Hacker News new | comments | show | ask | jobs | submit login
Face++: API for face detection – also detects gender, age, pose (faceplusplus.com)
127 points by gagzilla on Nov 4, 2014 | hide | past | web | favorite | 50 comments



I have some experience with computer vision [1]. It is non-trivial and requires real processing power to do it at scale. So I suspect they'll be charging soon unless they have a huge amount of funding. Other than that potential issue, this looks like a fairly usable, credible API.

[1] I wrote software to scan Facebook profile photos for overweight people. We store their ID's for targeting through FB ads.


Your footnote should win some kind of prize for "most terrifying inconsequential remark".


I think there's an unspoken rule on the internet: any piece of personal data will eventually be used for ad targeting.

The response rates for display ads are so abysmal that any edge can make a difference. CTRs (click-through rates) hover around 0.1%, so if you increased CTR by a slim 0.1%, you'd double the revenue!


The corollary (?) is that the most unexpected use will likely be the most lucrative.


I literally LOL'd at this :) .


For the last time, I am "Mr Stay Puft", I am a brand, not a real person. Please stop bombarding me with slimming products.


Can you actually target Facebook ads at specific users?


You can target a group of specific users. There are some restrictions (minimum group size) but there are ways around it.[1]

[1] http://mysocialsherpa.com/the-ultimate-retaliation-pranking-...


This is fucking terrifying.


You could until a couple of months ago, and you still can with some significant caveats. Also, combining names and locations with other data from third parties gives some pretty awesome postal mail/email/telemarketing lists for companies in this space.


I think hair restoration\transplant companies can also target users with ads by looking at their pictures. If they are bald then show them our ad


Yes, there are a few characteristics that are mainly visual and hard to identify any other way. Bald is one, wearing glasses (segmented by sunglasses/regular glasses) is another.


I believe this is a good place to plug a very usable open source computer vision project: http://openbiometrics.org/

Fantastic alternative you can hack with if you're allergic to APIs that "might" charge their free service in the future.


Another project that I think is really good is dlib : http://dlib.net

To compare how well it works compared to OpenCV's face detector: http://www.youtube.com/watch?v=LsK0hzcEyHI

dlib is also great at picking out facial landmarks: http://blog.dlib.net/2014/08/real-time-face-pose-estimation....

Between dlib and OpenBR, I think almost all of these usecases can be covered without commercial APIs - if you have a large enough training set.

Face Recognition is a whole another matter though.


Sadly none of these free/open projects can do gender, age, pose


OpenBR does gender & age (probably pose in 2015). YMMV though, current algorithm is very dependent on an "ID card" quality photo.


dlib does pose, see: http://blog.dlib.net/2014/08/real-time-face-pose-estimation..... No gender or age prediction though. Do many people care about gender and age prediction?


Those characteristics including ethnicity can be useful for marketing purposes.

I remember reading about a shop that used this sort of technology to profile their customers. It revealed that at a certain time of week they received an unusually large number of Japanese customers (turned out they were on a tour bus route) and responded by repositioning their Japanese member of staff to be a greeter during these periods and it significantly improved their revenue.

A similar product based around this idea might be clothes shop dummies with this built in. This would provide an interesting profile of the people interested in the particular outfit the dummy was modelling which might be useful for further advertising targeting or in the case of a multi-national brand some insights into what they should advertise in which regions.


Also of note is clmtracker: https://github.com/auduno/clmtrackr

Its open source (MIT license I believe) and performs some of the same functions as Face++ like detection, "landmarking" and replacing features/mapping a mask to your face. It includes some fun demos as well.


OpenBR author here, thanks for the plug!


I've been doing research for a facial detection/facial information API since Face.com was mothballed by Facebook.

Not loving the idea of relying on third-party APIs for the above reason makes this project is very useful.

Thanks.


Looks interesting, might implement this on a project soon.

