Plate recognition pattern / custom models

[feochoa]

Hello from Chile,

The plate recognition engine sometimes fails because of plate pattern (for instance, an "8" instead of "B" where should be only letters).

An API response with the top N results can be very useful to compare the candidates against the pattern and improve accuracy.

In general terms, the API works ok with chilean plates, but it never achieves the high perfomance showed in the white paper related to LPR. I suspect that the accuracy could improve with a custom training using local images . Do you plan to add this feature in the near future?

Buen día,

Felipe

[Stephen Neish, CEO]

Hello Filipe,

Thanks for your suggestion. It's a good one, so we'll take a look at adding the top N results in the near future. There is no specific training on Chilean plates, but we are certainly open to such training. We have tended to follow the commercial opportunities to date. For the record, these are the officially supported countries:
1. Belgium
2. France
3. Germany
4. Italy
5. Netherlands
6. UK
7. USA

In addition we are told we have high scores on the plates of several other EU countries, Singapore, Turkey, Brazil, Australia and New Zealand.

If you have a specific commercial opportunity in Chile please let us know via sales@ and we'll prioritize the training.

Stephen Neish

[feochoa]

Thank you Stephen for your reply. We work with openalpr to access control (using RPI3), and planning to migrate to Sigthhound for both plate and face recognition. I will contact you for further discussion.

Buen día,
Felipe