CODEWITHSUNDEEP
ocrtesseractimage-recognition
Pythonist
Pythonist

Reputation: 2679

How to help Tesseract to correctly recognise the numbers in this image

I have the following image with a time:

enter image description here

Tesseract is incorrectly reading the 9 as a 3:

$ tesseract test.png -
Estimating resolution as 233
03:41 pm

How can I help Tesseract to realise that this should be read as 9, not a 3?c I have similar problems the character 1, which sometimes is recognised as 7 (and the other way around).

$ tesseract -v
tesseract 5.0.0-alpha-20210401-130-g7a308
 leptonica-1.79.0
  libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 2.0.3) : libpng 1.6.37 : libtiff 4.1.0 : zlib 1.2.11 : libwebp 0.6.1 : libopenjp2 2.3.1
 Found AVX2
 Found AVX
 Found FMA
 Found SSE4.1
 Found OpenMP 201511

Upvotes: 0

Views: 476

Answers (1)

user898678
user898678

Reputation: 3328

blur and resize, so letter have high around 30 points

https://groups.google.com/g/tesseract-ocr/c/p1zRTYkSP98/m/vMw8cfn5HgAJ

Upvotes: 1

Related Questions