I did not receive any answer. Sorry if my question was stupid, i just
need some help to do this part of my project.
I hope that i was clear to tell you about my question.
I already did the segmentation part of the document, and now i have
small images, where is written (hand-written) an allphanumeric string
like: AMN45FG, with a good resolution and a realy small noise.
Although the image is pretty clear, the text is really "readable", if
I process the image with tesseract the result is disappointing.
Tesseract recognizes something like the 15 percent of the characters.
I think that is depend because of a not-correct use of the dictionary.
Now, i can improve this result because the strings are related between
them, and some of them are for example just a name of a person or of a
city, so with a limited output.
What I need to know, if there is some function that analizes the
character and return a value that represent the probabilities of the
character to be that one, or another one.
Like, after the process, i have an output like this

A : 23 %
B: 0.2 % ...

In this way when I will rebuild the string, i can use just this
probabilities and other implicit informations of document to improve
my results.
I hope I was clear, and if i am saying a lot of bullshits, please tell
me!!!! :)


On Apr 10, 9:29 am, Pierpaolo Monaco <[email protected]>
wrote:
> Hello,
> I am new with this project.
> I am doing a work with my University for recognize handwritten digit, only
> upper case and I thought to use OCROpus.
> After a work of image processing, now I need a function that return a kind
> of match score for any digit.
> A value that represent the probabilities of the character to be A,B,C....
> etc...
> In this way, i can avoid the use of a dictionary, becouse the string is
> often not related to a specific language, but simply a alphanumeric string.
> The strings are reletad between them so I can use this value to build a more
> specif probability.
> Is there some function that return this values?
> Thanks in advance.
>
> Regards.
>
> --
> -----------------------------
> Pierpaolo Monaco
> ----------------------------
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"ocropus" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/ocropus?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to