Since it is 2009 already, I thought it was about time I released a new module.
BaH.Tesseract is an OCR module. It can read an image and recognise characters, converting them to a String. There's a small usage example here.
The module can be downloaded from the maxmods downloads page.
The provided examples use BaH.FreeImage to load the example .tif images. But since the API accepts a TPixmap, you can use any image loader you want. We like to give you choice here at BaH Central :-)
Note that tesseract is only an OCR module. It doesn't do page analysis, meaning it won't understand multiple columns, or pages with "pictures". However, the API lets you specify rectangular areas within an image, so you can be quite precise.
Since the API is very simple (there are only 6 or 7 functions in total), the documentation may seem a little sparse. But it's all there :-)
:o)
Enjoy!
BaH.Tesseract is an OCR module. It can read an image and recognise characters, converting them to a String. There's a small usage example here.
The module can be downloaded from the maxmods downloads page.
The provided examples use BaH.FreeImage to load the example .tif images. But since the API accepts a TPixmap, you can use any image loader you want. We like to give you choice here at BaH Central :-)
Note that tesseract is only an OCR module. It doesn't do page analysis, meaning it won't understand multiple columns, or pages with "pictures". However, the API lets you specify rectangular areas within an image, so you can be quite precise.
Since the API is very simple (there are only 6 or 7 functions in total), the documentation may seem a little sparse. But it's all there :-)
:o)
Enjoy!