What camera settings work best for photographing documents for OCR?
Asked 2/10/2011
4 views
2 answers
0
I’m using a Canon S95 to photograph paper documents and microfilm for OCR, often in low-light library conditions and usually without a tripod. I want the text to be as sharp and readable as possible.
What settings matter most for this kind of document capture—resolution, aperture, shutter speed, ISO, and white balance? I’m especially interested in the best tradeoffs when handholding the camera and trying to avoid blur while keeping text crisp.
Originally by Photography Stack Exchange contributor. Source · Licensed CC BY-SA 4.0
Photography Stack Exchange contributor
15y ago
2 Answers
7
If your camera has a black and white mode, I'd try that to reduce your post processing time. Additionally, many OCR programs I've worked with do much better in B&W.
You'll want get as parallel to the page as you can, because in order to reduce camera shake when hand holding, you're probably going to need your widest aperture in order to maximum your shutter speed. The small sensor on your s95 should increase your DOF enough that I'd open the aperture as wide as you can get away with.
Considering you're just going to be running this through OCR, crank your ISO up to whatever gives you a proper exposure with minimal shake. The OCR is much less likely to complain about the extra noise than blurry letters.
White balance, if you're just talking about text, should be for whatever your "indoor" setting for your camera is - but frankly, don't worry too much about it.
Your megapixels may only matter if your document text is incredibly small and you'll need to clearly resolve that level of detail, but I would guess 6-7 is going to be fine for most things.
Originally by user1917. Source · Licensed CC BY-SA 4.0
user1917
15y ago
0
Generated from our catalog & community — verify before relying on it.
For document/OCR work, prioritize sharpness and avoiding motion blur above everything else.
- Keep the camera as parallel/perpendicular to the page as possible. Good alignment matters more than relying on depth of field.
- If handholding, use a shutter speed at least around 1 / focal length (35mm equivalent), and use image stabilization if available. Zooming wider helps you keep shutter speed up.
- Use whatever ISO gives you a proper exposure at a safe shutter speed. Noise usually hurts OCR less than blur.
- Aperture: don’t stop down too much if light is limited. A moderately wide aperture is often best for handheld shooting; stopping down slightly from fully wide open can help reduce lens aberrations if you have enough light.
- Shoot at maximum resolution, then resize later if needed. Downsizing afterward lets you apply sharpening and usually gives better results than capturing smaller files in-camera.
- White balance is less critical for OCR, but setting a custom white balance from the paper can help consistency.
- If your camera offers black-and-white mode, it may speed workflow, and some OCR software works well with high-contrast monochrome images.
Recommended products
UniqueBot
AI15y ago
Your Answer
Related Questions
How can I create realistic-looking historical document props for a photo shoot on a short deadline?
How can I even out yellow, uneven lighting in a photographed document using GIMP on Linux?
How can I reduce glare when photographing an LCD computer screen with a Canon S95?
How can I photograph a microfiche reader screen without the bright center washing out the image?
Best practices for photographing old documents for long-term digital preservation