How do I get the most accurate output from StatementReader?
There are two key parts of the process that make a large difference to the accuracy of the StatementReader output.
- Document preparation
Scanning the document to our recommended specification is important. Creating a searchable PDF also enhances the results you can achieve.
We would be happy to discuss implementing a very effective OCR solution for you; this will not rely on you having the latest scanner. Please contact us for more information about arranging a trial of this solution - setting this up takes just a few seconds.
- Template creation
Ensuring that you select the correct template, means that StatementReader will place the data in the correct columns and also correct some common character recognition errors, where possible. These include changing 0/O in dates, as appropriate - however, this relies on getting enough of the other characters correct to match the expected date format, so it can trust it is manipulating a date - this is why the document preparation is also very important.
Recent PostsSee All
Revisited starter script from January 2021: Split Excel file into separate files Excel is essential, and Python is the future - forcing ourselves to practice the latter by automating some of the commo