2 points | by maniazi83 13 hours ago ago
2 comments
One thing we noticed while building OCR is that accuracy drops heavily with low-resolution scans and rotated documents. GPU acceleration helped speed, but preprocessing ended up being the bigger challenge. Curious how others handle that.
[dead]
One thing we noticed while building OCR is that accuracy drops heavily with low-resolution scans and rotated documents. GPU acceleration helped speed, but preprocessing ended up being the bigger challenge. Curious how others handle that.
[dead]