Skip to main content

Python package for Near Duplicate Video Detection (Perceptual Video Hashing) - Get a 64-bit comparable hash-value for any video.

Project description

The Python package for near duplicate video detection

Build Status Build Status Build Status codecov Total alerts Language grade: Python pypi Downloads GitHub lastest commit PyPI - Python Version

⭐️ Introduction

Videohash is a Python library for detecting near-duplicate videos (Perceptual Video Hashing). Any video input can be used to generate a 64-bit equivalent hash value with this package.

The video-hash-values for identical or near-duplicate videos are the same or similar, implying that if the video is resized (upscaled/downscaled), transcoded, watermark added/removed, stabilized, color changed, frame rate changed, changed aspect ratio, slightly cropped, black-bars added or removed, the hash-value should remain unchanged or not vary substantially.

How the hash values are calculated

  • Every one second, a frame from the input video is extracted, the frames are shrunk to a 144x144 pixel square, a collage is constructed that contains all of the resized frames(square-shaped), the collage's wavelet hash is the video hash value for the original input video.

When not to use Videohash

  • Videohash cannot be used to verify whether one video is a part of another (video fingerprinting). If the video is reversed or rotated by a substantial angle (greater than 10 degrees), Videohash will not provide the same or similar hash result, but you can always reverse the video manually and generate the hash value for reversed video.

How to compare the video hash values stored in a database

🏗 Installation

To use this software, you must have FFmpeg installed. Please read how to install FFmpeg if you don't already know how.

Install videohash

Upgrade pip

python3 -m pip install --upgrade pip

If you do not want to upgrade pip and the installation fails try appending --prefer-binary to the following installation command(s).

  • Install from the PyPi (recommended):
pip install videohash
  • Install directly from the GitHub repository (NOT recommended):
pip install git+

🌱 Features

  • Generate videohash of a video directly from its URL or its path.
  • Can be used to implement scalable Near Duplicate Video Retrieval.
  • The end-user can access the image representation(the collage) of the video.
  • A videohash instance can be compared to a 64-bit stored hash, its hex representation, bitlist, and other videohash instances.
  • Faster than the old method of comparing each frame individually. The videohash package generates a single 64-bit video hash value, which saves a significant amount of database space. And the number of comparisons required drops significantly.

🚀 Usage

In the following usage example the first three instance of VideoHash class are computing the hash for the same video(not same as in checksum) and the last one is a different video.

>>> from videohash import VideoHash
>>> # video: Artemis I Hot Fire Test
>>> url1 = ""
>>> videohash1 = VideoHash(url=url1, download_worst=False)
>>> videohash1.hash # video hash value of the file, value is same as str(videohash1)
>>> #VIDEO:Artemis I Hot Fire Test
>>> url2=""
>>> videohash2 = VideoHash(url=url2)
>>> videohash2.hash
>>> videohash2.hash_hex
>>> videohash2.hash_hex
>>> videohash1 - videohash2
>>> videohash1 == videohash2
>>> videohash1 == "0b0011010000011111111011111111111110001111011110000000000000000000"
>>> videohash1 != videohash2
>>> path3 = "/home/akamhy/Downloads/rocket.mkv" #VIDEO: Artemis I Hot Fire Test
>>> videohash3 = VideoHash(path=path3)
>>> videohash3.hash
>>> videohash3 - videohash2
>>> videohash3 == videohash1
>>> url4 = "" #VIDEO: How We Are Going to the Moon
>>> videohash4 = VideoHash(url=url4)
>>> videohash4.hash_hex
>>> videohash4 - "0x7cffff000000eff0"
>>> videohash4.hash
>>> videohash4 - videohash2
>>> videohash4 != videohash2

Run the above code @

Extended Usage :

API Reference :

🛡 License

License: MIT

Copyright (c) 2021 Akash Mahanty. See license for details.

The VideoHash logo was created by iconolocode. See license for details.

Videos are from NASA and are in the public domain.

NASA copyright policy states that "NASA material is not protected by copyright unless noted".

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

videohash-2.1.6.tar.gz (20.0 kB view hashes)

Uploaded Source

Built Distribution

videohash-2.1.6-py3-none-any.whl (20.1 kB view hashes)

Uploaded Python 3

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