We all know we can search web pages for text, but many services are looking to go above and beyond with features like location and people tagging. The big downside to these features is that they rely on end users to manually enter in the appropriate data. Really, when was the last time you tagged all the people in the 200 photos you just uploaded to Facebook?
To help automate the process of face recognition, face.com, who have a consumer service for both tagging and automatically doing facial recognition, have just opened their API (our Face.com API profile):
We've opened up our APIs so that you can integrate our face detection and recognition technology with your apps and services. Whether you're looking to add tagging for photos, cool sci-fi experiences, or creative flavors to your apps, we're here to help.
As they note, there are a number of potential uses:
- We offer services for detecting, recognizing, and tagging faces in any photo, through our REST API
- Face.com's services are offered for FREE with rate limits. Whitelisting and Premium licensing options are available.
- You can tag and recognize users from Facebook or Twitter. Alternatively, you can train our index with your own set of users in a namespace.
- Saving Facebook and Twitter tags improves recognition for you and others, and it qualifies you for better rate limits.
- We process photos from anywhere, so you can mix and match photo sources with user IDs, which could enable you to, say, recognize Facebook users in Flickr photos...
While the service is free, keep in mind that there is a rate limit of 200 photo's processed per hour. Developers might also hit a few glitches as the API is still in the alpha stage.
To get a feel for what is possible with the API you can browse some of the online examples, complete with source code, or play in the API sandbox. The face.com API has some decent documentation for those looking to dig deeper into the service, although the forums are fairly quiet at the moment.