Detection of hand gestures using gesture language discrete values

Abstract

Computer implemented method for detecting a hand gesture of a user, comprising: (a) Receiving sequential logic models each representing a hand gesture. The sequential logic model maps pre-defined hand poses and motions each represented by a hand features record defined by discrete hand values each indicating a state of respective hand feature. (b) Receiving a runtime sequence of runtime hand datasets each defined by discrete hand values scores indicating current state hand features of a user's moving hand which are inferred by analyzing timed images depicting the moving hand. (c) Submitting the runtime hand datasets and the pre-defined hand features records in SSVM functions to generate estimation terms for the runtime hand datasets with respect to the hand features records. (d) Estimating which of the hand gestures best matches the runtime sequence depicted in the timed images by optimizing score functions using the estimation terms for the runtime hand datasets.

What is claimed is: 
     
         1 . A method for displaying a dynamic soft keyboard, the method comprising:
 receiving a user input within a user interface (UI) field on a screen of the device;   displaying the soft keyboard on the screen with keys having defined display boundaries that remain constant but with associated hit targets that change;
 identifying a grammar type of a preceding word entered by the user; 
 predicting a subsequent word having a different grammar type than the grammar type of the preceding word; and 
 modifying one or more hit targets of the keys of the soft keyboard based on the predicted subsequent word. 
   
     
     
         2 . The method of  claim 1 , wherein the user input comprises a set of one or more coordinates indicating one or more locations of the soft keyboard selected by the user 
     
     
         3 . The method of  claim 1 , further comprising:
 identifying three-dimensional positions of the stylus or finger, wherein the three-dimensional positions comprise positions in X, Y, and Z coordinates relative to the screen.   
     
     
         4 . The method of  claim 1 , further comprising identifying three-dimensional positions of the stylus or finger, wherein the three-dimensional positions comprise positions in x and y positions on the screen and a z position extending away from the screen. 
     
     
         5 . The method of  claim 4 , further comprising:
 receiving a stream data comprising X-Y-Z coordinates associated with the stylus; and   detecting a hover of the stylus or finger from the stream of X-Y-Z coordinates.   
     
     
         6 . The method of  claim 1 , wherein the grammar type comprises a noun, verb, or adjective. 
     
     
         7 . The method of  claim 1 , wherein said prediction comprises computing n-gram statistics to identify the subsequent word. 
     
     
         8 . The method of  claim 1 , wherein the one or more hit targets of the keys are extended beyond rendered boundaries of the keys such that a touch within a rendered boundary of a first key results is registered as an adjacent key having an extended hit target. 
     
     
         9 . The method of  claim 1 , wherein said extending the one or more hit targets is additionally based on a second key that a stylus or finger hovered over in addition to the identified grammar type. 
     
     
         10 . The method of  claim 1 , wherein the device is at least one of a television, a wireless phone, a digital camera, a game console, or an automotive computer. 
     
     
         11 . A system, comprising:
 memory embodied with instructions for presenting and dynamically modifying a soft keyboard; and   one or more processors configured execute the instructions for;
 receiving a user input within a user interface (UI) field on a screen of the device; 
 displaying the soft keyboard on the screen with keys having defined display boundaries that remain constant but with associated hit targets that change; 
 identifying a grammar type of a preceding word entered by the user; 
 predicting a subsequent word having a different grammar type than the grammar type of the preceding word; and 
 modifying illumination of one or more of the keys of the soft keyboard based on the predicted subsequent word. 
   
     
     
         12 . The system of  claim 11 , wherein said modification of the illumination of the one or more keys comprises extending a hit target of at least one key into the rendered boundary of an adjacent key. 
     
     
         13 . The system of  claim 11 , wherein the machine-executable instructions are further executable for:
 identifying three-dimensional positions of a stylus, wherein the three-dimensional positions comprise positions in x and y positions on the screen and a z position extending away from the screen.   
     
     
         14 . The system of  claim 11 , wherein a hover is detected through identifying a Z coordinate of the stylus, the Z coordinate indicative of a distance the stylus are detected away from the screen. 
     
     
         15 . The system of  claim 14 , wherein the grammar type comprises a noun, verb, or adjective. 
     
     
         16 . The system of  claim 11 , wherein the machine executable instructions are further executable for:
 receiving a stream data comprising at least one of an incoming trajectory, one or more pen-down trajectories, or an outgoing trajectory associated with the associated with the stylus; and   detecting the hover of the stylus from the stream data.   
     
     
         17 . The system of  claim 11 , wherein said modifying illumination of one or more of the keys of the soft keyboard based on the predicted subsequent word comprises changing an order of the keys in the soft keyboard. 
     
     
         18 . One or more computer hardware memory devices embodied with executable instructions for displaying a soft keyboard that, when executed by one or more processors of a device, cause the one or more processors to perform operations, comprising:
 receiving a user input within a user interface (UI) field on a screen of the device;   displaying the soft keyboard on the screen with keys having defined display boundaries that remain constant but with associated hit targets that change;   identifying a grammar type of a preceding word entered by the user;   predicting a subsequent word having a different grammar type than the grammar type of the preceding word; and   modifying one or more hit targets of the keys of the soft keyboard based on the predicted subsequent word.   
     
     
         19 . The one or more computer hardware memory devices of  claim 18 , wherein one or more hit targets of the one or more keys are increased upon prediction of the subsequent word. 
     
     
         20 . The one or more computer hardware memory devices of  claim 18 , further comprising changing a layout of the soft keyboard between a QWERTY layout and a numeric pad layout based, at least in part, on a type of data that is valid for the UI field receiving the user input.