[Burichan] [Futaba] [Futaba Ols] [Gurochan] [Photon] - [Home]

[Return]
Reply mode
Link
Subject
Comment
File
Verification
Password (for post and file deletion)
Leave empty (spam trap):
  • Supported file types are: GIF, JPG, PNG
  • Maximum file size allowed is 1000 KB.
  • Images greater than 200x200 pixels will be thumbnailed.

File: 1430579951239.jpg -(198945 B, 845x653) Thumbnail displayed, click image for full size.
198945 No.1   [Reply]
>> No.2  
File: 1430580769493.jpg -(55823 B, 485x659) Thumbnail displayed, click image for full size.
55823

FUUUU

>> No.3  
File: 1430580956894.jpg -(36824 B, 495x652) Thumbnail displayed, click image for full size.
36824

Heretics

>> No.4  
File: 1430586313392.jpg -(36094 B, 363x233) Thumbnail displayed, click image for full size.
36094

lol

>> No.5  

Seems pretty accurate if just taking the face into account. I do this myself as a game. If you just look at the face and in some different posed, you see different ages. Also some women look pretty manly if you just look at the face alone without makeup. Not saying Cracky is.

>> No.6  

>>5
But you work out the rest from context, which makes this a nice illustration of bot failure. Cameras are terrible at preserving definition of skin tones, and there's very little depth information. I reckon photos from a known angle of emotionless faces with a preset light source would give very accurate results.

Male / Female is probably trivial but gamifying that would be quite problematic.

Meanwhile "cat or dog" has also turned out to be a very easy problem even without using external cues, consistent angles, knowledge of different breeds etc.

>> No.7  

>>4
i lol'd



Delete Post []
Password