karolzak / boxdetect

BoxDetect is a Python package based on OpenCV which allows you to easily detect rectangular shapes like character or checkbox boxes on scanned forms.

karolzak/boxdetect Issues

AttributeError: module 'boxdetect.config' has no attribute 'update_num_iterations'. Did you mean: 'dilation_iterations'?
Closed 8 months ago1
using boxdetect in a lambda errors due to GUI artifacts
Updated a year ago
Which configurations should I use?
Updated a year ago
Can't detect table cells
Updated a year ago
Failure in UnitTests
Closed a year ago1
New release for scikit-learn installation
Closed a year ago3
Default config for vertical grouping has bad results for vertically aligned checkboxes
Updated 2 years ago2
Not detecting all the boxes
Updated 2 years ago1
Removing noise while preserving the boundary of the checkbox
Closed 2 years ago4
Cumulative results?
Closed 2 years ago2
Is there way to extract coordinates
Closed 2 years ago3
checkbox detect fails with sloppy crosses
Closed 2 years ago7
Failed detection of cropped image
Updated 3 years ago2
challenging case on checkbox crossing outside box
Closed 3 years ago2
Check box mapping with text
Updated 3 years ago1
Strategies for getting accurate checkboxes on documents with Serif Font
Closed 3 years ago3
AttributeError: module 'boxdetect.config' has no attribute 'update_num_iterations'
Closed 3 years ago
Add missing docstrings
Closed 4 years ago
Add full tests coverage
Closed 4 years ago
Unhandled exception when no rectangles found
Closed 4 years ago1
Potential bug in `boxdetect.pipelines.get_boxes()` when resizing the image
Closed 4 years ago
Add an option to save/load configs
Closed 4 years ago
As a user I want to automatically get optimal configuration based on provided ground truth
Closed 4 years ago