Hacker News Reader

Most of the guys here have more experience with text processing but we are expanding into image processing. I think we could definitely detect hair colour but it isn't that useful for Lyst. Gender identification on the other hand...(watch this space)

View on HN

That's a very sensitive area to be heading into. Any assumptions you might try to make will find themselves with counter-examples quite often.

A better direction to move in might be to minimize gender differences as much as possible (although that's hard for marketing to stomach).

I mean, would one try not to recommend pants for girls or skirts for boys (kilts)? It's tricky...

I'll be curious about the gender classifier, mostly because I'm working on a statistical aging model for different gender/ethnicities. Keep on posting!

Reply on news.ycombinator.com