An Algorithm for Nudity Detection [pdf] • Hacker News Board

Re: An Algorithm for Nudity Detection [pdf]

#21

Post by laumars » Sat, Feb 22, 2014, 3:17 AM UTC

cmelbye wrote: post #7

notastartup wrote: post #3

how do these nudity detection API work? Is there a crowdsourcing going underneath the hood? Are they using some clustering algorithm to detect a range of skin color (if 90%), it's nude.

The link that you just commented on answers your question in literally the best way possible, it's an academic paper on an algorithm used for this.

To be fair, he may have tried that. The site is completely unusable on a phone as it seems to make assumptions about the minimum screen resolution and doesn't allow you to zoom out like most desktop sites on a mobile screen do. In fact it's one of the most poorly designed sites I've stumbled upon in a long time in that regard (which is a great pity as the content looked interesting)

Re: An Algorithm for Nudity Detection [pdf]

#22

Post by EpicEng » Sat, Feb 22, 2014, 4:04 AM UTC

organelle wrote: post #5

notastartup wrote: post #3

how do these nudity detection API work? Is there a crowdsourcing going underneath the hood? Are they using some clustering algorithm to detect a range of skin color (if 90%), it's nude.

Protip: If you film pornography in black and white, there is no such thing as "skin color." If you remap the palette for a desaturated image, so that everyone's skin is green or magenta, are there any fewer penises penetrating vaginas in the image? If it's a horse and a fully clothed person's mouth, where is the algorithm for that? Think about it.

How many pornography images do you see on the internet that are taken in black and white? How many are modified so that the people involved look like the hulk? An algorithm like this does not need to be 100% bulletproof in every situation imaginable, it just needs to work most of the time.

Think about it.

Re: An Algorithm for Nudity Detection [pdf]

#23

Post by tachyonbeam » Sat, Feb 22, 2014, 4:56 AM UTC

nathancahill wrote: post #11

"The training set for the skin filter consisted of 1,182,608 manually labeled skin pixels and 10,471,553 manually labeled non-skin pixels while the testing set consisted of 2,303,824 manually labeled skin pixels and 24,285,952 manually labeled non-skin pixels." That's a lot of pixels to manually label.

One word: rectangles.

Re: An Algorithm for Nudity Detection [pdf]

#24

Post by wlievens » Sat, Feb 22, 2014, 9:00 AM UTC

benched wrote: post #12

dclowd9901 wrote: post #10

Seems like a not very scalable approach to the problem. I would think if you wanted to capture all nudity (including monochromatic or illustrated), you would instead go at the problem from the angle of titillation . You could even round up images that are not necessarily human based (fruit arranged provocatively, for instance).

If the algorithm gets aroused, return positive, otherwise return negative. Bam, patent.

So your algorithm would be a MTurk api?