4 Replies
|
24 Total Likes
View groups...
Share
Share this post:

"SafeCracker" puzzle - a coffee table challenge

Posted 10 years ago
Attachments:
POSTED BY: Helen Shiells
4 Replies

Machine learning should definitely help here. Please see this example. It is also in the docs. You can get training data as:

digits = ExampleData[{"MachineLearning", "MNIST"}, "Data"];

or you also can build your own training set.

enter image description here

POSTED BY: Vitaliy Kaurov

At present the heaviest data in the result images are the rotation boundaries. As we know the rotation angle before the images are cut out, one could include a rotation dependent margin and crop the characters square. I expect that's the most significant possible improvement.

It's a mild cop out, but building a custom classifier from the images would definitely give the most reliable match.

POSTED BY: David Gathercole
Posted 10 years ago

That's brilliant, thanks David. I have also had this issue where TextRecognize won't recognise these individual numbers. I tried image rotation (with the individual pictures from your notebook) and it seems to think that "19" is "E":

output = TableForm[Rasterize[#, ImageSize -> {45}] & /@ # & /@ resultImagery]
recog = {}; AppendTo[recog, Table[TextRecognize[ImageRotate[output[[1, 1]][[1]], i]], {i, 6, 7, 0.05}]]

Maybe (as you suggested) a filter of some sort will help.

POSTED BY: Helen Shiells
Attachments:
POSTED BY: David Gathercole
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard