Is it possible to achieve the text quality and coverage (i.e., including smaller text or low quality areas of the image) of the textExtraction profile, while retaining the document structure information of the documentConversion profile? If not possible through the cloud API, then would it be possible via direct usage FineReader (or similar)?
Sorry for the delay in response.
Recently ABBYY Cloud OCR SDK team has improved technology of TXT export used in our service. Now the text export format simulates original layout of a source document with the help of inserted spaces and empty lines. The new TXT export is available by default if your application uses the
The old text export format is available, too. It can be used by setting the exportFormat option to txtUnstructured. If this option value is selected, OCR results will be saved in the resulting text file in the same order as they are recognized, i.e. block by block.
ABBYY Cloud OCR SDK documentation will be updated accordingly.
This answer is marked "community wiki".
answered 23 Mar '15, 12:27
Oksana Serdyuk ♦♦