Skip to main content

Imeti - Local Image Privacy Tool

Project description

Imeti Logo

Imeti

Local Image Privacy Tool

Python Platform

Protect your identity. Scrub your footprint. Keep it local.


Overview

Imeti is a fully local desktop application for image privacy and forensic analysis. It provides a suite of redaction and analysis tools that run entirely on your machine, with no data sent to the cloud.

It is intended for journalists protecting sources, security researchers analyzing suspicious files, and anyone who wants control over what their images reveal.


Features

Privacy & Redaction

  • Face Anonymization: AI-powered face detection with four anonymization methods — Gaussian blur, pixelation, black bar, and solid fill.
  • Text Redaction: Automatically detects text regions in an image and redacts them using the EAST model.
  • Metadata Scrubbing: Remove all metadata or selectively strip EXIF, IPTC, XMP, GPS data, ICC profiles, and hidden thumbnails.
  • Batch Processing: Anonymize and clean entire folders of images at once.

Forensic Analysis

  • Steganography Scanner: Detects hidden data payloads using LSB analysis, chi-square tests, and entropy analysis.
  • Watermark Detection: Frequency-domain analysis to flag invisible watermarks.
  • Cryptographic Hashing: Computes SHA-256, SHA-1, and MD5 hashes for file integrity verification.
  • Metadata Injection: Deliberately inject custom or fake EXIF data to mislead trackers.

Installation & Setup

Prerequisites

  • Python 3.10+

1. Clone & Install

# Clone the repository
git clone https://github.com/Astrosp/Imeti.git
cd Imeti

# Install dependencies
pip install -r requirements.txt

2. Run Imeti

python main.py

Note: The first time you use Face Detection or Text Redaction, Imeti will briefly connect to the internet to download the required pre-trained AI models (~100MB). These are cached locally in the models/ directory afterward.


Usage Guide

  1. Load Media — Drag and drop an image, click "Open Image," or select "Batch" to process a folder.
  2. Configure Options — Use the sidebar to enable or disable Face Anonymization, Text Redaction, or Metadata Stripping.
  3. Analyze — Run Steganography or Watermark scans from the forensic tools section.
  4. Process — Click "Process" to apply the selected redactions.
  5. Save — Click "Save" to export the sanitized image to disk.

Privacy Guarantee

Imeti is designed to operate entirely offline:

  • No telemetry
  • No analytics
  • No cloud APIs

Your data never leaves your computer.


License

This project is licensed under the MIT License, free for personal use only. See the LICENSE file for details.

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

imeti-1.0.2.tar.gz (37.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

imeti-1.0.2-py3-none-any.whl (47.1 kB view details)

Uploaded Python 3

File details

Details for the file imeti-1.0.2.tar.gz.

File metadata

  • Download URL: imeti-1.0.2.tar.gz
  • Upload date:
  • Size: 37.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.6

File hashes

Hashes for imeti-1.0.2.tar.gz
Algorithm Hash digest
SHA256 bc4900cacd08366965bf2ed75ae5a1e66dd1afa3214b04d2c1f3b6bd17e5b43e
MD5 c4a338f2cfc93682b5a5e67e1a4f1e28
BLAKE2b-256 eef730efa39ff0ced1b0e0c02e066d7ffd7883524c4c0e993777893ed96e7e65

See more details on using hashes here.

File details

Details for the file imeti-1.0.2-py3-none-any.whl.

File metadata

  • Download URL: imeti-1.0.2-py3-none-any.whl
  • Upload date:
  • Size: 47.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.6

File hashes

Hashes for imeti-1.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 82256a2d57c4cccfd1a4fb783aea05a745247a3c5e45fe3a82959c781caa220d
MD5 40892e1c9a593cb5d572a591950db2aa
BLAKE2b-256 85432cd2b289485453a6eca1f37e701e81f023f890ba6bb2666cb9c0eff3779e

See more details on using hashes here.

Supported by

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