#251 · Primary category: Computer Vision

ultimateALPR-SDK

alpr amlogic-npu android anpr anpr-sdk artificial-intelligence deep-learning jetson jetson-nano khadas-vim3 khadas-vims-boards license-plate license-plate-detection license-plate-recognition linux machine-learning openvino raspberry-pi tensorflow windows

World's fastest ANPR / ALPR implementation for CPUs, GPUs, VPUs and NPUs using deep learning (Tensorflow, Tensorflow lite, TensorRT, OpenVX, OpenVINO). Multi-Charset (Latin, Korean, Chinese) & Multi-OS (Jetson, Android, Raspberry Pi, Linux, Windows) & Multi-Arch (ARM, x86).

Project last updated:11/05/25

GitHub Stars

742

Forks

182

Contributors

2

License

Other

Why we included this project

Reading license plates from live camera feeds is a common need, and this SDK is one of the few open implementations built for embedded and edge hardware rather than data-center GPUs. It runs on plain CPUs with SIMD optimizations, and also supports GPUs, VPUs, and NPUs. Ready-made sample apps cover Android, Raspberry Pi, Jetson, and Windows, with APIs in C++, C#, Java, and Python. Beyond plate recognition, it also estimates vehicle color, make/model, body style, direction, and speed, which makes it useful for traffic and parking systems that want more than just the plate number. The project is a commercial SDK with a non-commercial license, so treat it as a strong reference and evaluation base rather than assuming free production use. If you're working on constrained ARM devices and want to see how far deep-learning ANPR can go without a dedicated GPU, this is a good place to start.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category