----------------------
EvaluateMathRegions.py
----------------------

[Usage]

python3 EvaluateMathRegions.py --detections <detections.csv> --ground_truth <ground_truths.csv>
======================================================

[Description]

This tool can be used to evaluate IoU metric for predicted math regions against ground truth math regions. 
For each document image, <detections.csv> contains predicted bounding box region information and
<ground_truths.csv> contains ground truth bounding box information.

Each line in the <detections.csv> or <ground_truths.csv>, corresponds to a bounding box for one math region. It consists
of 5 attributes.

math:   class_name ("math")
x:      top left x-coordinate of the bounding box for the math region
y:      top left y-coordinate of the bounding box for the math region
width:  width of the bounding box for the math region
height: height of the bounding box for the math region

For each math region in <ground_truths.csv>, the IoU metric is computed for all of the predicted math regions in <detecions.csv> and
a sorted list of (IoU, ground_truth, detection) returns in descending order.

Please look at sample files in "detections" and "groundtruths" folders, to know more about input formats.
======================================================
Acknowledgements
Thanks to Rafael Padilla.
https://github.com/rafaelpadilla/Object-Detection-Metrics
