1

I have been using google vision OCR for a while now. And I have observed that the OCR result varies with image dimension. Say for example an image with dimension 720 x 1280 gives a better result than 360 x 720. And it sometimes does worse the other way.

I have experienced the same with Microsoft's OCR API.

So is there an ideal image dimension that always gives a good OCR result? How does the image dimensions affect the OCR result?

Arun Gowda
  • 2,721
  • 5
  • 29
  • 50

2 Answers2

1

Please reference here for that information: Google Supported images

FACE_DETECTION 1600 x 1200 Distance between eyes is most important

LANDMARK_DETECTION 640 x 480

LOGO_DETECTION 640 x 480

LABEL_DETECTION 640 x 480

TEXT_DETECTION and DOCUMENT_TEXT_DETECTION 1024 x 768 OCR requires more resolution to detect characters

SAFE_SEARCH_DETECTION 640 x 480

Google Supported images

Shaun Moore
  • 33
  • 7
0

Based on the link below, not only the resolution, the aspect ratio is also a factor https://www.mlreader.com/prepare-image-for-google-vision-api

Lixin M.
  • 1