11–20 of 24 posts
That's a lot of pixels to manually label.
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).
"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.
I'm under the impression that Google's machine learning is already filtering your personal G+ photos for nudity.
1. attempt to post the image to google+
2. if the post is there, there is no nudity;
if it failed to post, there is nudityI'm under the impression that Google's machine learning is already filtering your personal G+ photos for nudity.
maybe the best nudity detector API involves the following: 1. attempt to post the image to google+ 2. if the post is there, there is no nudity; if it failed to post, there is nudity
"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.
40 million pixels is roughly 40 ~1 megapixel (1280x720) images. It's not that many, especially when it's likely something like this: http://pascallin.ecs.soton.ac.uk/challenges/VOC/images/voc20...
I'm under the impression that Google's machine learning is already filtering your personal G+ photos for nudity.