NVIDIA
NVIDIA
License Plate Recognition
Model
NVIDIA
NVIDIA
License Plate Recognition

Model to recognize characters from the image crop of a License Plate.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Application(s) & Domain(s):Classifying characters in vehicle license plates for vehicle identification and traffic management
Model Type:Character Recognition
Intended Users:Developers working in smart city and transportation applications.
Output:Alphanumeric String (Characters in Sequence)
Describe how the model works:Recognizes characters in license plates from cropped images and outputs the character sequence.
Technical Limitations:Model may not recognize characters win truncated license plates or if the license plate is crooked (>30 degrees from horizontal). Model is trained with data from the United States and China and may not work well for characters seen outside of the English and Mandarin contexts.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Precision
Potential Known Risks:This model may fail to detect alphanumeric characters in vehicle license plates.
Licensing:https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/