Future iPhones and iPads may recognize if the person picking them up is left or right-handed. The devices may also recognize how quickly, or slowly, they were were picked up and respond accordingly, according to a new Apple patent application (20150355721) for “motion pattern classification and gesture recognition.”
The patent involves methods, program products, and systems for gesture classification and recognition are disclosed. If the invention ever comes to fruition, your iPhone or iPad may one day determine multiple motion patterns (e.g., picking up a mobile device from a table) after a period of “training.”
The version of iOS that supports this could collect the training data from one or more mobile devices. The training data can include multiple series of motion sensor readings for a specified gesture. Each series of motion sensor readings can correspond to a particular way a user performs the gesture. The system can send the motion patterns to mobile devices as prototypes for gesture recognition.
Apple says that motion pattern classification and gesture recognition can be implemented to achieve several advantages. Multiple ways of a same gesture can be recognized. For example, a mobile device can recognize a same gesture of picking up the mobile device without regard to whether the device was picked up by a left hand, by a right hand, in a slow motion, in a fast motion, from a pocket, or from a table.
The mobile device can recognize a user's gesture without requiring the user to practice the gesture. The mobile device can recognize a user's gesture regardless of the user's specific habit of gesturing the mobile devices. Complex and customized gestures can be recognized. For example, a mobile device can designate a specific gesture as a signature. Subsequently, the iOS device can use the signature to authenticate a user by recognizing the user's gesture in place of or in addition to a user name or a password or both.