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, an open-source machine learning library for JavaScript.
With a current accuracy rate of 93%, NSFWJS is trained to recognize particular patterns in images, enabling it to identify potentially inappropriate content. It incorporates CameraBlur Protection, which automatically blurs any images it identifies as being potentially inappropriate.
Constantly improving and updating, NSFWJS releases new models frequently to enhance its performance. It is freely available for use, modification, and distribution under the MIT license. Additionally, the library offers a mobile demo, allowing users to test different images on their mobile devices.
To facilitate accessibility, NSFWJS can be downloaded through GitHub. Users are encouraged to report any false positives they encounter and contribute to the ongoing development of the library.
