Is there software that can batch auto-crop and straighten scanned photos with varying borders and backgrounds?
Asked 3/23/2019
9 views
2 answers
0
I need to process about 1,000 scanned or photographed prints. Each image is rectangular or square, but they vary in size and may include white borders, a visible background (for example a wooden table), and slight rotation.
I’m looking for software that can batch-detect the photo edges, crop away the surrounding background/white space, and ideally deskew or straighten the result automatically. Photoshop’s automatic crop/straighten and other tools I tried have not been reliable enough for unattended batch work.
Is there a tool or workflow that can do this well, or is semi-manual processing still the most realistic option?
Originally by Photography Stack Exchange contributor. Source · Licensed CC BY-SA 4.0
Photography Stack Exchange contributor
7y ago
2 Answers
2
I made a free website (https://www.autocropper.io/) that automatically crops the individual photos from multi-photo scans. It works via Python OpenCV and specifically searches for rectangular shapes surrounded by white edges. Here's an example scan with 4 photos:
I tested your example image and it detected the image:
You can upload 10 scans at a time. If you have more example images with differing backgrounds, feel free to share and I can better understand your use case. It was originally built for digital scanned images instead of actual pictures.
No download required, it's an in-browser application. I wrote extensively on how my image detection algorithm works using Python OpenCV if you want to run it locally. See here https://www.autocropper.io/technical-overview
Originally by user110097. Source · Licensed CC BY-SA 4.0
user110097
3y ago
0
Generated from our catalog & community — verify before relying on it.
There isn’t a universally reliable “AI” tool mentioned here that will perfectly handle every mixed scan/photo automatically, but a few workable options were suggested.
For automatic cropping, one answer recommends autocropper.io, a browser-based tool built on OpenCV that detects rectangular photos, especially when surrounded by white edges. It was designed for scanned photos and may work well if your images are reasonably clean and rectangular.
On Mac, SnipTag/Snip were reported to batch-crop scans correctly, including separating multiple photos from one scan, though they did not automatically rotate images upright in the test described.
If full automation is inconsistent, the most realistic fallback is a semi-manual workflow in GIMP: use the Perspective tool to correct/crop one image, then a “next file” script to save and advance rapidly. The reported speed was about 10–15 seconds per image, which may be far faster than a slower Photoshop workflow.
So: try a dedicated auto-crop tool first, but expect that mixed backgrounds and slight skew may still require manual review or a semi-automated workflow.
Recommended products
UniqueBot
AI7y ago
Your Answer
Related Questions
How can I batch-crop scanned images evenly from all sides without resizing?
How can I batch crop white borders from many images?
How can I correct a scanned photo that is slightly warped or curved?
How can I automatically crop scanned book-cover images in bulk?
Is there a free alternative to Photoshop’s Adaptive Wide Angle for lens distortion correction?