Quick facts
- Best for
- Identify NSFW images in the browser
- Pricing
- Free
- Editor rating
- 4.5 / 5
- Community saves
- 1
About NSFW JS
NSFWJS is a JavaScript library designed to help identify potentially inappropriate images on a client's browser, without needing to send the image to a server. The library is powered by TensorFlowJS, which is an open-source machine learning library for JavaScript. The library is trained to recognize particular patterns in the images, with the current accuracy rate at 93%. The library also incorporates CameraBlur Protection, which is a feature that blurs any images that it identifies as being potentially inappropriate. The library is constantly being improved and updated, with new models being released frequently. NSFWJS is free to use, and can be modified and distributed under the MIT license. The library also includes a mobile demo, which allows users to test different images on their mobile devices. Finally, the library is available for download through GitHub, and users are encouraged to report any false positives or contribute to the development of the library.
Pros
- Client-side Image detection
- Powered by Tensor
- Flow
- JS93% Accuracy rate
- Includes Camera
- Blur Protection
- Constant updates and improvement
- Free to use
- Open-source (MIT License)Mobile demo included
- Available on Git
- Community contribution encouraged
- NSFW Patterns recognition
Cons
- Dependent on Tensor
- Flow
- JSNo server-side processing93% Accuracy (false positives)Potential privacy issues with Camera
- Blur
- Regular updates required
- Only Javascript implementation
- Limited cross-platform usage
- No real-time detection
- Reliant on pattern recognition
- Limited user support