Gesture recognition for device input

#People are increasingly using portable computing devices in a wider variety of ways and increasingly relying upon computing devices to access various types of content. Much of this content can be confidential or otherwise sensitive to the user. A user might store a list of personal contact information, or might install an application that provides access to that user's bank accounts, for example. Accordingly, it can be desirable to protect against unauthorized or inadvertent access to a device. In many instances, such protection requires a user to enter a password or other identifying information each time that user wants to access the device. For many users such repetitive validation can be distracting or even annoying. Thus, as technology advances and as people are increasingly using portable computing devices in a wider variety of ways, it can be advantageous to adapt the ways in which people access content through the same.

#Various embodiments in accordance with the present disclosure will be described with reference to the drawings, in which:

#FIG. 1 illustrates an example environment in which various aspects can be implemented in accordance with various embodiments;

#FIG. 2 illustrates another example environment in which various aspects can be implemented in accordance with various embodiments;

#Systems and methods in accordance with various embodiments of the present disclosure may overcome one or more of the aforementioned and other deficiencies experienced in conventional approaches to providing input to a computing device. In particular, various embodiments enable a user to make a gesture with a feature such as one of the user's hands, for example. The computing device can capture one or more images (or video) of the feature during the performance of the gesture, which can be analyzed by the computing device (or a system, or service in communication with the computing device) in order to attempt to recognize the gesture. The recognition of the gesture can cause a corresponding action or function to be performed, such as to open an application, unlock certain functionality, or perform another such function. In at least some embodiments, the computing device determines position information for one or more features of the user's hand at one point in time and/or changes in the position information over a period of time, as represented in the captured image(s). The position information can be compared to position information stored for the user for use in identifying an application or function associated with a particular gesture.

#In various embodiments, a user can form a symbol, or other such gesture, with his or her hand, at a distance from a computing device that can be captured by at least one imaging element of the device. When the computing device detects an object indicative of a user's hand forming such a symbol, the captured image(s) can be analyzed to attempt to determine the location of distinguishing features of the symbol, or of user's hand itself, in the image(s). The locations of these features then are compared to hand gesture information stored in, for example, a library of hand gestures for the user. Upon identifying a match with at least a minimum level of certainty, an input to an application executing on the computing device is provided. The hand gesture can include a single “static” gesture, such as a specific letter in sign language, for example, or include two or more “static” gestures. In at least some embodiments, the gesture can include motion, such as movement of a user's hand, a specific movement of a specific symbol, or movement associated with drawing a symbol in the air above the computing device with a finger, for example. The movement could be associated with a specific path or transition from a first “static” gesture to a second “static” gesture. These gestures can be customizable by the user and assigned to various functions or applications as shortcuts or as a security layer alternative to inputting a password or passcode to unlock a device or application. Further, the user can also teach or train the computing device to recognize new gestures.

#In at least one embodiment, the captured image analysis may additionally include analysis of biometric information, such as the relations of various feature points in the gesture. For example, different users will have different relative finger lengths, palm widths, forearm lengths, and other such aspects, which can be combined with the gesture to help in determining a particular person's identity. Therefore, an unauthorized user making a correct hand gesture would be unable to cause the computing device to provide the corresponding input based on differences in the way the symbol appears for an unauthorized hand.