[tesseract-ocr] OCR forum/mailing list

Is there a generic OCR or document image analysis forum or mailing list somewhere? Something that's not limited to tesseract. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it,

Re: [tesseract-ocr] Tesseract 4.0: VGSLSpecs

+ Ray Smith On 16-Dec-2016 10:58 PM, "Kay-Michael Würzner" wrote: > Yes, I did and in principle everything works like a charm which is great. > What I want to accomplish now is some understanding: Why do I have to set a > documented parameter in some undocumented way or to

Re: [tesseract-ocr] Tesseract 4.0: VGSLSpecs

Yes, I did and in principle everything works like a charm which is great. What I want to accomplish now is some understanding: Why do I have to set a documented parameter in some undocumented way or to be more precise set this parameter to a value which conflicts with the documentation to make

Re: [tesseract-ocr] Tesseract 4.0: VGSLSpecs

Did you try out the commands as per the LSTM training tutorial? On 16-Dec-2016 8:31 PM, "Kay-Michael Würzner" wrote: > Dear @, > > I played around with training the new LSTM mode. According to the > documentation of the network specification (https://github.com/tesseract- >

[tesseract-ocr] Tesseract 4.0: VGSLSpecs

Dear @, I played around with training the new LSTM mode. According to the documentation of the network specification (https://github.com/tesseract-ocr/tesseract/wiki/VGSLSpecs), the last number in the first tupel called 'depth' corresponds to the type of input (i.e. 1 ... grayscale, 3 ...