ORT-ALPR (ONNXRunTime Automatic License Plate Recognition)

This is an ALPR framework (Automatic License Plate Recognition) that is optimised for cpu inferencing on Onnxruntime. This framework is capable of detecting vehicle license plates, recognizing license plates and blurring license plates. For detecting license plates pre-trained WPOD-NET has been used. For OCR (Optical Character Recognition), paddle's OCR model has been used. All the models are converted to ONNX for inferencing on Onnxruntime

Installation

Create a new conda environment. If you dont have conda installed download miniconda

conda create -n ort-alpr python=3.8

Clone this repository to your computer and navigate to the directory.

Activate new enviroment

conda activate ort-alpr  

Install all the libraries used

pip install -r requirements.txt  

Usage

Initialize the ALPR class

x = ALPR(out_dir='lpd_results')

Detecting Mode

x.detect_lp(path ='Test_Images/Cars438.jpeg',Bbox=False,show=True,save=False)

Recognizing Mode

x.recognize_lp(path ='Test_Images/Cars450.jpeg',show=True,save=False,f_scale=1.5)

Blurring Mode

x.blur_lp(path ='Test_Images/Cars422.png',show=True,save=False)

License

MIT