It looks like you're new here. If you want to get involved, click one of these buttons!
Currently I'm not satisfied with the current vision OCR technologies for the U.S. tax industry. However, I came across what appears to be a promising vision program to extract data from any document faster than if one does manual data entry. So far my favorite feature of it is the "Text Line Capture" hotkey. However in order for this feature to work properly, it's contingent on how well clients scan their documents via the mobile app or through their own scanner. Also, it depends on how well the data in the document is structured, for example it will not work when the dollar amount intersects with a line. Despite its imperfections, it still helps to get through a large volume of data smoothly.
It would be nice to see a deeper integration between this type of OCR technology and Canopy because it would allow me to do data extraction via touch on the iPad or via mouse input on both MacOS and Windows operating systems but I think in the long-term touch input for data extracting may be faster than doing it through a computer mouse.
I'm interested in learning more what other Canopy users are doing for digital vision of tax documents to extract data.