Skip to main content

No project description provided

Project description

Plate OCR

A Mobilenet based, single IL car plate OCR

Installation

Currently plt-ocr is intended to use on CPU machine (GPU support is coming soon). To install plt-ocr on a CPU run:

pip3 install plt-ocr
pip3 install torch --index-url https://download.pytorch.org/whl/cpu

Usage

Command line

If you have a car plate image named plate.jpg

You can run pltocr car.jpg and get

{"prediction": "70660202", "confidence": 0.9978833775525012}

Python

import json
from PIL import Image
from plt_ocr.model import OCR

img = Image.open(plate_path)
model = OCR()
result = model(img)
print(json.dumps(result.__dict__))

Related

  • Detecty is a Mobilenet based single car plate detection model that works well with plt-ocr.
  • cars.vardale.org is a website that uses both detecty and plt-ocr.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

plt_ocr-0.0.20.tar.gz (8.8 MB view details)

Uploaded Source

Built Distribution

plt_ocr-0.0.20-py3-none-any.whl (8.8 MB view details)

Uploaded Python 3

File details

Details for the file plt_ocr-0.0.20.tar.gz.

File metadata

  • Download URL: plt_ocr-0.0.20.tar.gz
  • Upload date:
  • Size: 8.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.10.13 Linux/5.3.0-28-generic

File hashes

Hashes for plt_ocr-0.0.20.tar.gz
Algorithm Hash digest
SHA256 57ebb5b1eb5b0d21144742d86894a4acb21abe841a2c8d8a5e67c8fb25793fd2
MD5 f22b9c02554e94f6582336e085b5e215
BLAKE2b-256 ef7724af77903044c629e2093111cfcd151b817541852b466fa7928c8ec7a333

See more details on using hashes here.

File details

Details for the file plt_ocr-0.0.20-py3-none-any.whl.

File metadata

  • Download URL: plt_ocr-0.0.20-py3-none-any.whl
  • Upload date:
  • Size: 8.8 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.10.13 Linux/5.3.0-28-generic

File hashes

Hashes for plt_ocr-0.0.20-py3-none-any.whl
Algorithm Hash digest
SHA256 3bfa2b85ec2bd67aba7763f52285a86298c889673f8131e8442edb49b47e9ec8
MD5 59402c184d32aa114091bd2db64d470b
BLAKE2b-256 11a6f4eb355ee318c32a0cd3da46ebd5dc151201b18644dcd34797f6b598660d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page