search

femioladeji / License-Plate-Recognition-Nigerian-vehicles

A python program that uses the concept of OCR using machine learning to identify the characters on a Nigerian license plate
https://blog.devcenter.co/developing-a-license-plate-recognition-system-with-machine-learning-in-python-787833569ccd
250 stars 126 forks source link

License Plate Recognition with EVA multimedia database system #56

Open jarulraj opened 1 year ago

jarulraj commented 1 year ago

Hello @femioladeji. Thanks for creating and sharing this useful application. Can you please share your thoughts on integrating this application with a Python-based multimedia database system like EVA? Do you anticipate any use-cases for a query language over the extracted labels?

https://github.com/georgia-tech-db/license-plate-recognition/blob/main/README.ipynb https://github.com/georgia-tech-db/eva

CREATE UDF IF NOT EXISTS OCRExtractor
INPUT (frame NDARRAY UINT8(3, ANYDIM, ANYDIM)) OUTPUT (labels NDARRAY STR(ANYDIM), bboxes NDARRAY FLOAT32(ANYDIM, 4), scores NDARRAY FLOAT32(ANYDIM)) TYPE TextExtraction IMPL 'ocr_extractor.py';

SELECT OCRExtractor(data) FROM MyImages WHERE ocrextractor.label LIKE "LEM446A4"

README_12_7