I'm trying to write some software that will chop up some TIFFs then rename and refile them depending on what tesseract (or whatever OCR software I use) sees in certain areas of the document - order numbers etc.
Does anyone know if OCRopus is configurable to look only at certain areas of a document and then pass the information on to software I write to do what I want or would it be easier just to get Imagemagik to chop up the TIFFs make two copies of the cut sections cut one into prearranged sections and get tesseract to read it then rename and file the unchopped-up sections of TIFF.
I understand that that may not make very much sense, please ask me to re-explain any areas that are unclear.
Does anyone know if OCRopus is configurable to look only at certain areas of a document and then pass the information on to software I write to do what I want or would it be easier just to get Imagemagik to chop up the TIFFs make two copies of the cut sections cut one into prearranged sections and get tesseract to read it then rename and file the unchopped-up sections of TIFF.
I understand that that may not make very much sense, please ask me to re-explain any areas that are unclear.