0

I'm looking an algorithm that analyzes a portrait-photo of a person and outputs a descriptive text like "young man, rather long nose, green eyes".

It doesn't matter if the output is very precise or not; it is for an art installation. But it should be possible to do it automatic.

I found this one: https://code.google.com/p/deep-learning-faces/, but it is impossible for me to fulfill the hardware and software requirements (NVIDIA Fermi GPUs & matlab)

Do you know of anything more accessible?

martinh
  • 13
  • 3

3 Answers3

0

This is one of the hardest problems in computer vision. I'd recommend you watch the ted talk by Fei-Fei Li to get an understanding of it:

https://www.ted.com/talks/fei_fei_li_how_we_re_teaching_computers_to_understand_pictures

In short: If you want to use any of the state-of-the-art methods you will need a lot of processing power. A lot more than just a single high-end graphics card, I'm talking about super computing here.

And unless you're really lucky and find a research group that has released their implementation, this also requires a huge amount of engineering.

Konstantin
  • 115
  • 1
  • 8
  • Thank you, very helpful. The video is also very interesting. I see it won't be possible on my raspberry pi:) – martinh May 22 '15 at 20:03
  • TED talks are just a show and tell that lasts a few minutes. I guess several grad students spend valuable years of their lives actually doing this stuff. – Totoro May 25 '15 at 06:21
0

I found this online service that describes faces: http://www.faceplusplus.com/

It has a very well documented API and seems to be free of charge. Or at least I didn't find any information about pricing.

martinh
  • 13
  • 3
0

There are a few free face analyser APIs that are fairly easy to use:

  1. Rekognition, by Orbeus
  2. MP Face Analyzer SDK (evaluation) by MotionPortrait
  3. Faceplusplus (linked above)

You might have to take measurements of an "average face" to make interpretations like "long nose". ToonifyMe is an app that caricatures faces using this approach.

Some of these API's can actually work on a Pi. Recognition does the analysis in the cloud, so that should be doable.

Totoro
  • 3,398
  • 1
  • 24
  • 39
  • Thank you, Rekognition looks great. It returns more descriptions than Faceplusplus, like mood and beauty. – martinh May 25 '15 at 10:35