Hi Sathish,The Tesseract OCR engine does not work as well with white text on a coloured background, but you should be able to train the document successfully with a few samples without using the header.Regards
Hi @Sangjun ,I agree that it might be useful to restart your training as a new DFD will use the same training data (unless the segregation option has been selected).It can also sometimes be that the hyphen character "-" is not the same unicode charac...
Hi @Sangjun ,I would recommend removing the formula and deselecting the Auto-Calculate flag as there is potentially a more efficient way to remove the unwanted space.You can use the misc parameter "RegexMode" and set it to "2", which uses a fuzzy mat...
Hi,I haven't seen this behaviour myself, but it could be possible in some use cases where there have been updates to Decipher's region detection.I would recommend raising a support ticket so we can investigate.Regards
Hi @NageshaYaliyappa ,Decipher doesn't currently support the automatic extraction of multiple tables in a single DFD, only the first table will be trained and the others will need to be manually verified.Document form definitionsKind Regards
