How to improve OCR results of tesseract

0
votes

I'm having problems with tesseract conducting OCR of numbers. This picture

enter image description here

is recognised as

‘I .38)

I'm using -psm 6 as parameter. Are there any better ways to recognise numbers? Do I need to configure tesseract or is there any additional pre processing needed of the image?

1
ocrtesseract

1 Answers

3
votes

I rescaled to 300DPI and got the correct result.