Their pricing is a bit iffy though... " The Face++ APIs are currently provided free of charge. However, Face++ may charge fees for future use of or access to the Face++ APIs or the Face++ services according to its sole discretion. If Face++ decides to charge for the Face++ APIs Services, Face++ will provide you prior notice of such charges. Face++ may also charge You when providing You a service different from the service under these Terms; for example, we may charge additional fees for excessive API use. "

not even a rough clue given as to how much they'll charge (could be reasonable, or very expensive)...

but, still, looks very good


How do they get away with using all those celebrity photos?

Founder/CEO of the 3D Avatar Store here. We do most of what they do: face detection, facial feature detection and tracking, smile/expression analysis, and facial recognition. And we go further with 3D Reconstruction into performance animation ready 3D geometry, automated lip sync generation and so on.


A lot of people dont know or dont care. E.g. look at mightytexts website[1].

[1] http://mightytext.net/


I'm guessing because China.


I've tried this for a hobby project, and was quite surprised by the quality of the API. I'm a bit wary though because of the lack of a clear business model / pricing on their website.


Reminds me of Kairos - facial recognition API apihttp://www.kairos.com/


Thanks for the mention. CTO of Kairos here.

We offer a web API that will perform 2d to 3d facial recognition which helps greatly when dealing with natural world images as opposed to mug shot type of controlled imagery. We turn the 2d image into a 3d model and then normalize the pose and lighting before performing the matching leading to higher results on everyday pictures.

Check us out at www.kairos.com


This is fun, but it thinks I'm about 20 years older than I am, and the grey-beard Swedish sysadmin was identified as a black woman.


Yep. I'm a 30 year old bearded man. It said it was 99.7% sure I'm a 47 year old woman. At least it got my race right! Though it was only 77% sure of that.


Recognition leaves something to be desired. Detection classifies her as female, 40 years old ±10 years. Recognition apparently doesn't add metadata parameters from detection into it's weighting:

http://imgur.com/n23vVQT


http://challengepost.com/software/smileforce

ran emotional sentiment analysis from an ipad camera while user scrolled thru menu items. won a prize in salesforce $1 hackathon


What's the principle behind gender detection? Is it based on machine learning algorithms trained with a huge pile of data, or is there some inherent geometric difference between male and female faces that I'm missing?


There's definitely geometric differences between male and female faces. The most distinct difference is that the male chin tends to be larger, giving the face a more "square" shape, while female faces have smaller chins, giving the face a slight "almond" shape. And I'm sure there's more subtle differences as well.



Lol, it doesn't like my picture much :P I'm a 31 year old white guy (ok, was 29 in the picture) and it tells me I'm probably 43 with 7 variance and black :P


I'm in my 30s and the software thinks I'm 7 or 14, depending on the pic :) And I don't look this childish at all


So what are some people building with this? I'm curious of the possibilities, which probably are endless.


What comes to mind is a generic "upload profile photo" for websites, where the system can automatically crop your uploaded photo. Or even just to check that it is a "valid" photo.

Not sure how the gender/age info would be useful.

That's the best I can come up with. My brain actually works best in the opposite direction (problem->solution) :)


Already getting 504 errors. Such an API cannot be free unless they got a huge amount of funding...


This is really awesome. Good job! And the response time is pretty fast too.


is this a project by the people at Face.com? I know they were acquired by fb some time ago so it would be neat to know they are still working on related stuff post-acquisition


I wonder if this could be used to filter out duckface pictures...


Doesn't work at all for me.

ILLEGAL_USE_OF_DEMO_KEY


You have to sign up and create an app to get the key. From what I could gather there is no limit or pricing on the site. Once you are in to the developer center they have you can see the docs and use the API. It's quite nice, even if it ages me at 31, a bit older than I am.


It is not even detecting my face!


It needs a good photo of mostly just your face in order to get a good detection. Detected my face quite accurately, I'd try again with a headshot.


So you need to detect the face before you can detect the face...


happy to see this...was using face.com till facebook bought them :(


Meh. Betaface has had this for years.




Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact

Search: