NSFWDetector alternatives and similar libraries
Based on the "Media Processing" category.
Alternatively, view NSFWDetector alternatives based on common mentions on social networks and blogs.
-
EFQRCode
A better way to operate QR Code in Swift, support iOS, macOS, watchOS and tvOS.
* Code Quality Rankings and insights are calculated and provided by Lumnify.
They vary from L1 to L5 with "L5" being the highest.
Do you think we are missing an alternative of NSFWDetector or a related project?
Popular Comparisons
README
NSFWDetector is a small (17 kB) CoreML Model to scan images for nudity. It was trained using CreateML to distinguish between porn/nudity and appropriate pictures. With the main focus on distinguishing between instagram model like pictures and porn.
Usage
guard #available(iOS 12.0, *), let detector = NSFWDetector.shared else {
return
}
detector.check(image: image, completion: { result in
switch result {
case let .success(nsfwConfidence: confidence):
if confidence > 0.9 {
// ๐ฑ๐๐
} else {
// ยฏ\_(ใ)_/ยฏ
}
default:
break
}
})
If you want to enforce stricter boundaries for your platform, just apply a lower threshold for the confidence.
Installation
NSFWDetector is available through CocoaPods. To install it, simply add the following line to your Podfile:
pod 'NSFWDetector'
โ ๏ธ Because the model was trained with CreateML, you need Xcode 10 and above to compile the project.
App Size
The Machine Learning Model is only 17 kB in size, so App size won't be affected compared to other libraries using the yahoo model.
Using just the Model
If you don't want to use the Detection Code, you can also just download the MLModel file directly from the latest Release.
Feedback
If you recognize issues with certain kind of pictures, feel free to reach out via Mail or Twitter.
Author
Michael Berg, [email protected]voo.com
License
NSFWDetector is available under the BSD license. See the LICENSE file for more info.
*Note that all licence references and agreements mentioned in the NSFWDetector README section above
are relevant to that project's source code only.