Hi,
Yes this API function helped me. I also found that I could disable the
classifier and learning by using:
TessBaseAPI::SetVariable() -> with "classify_enable_learning", "0");
TessBaseAPI::SetVariable() -> with
"classify_enable_adaptive_matcher", "0");
Many thanks for your quick help again.
Best Regards,
- ganesh
On Saturday, November 17, 2012 6:13:48 AM UTC+8, zdenop wrote:
>
> On Fri, Nov 16, 2012 at 2:29 AM, newtotesseract
> <[email protected]<javascript:>
> > wrote:
>
>> Hi Dmitri,
>>
>> How do we clear the adaptive classifier?
>>
>> Can I please know, what is the API or function for clearing the adaptive
>> classifier?
>>
>
> ClearAdaptiveClassifier[1] ;-)
>
> [1]
> http://code.google.com/p/tesseract-ocr/source/browse/trunk/api/baseapi.h?r=760#290
>
>
>> Best Regards,
>> - ganesh
>>
>> On Friday, November 16, 2012 3:39:22 AM UTC+8, Dmitri Silaev wrote:
>>
>>> Sriranga,
>>>
>>> All you can specify in the command line can be seen if you run
>>> tesseract's executable with no parameters. As you can see no trace of
>>> anything like adaptive classifier. Anyway you won't even need it as it's
>>> only an API routine for programmers and has no value when using the command
>>> line.
>>>
>>> Warm regards,
>>> Dmitri Silaev
>>> www.CustomOCR.com
>>>
>>>
>>>
>>> On Thu, Nov 15, 2012 at 8:15 PM, Sriranga(78yrsold) <[email protected]
>>> > wrote:
>>>
>>>> Hi Dmitri,
>>>> what is the *commandline* for clearing the adaptive classifier after
>>>> every image as well as after generating the traineddata file?.
>>>> With warmest regards,
>>>> -sriranga(79yrs)
>>>>
>>>>
>>>> On Thu, Nov 15, 2012 at 8:22 PM, Dmitri Silaev <[email protected]>wrote:
>>>>
>>>>> Hi Ganesh,
>>>>>
>>>>> One of the things to try is clearing the adaptive classifier after
>>>>> every image or a number of images. It may get spoiled after some
>>>>> different
>>>>> documents, on the other hand for a few very similar documents it can
>>>>> bring
>>>>> some help. Well for a few similar pages it can get spoiled too ))
>>>>>
>>>>> Warm regards,
>>>>> Dmitri Silaev
>>>>> www.CustomOCR.com
>>>>>
>>>>>
>>>>>
>>>>> On Thu, Nov 15, 2012 at 12:14 PM, newtotesseract <[email protected]>wrote:
>>>>>
>>>>>> Hi friends
>>>>>>
>>>>>> I am using a static TessBaseAPI object in my application. This object
>>>>>> gets initialized and reads, processes the training data at the startup
>>>>>> of
>>>>>> the application.
>>>>>>
>>>>>> Then, this application processes multiple scanned images through the
>>>>>> TESS_API TessBaseAPI::ProcessPages() function, using the
>>>>>> same TessBaseAPI object over and over again.
>>>>>>
>>>>>> I observed that the correctness of text decoded from images after
>>>>>> some time reduces.
>>>>>>
>>>>>> I could simulate this issue in tesseract.exe also by modifying
>>>>>> tesseractmain.cpp file to have one TessBaseAPI object and process all
>>>>>> the
>>>>>> images using this same object.
>>>>>>
>>>>>> Can you please guide me whether there are any modifications done to
>>>>>> training data loaded in TessBaseAPI object?
>>>>>>
>>>>>> Shall we not use different TessBaseAPI object for each image
>>>>>> decoding? Is this a known issue?
>>>>>>
>>>>>> Thanks in advance for your time and help.
>>>>>>
>>>>>> Best Regards,
>>>>>> - ganesh
>>>>>>
>>>>>> --
>>>>>> You received this message because you are subscribed to the Google
>>>>>> Groups "tesseract-ocr" group.
>>>>>> To post to this group, send email to [email protected]
>>>>>>
>>>>>> To unsubscribe from this group, send email to
>>>>>> tesseract-oc...@**googlegroups.com
>>>>>>
>>>>>> For more options, visit this group at
>>>>>> http://groups.google.com/**group/tesseract-ocr?hl=en<http://groups.google.com/group/tesseract-ocr?hl=en>
>>>>>>
>>>>>
>
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" 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/tesseract-ocr?hl=en
