|
|
 |
Introducing Moods and Facial Expressions
As of today we’re releasing a new set of facial analysis attributes for alpha testing, allowing you to estimate moods and key facial expressions. To try these new attributes, just pass our API a photo for face detection, and there’s no need to pass any personal user identifiers. Check it out: |
 |
 |
Code Samples
If you want to try out our latest API without coding, check out our Sandbox Console on the developers’ site. We’ve added a new ‘attributes’ parameter where you can specify which attributes you want retrieved: “all”, “none”, comma-separated, or leave empty for default (which returns the original 3 attributes: gender, glasses, and smiling).
 |
For example, here's a call to get some photos of one of the celebrities in our celebs.face.com namespace, Bar Refaeli, and focus on the smiling, mood and lips attribute:

|
 |
Now consider you want to see only the photos where Bar (from the same photo urls above) is smiling widely - so we'll use the tags.get method with filters for mood:happy, smiling:true and lips:parted:

|
 |
|
 |
 |
What can you do with Moods and Facial Expressions?
This attribute pack is a result of requests from our partners and developer community. Here are some of the uses that we’ve heard of:
- Selecting "best" photos for display
- Measuring reactions on live chats
- Photo search filters
|
- Dating preferences
- Competitions
- And much more…
|
|
 |
|