Is there a way to use tesseract for single digit numbers?

TL;DR It appears that tesseract cannot recognize images consisting of a single digit. Is there a workaround/reason for this?

I am using (the digits only version of) tesseract to automate inputting invoices to the system. However, I noticed that tesseract seems to be unable to recognize single digit numbers such as the following:

The raw scan after crop is:

enter image description here

After I did some image enhancing:

enter image description here

It works fine if it has at least two digits:

enter image description here

I've tested on a couple of other figures:

Not working: enter image description here , ,

Working: enter image description here , ,

If it helps, for my purpose all inputs to tesseract has been cropped and rotated like above. I am using pyocr as a bridge between my project and tesseract.

Solution

Individual digits are handled the same way as other characters, so changing the page segmentation mode should help to pick up the digits correctly.