Reputation: 864
I found that page about OCR using Tesseract on OpenCV 3.1. The problem is that given links include examples with older OpenCV versions. Is there any up to date example of usage of OCR Tesseract? and How can I told this to OpenCV authority?
Upvotes: 0
Views: 2267
Reputation: 8626
The sample code below is unfortunately in Python
with the text module
/opencv_contrib
of OpenCV 3.2
. I compiled Tesseract 4.0.0alpha
with OpenCV 3.2.0
binding to make it works few months ago. Hope this could be a reference for your C++
implementation.
# para: tessdata path, language, whitelist, psm, oem
tesser = cv2.text.OCRTesseract_create('C:/Program Files/Tesseract 4.0.0/tessdata/','eng',
'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ',11,3)
retval = tesser.run(processed_image, 0) # ' return string type
As far as I know, the Text module
doesn't work well in OpenCV 3.0/3.1
. Would suggest to use 3.2.0
to avoid any possible issue on earlier 3.x
versions.
Upvotes: 1