parkpow/deep-license-plate-recognition

Automatic License Plate Recognition (ALPR) or Automatic Number Plate Recognition (ANPR) software that works with any camera.

What it solves

This project provides a suite of tools and example clients to help developers integrate license plate recognition (LPR) into their workflows. It simplifies the process of sending images or video streams to the Plate Recognizer API (cloud or self-hosted) to extract plate numbers, confidence scores, and bounding boxes.

How it works

The repository acts as a utility layer that interacts with the Plate Recognizer Snapshot, Stream, and Blur services. It includes Python scripts that handle image uploads, API requests, and response parsing. It also provides specialized utilities for bulk processing, such as monitoring local directories or fetching images from FTP/SFTP servers, and tools for redacting (blurring) plates for privacy.

Who it’s for

It is designed for developers and system integrators who need to implement automatic number plate recognition (ANPR) for parking management, security, or traffic monitoring using the Plate Recognizer ecosystem.

Highlights

  • Multi-source processing: Supports recognizing plates from local files, shell globs, FTP/SFTP servers, and live video streams.
  • Privacy tools: Includes a redaction script to detect and blur license plates in images.
  • Operational utilities: Features a directory watcher for automatic image transfer and archival.
  • Cross-language examples: Provides implementation examples in C++, C#, and Java.
  • Flexible deployment: Compatible with both the Plate Recognizer cloud API and self-hosted SDKs.

Related

  • Project
    runpod/runpod-python

    The official Python library for RunPod, providing an SDK to build serverless AI workers and a GraphQL wrapper to manage GPU cloud pods and endpoints.

  • Project
    georghess/neurad-studio

    neurad‑studio is a research‑grade library that brings neural‑rendering (NeRF and 3‑D Gaussian splatting) to autonomous‑driving data. It supplies ready‑to‑run implementations of NeuRAD and SplatAD, parsers for major AD datasets, a viewer that can display both camera images and lidar points, and standard training/visualisation tools built on Nerfstudio.

  • Project
    backnotprop/plannotator

    Plannotator is a local, browser‑based (and terminal) review UI that integrates with many AI coding agents. It lets you annotate plans, specs, markdown, HTML, and code diffs, then sends the feedback back to the agent. Installation is a one‑line script that auto‑detects agents; the tool works offline, stores everything locally, and only contacts the network for fetching URLs, PR data, or optional link‑sharing. It includes VS Code, Obsidian, and GitHub/GitLab integrations, and provides secure binary distribution with SLSA provenance.

  • Project
    huangjunsen0406/py-xiaozhi

    py‑xiaozhi is a Python‑based, async‑first framework for building multimodal AI assistants that can listen, speak, see, and control hardware. It offers real‑time Opus voice streaming, offline wake‑word detection, vision‑language integration, a JSON‑RPC tool server, and secure WebSocket/MQTT communication. Runs on Windows/macOS/Linux desktops and on edge boards (Raspberry Pi, Jetson Nano). Provides GUI (PySide6/QML), CLI, and GPIO modes, and a plugin system for easy extension.

  • Project
    lessweb/deepcode-cli

    A terminal-based AI coding assistant specifically optimized for DeepSeek models, featuring agent skills, MCP integration, and granular permission controls.