This happens when the OCR detects the characters as two separate detections because of the space. I have not look at the code recently, I will see if I can fix it.
It should work with the CUDA version you have installed. Try running a test with the attached image in Explore, like below. Also dose the License Plates V2 show in the Object Detection.
Just this past weekend I received an email from Chris the developer of CP.AI and he is still committed to maintaining CP.AI.
I just recently made some changes to my ALPR module and he will be releasing it shortly.
Yes, we are hoping that the users validate and correct any false reads
If the OCR read is not validate we will have to manual validate the data before using it for training
I want to improve both by retrain the models with the data we receive
The last time I chatted with Chris from CP.AI was around the holidays, he did say that him and Matthew are still going to keep developing CP.AI. Chris has recently closed some issue in the GitHub repo.
Early this morning, I caught catalytic converter thieves on one of my camera. It looks like both cars were not good enough for them. I was hoping to catch the license plate on my ALPR camera so I can report them, but no luck.