Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/oktopuzSlid/detectorPlacas/llms.txt

Use this file to discover all available pages before exploring further.

DetectorPlacas is a computer vision project built with TensorFlow and OpenCV that automatically detects vehicle license plates in real time. It ships with a pre-trained frozen inference graph based on SSD MobileNet v1 and supports three detection modes — static images, video files, and live webcam streams — all accessible through a Tkinter graphical interface or directly from the command line.

Introduction

Understand how DetectorPlacas works and explore the detection pipeline architecture.

Quickstart

Install dependencies and run your first license plate detection in minutes.

Detection Modes

Run detection on images, video files, or a live webcam feed with configurable thresholds.

Script Reference

Full reference for all Python scripts, flags, constants, and tensor names.

How it works

1

Install dependencies

Set up Python, TensorFlow 1.15, OpenCV, NumPy, and the TensorFlow Object Detection API.
2

Prepare model artifacts

Place the frozen inference graph (frozen_inference_graph.pb) and labelmap.pbtxt in the expected directory layout.
3

Choose a detection mode

Launch the Tkinter GUI (interfaz.py) or call an individual detection script directly from the terminal.
4

Visualize results

Bounding boxes, confidence scores, and class labels are drawn on each frame using the TensorFlow Object Detection API visualization utilities.

Build docs developers (and LLMs) love