Eyedea, a recognition service located in Czech Republic, has released the Eyeface SDK, a kit for developers interested to detect faces, analyze age and gender, and detect eyes, nose, and mouth. The SDK works with C/C++ libraries for Windows, Linux, and Mac OS X environments. The possibilities of this SDK include to target advertising, count people, and analyze profiles. Eyedea claims to be obsessed with accuracy, optimization, flexibility and speed.
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 face tagging. The big downside to these features is that they rely on end users have 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 have just opened their API.
Fourteen APIs have been added to the ProgrammableWeb directory in categories such as Voice, Notifications, Stocks, and Recognition. Featured today are four APIs that use machine learning technology to provide image recognition and visual search services. Here's a rundown of the latest additions.
Google has announced updates to the Cloud Speech API which include the addition of word-level timestamps which means that timestamp information is now available for each word in the transcript. Also, the API now supports long-form audio files up to three hours long and 30 additional languages.