Hi All,
I am trying to develop a vision-based model to detect multiple barcodes from the given image. The model will predict a list of bounding boxes for all barcodes in the image. I am wondering if there is an example tutorial that I can follow to use the new Fast AI library for object detection.
Any guidance will be greatly appreciated.
Many Thanks and
Kind Regards,
Bilal
Suggest search using the term “bbox” in this forum
There are numerous entries related to bounding boxes.
It’s faster to use a library such as pyzbar for detecting barcodes. Such libraries will give you the coordinates to draw a bounding box.
I have tried pyzbar on the actual dataset but its accuracy is too low for multiple barcodes reading from the images. This is what I have found. The images I have got contains up to a hundred barcodes. pyzbar is performing very poorly. So I thought to try out my own model if that can help.