Full ALPR Database System for Blue Iris!

Alright that's in the latest image now and I modified the data preparation and verified it's correct in the cloud. It's gonna show the update message because the versions don't match, but you can just close the alert. I'll make the release soon.
 
Screenshot from 2025-03-17 17-15-24.png


I updated again to get the confirmation feature, looks like that confused the update script.
 
  • Like
Reactions: wpiman
Does this latest version show the version info somewhere? I'm not finding it

I never got to displaying the version, but as Pete’s post shows, if it’s anything other than whenever is newest on GitHub, it will tell you. I haven’t created the release for 1.8 yet, but the current newest container is ready and has the version number 1.8 inside of it. It’s just not like official yet if that makes sense.
 
  • Like
Reactions: prsmith777
I'm not presently using the ALPR module to do my plate reads; using the free PlateRecognizer instead (<2500 plates per month). I'm also feeding in my delivery vehicle detections as if they were plates.

What effect will that have on the data sent for training? My delivery data isn't truly a plate. And my plate data from PlateRecognizer doesn't have the position of the recognized plate (unless Ken changes something).

Also, what happens if I've corrected a plate that was only partly in the image. I know the rest of the digits from looking at the footage, or recognizing it as a known vehicle. But could that cause the model to hallucinate digits for you others that aren't there?

I just don't want to be messing up the training data.
 
I'm not presently using the ALPR module to do my plate reads; using the free PlateRecognizer instead (<2500 plates per month). I'm also feeding in my delivery vehicle detections as if they were plates.

What effect will that have on the data sent for training? My delivery data isn't truly a plate. And my plate data from PlateRecognizer doesn't have the position of the recognized plate (unless Ken changes something).

Also, what happens if I've corrected a plate that was only partly in the image. I know the rest of the digits from looking at the footage, or recognizing it as a known vehicle. But could that cause the model to hallucinate digits for you others that aren't there?

I just don't want to be messing up the training data.
Yeah that will be totally different and it shouldn’t actually even try to create it if it doesn’t have the data it needs. I’d probably leave it turned off if you’re using platerecognizer, but even if it were on I don’t think it would do anything.
 
Yeah that will be totally different and it shouldn’t actually even try to create it if it doesn’t have the data it needs. I’d probably leave it turned off if you’re using platerecognizer, but even if it were on I don’t think it would do anything.
 
So are you saying only data read using the ai_dump tag, will have the requisite info for training and I don't have to worry about my reads from affecting things if I still use the memo or plate calls?
 
  • Like
Reactions: algertc
So are you saying only data read using the ai_dump tag, will have the requisite info for training and I don't have to worry about my reads from affecting things if I still use the memo or plate calls?
Correct. I’d still leave it turned off because it’s just a different thing, but no there’s nothing it could do to mess anything up.

Part of what is in the ai_dump are a bunch of coordinates and annotations from code project that get stored in a bunch of different columns in the database. If those are all null when it goes to create it, it will just skip and say 0 OCR records, 0 license plate records.
 
Added manual confirmation also. Correcting a plate will also set confirmed to true.

The resulting training data will be organized into two categories: validated, unvalidated. That should be more accurate.


View attachment 216982View attachment 216983

It worked the first time, but the next plate that gets corrected does not flip the confirm bit. I can flip it manually, tho.
 
Were you able to get it installed/working as a PWA on your home screen and not in the browser?

I'm not sure how that should look, but yes, I have the icon on my desktop, and it opens correctly. However, I still see the top and bottom bars of the browser, making it look like a browser rather than a standalone app.
That said, I'm not using Safari, my default browser on my iPhone is Brave. Could that be the reason?
 
Added manual confirmation also. Correcting a plate will also set confirmed to true.

The resulting training data will be organized into two categories: validated, unvalidated. That should be more accurate.


View attachment 216982View attachment 216983

Awesome! Thank you Charlie!

Two questions:
1) When the training sets get uploaded? Is it like the the non-confirmed sets are uploaded immediately after injections and the confirmed ones when they get confirmed?
2) Correcting a plate doesn't set confirmation flag true for me. Is this only me?
 
It worked the first time, but the next plate that gets corrected does not flip the confirm bit. I can flip it manually, tho.

On the correct it happens in the background, so it won't illuminate immediately. If you refresh the page it should show it. I'll try to make it instant. it should still be changing it though.
 
I'm not sure how that should look, but yes, I have the icon on my desktop, and it opens correctly. However, I still see the top and bottom bars of the browser, making it look like a browser rather than a standalone app.
That said, I'm not using Safari, my default browser on my iPhone is Brave. Could that be the reason?

That might be it. You can keep brave as your default browser, but I think you have to do it in safari when adding it to the home screen.
 
Awesome! Thank you Charlie!

Two questions:
1) When the training sets get uploaded? Is it like the the non-confirmed sets are uploaded immediately after injections and the confirmed ones when they get confirmed?
2) Correcting a plate doesn't set confirmation flag true for me. Is this only me?

1) Checked every 500 plates. it is all uploaded. They're just separated into two folders.
2) See #794
 
That might be it. You can keep brave as your default browser, but I think you have to do it in safari when adding it to the home screen.

I added it using Safari, but when I open it from the home screen, it launches in the default browser, Brave. Not a big deal, though... I can easily live with that!
 
1) Checked every 500 plates. it is all uploaded. They're just separated into two folders.
2) See #794

1) I’m not sure what you mean by this. Are you saying it waits until there are 500 unuploaded recognitions before uploading them all at once?
2) The flag doesn’t light up for me, even after refreshing the page.
 
1) I’m not sure what you mean by this. Are you saying it waits until there are 500 unuploaded recognitions before uploading them all at once?
2) The flag doesn’t light up for me, even after refreshing the page.

What happens if you try the correct button in the viewer when you click on the image? It seems to work for me but I’ll have a look later.

Yes it checks periodically and then if there are at least 500 plates with the necessary annotation data, it will build and send a training set. I’ll post a pic of what it looks like.