Classification of touch input as being unintended or intended

• US 9,430,085 B2
• Filed: 09/12/2014
• Issued: 08/30/2016
• Est. Priority Date: 09/12/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Durojaiye, Olumuyiwa M, Abzarian, David
• Primary Examiner(s): Merkoulova, Olga
• Application Number:
  US14/485,573
• Publication Number:
  US 20160077650A1
• Time in Patent Office: 718 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 2203/04101 2.5D-digitiser, i.e. digitiser detecting the X/Y position of the input means, finger or stylus, also when it does not touch, but is proximate to the digitiser's interaction surface and also measures the distance of the input means within a short range in the Z direction, possibly with a separate measurement setup
• CPC Class Codes: G06F 2203/04104 Multi-touch detection in digitiser, i.e. details about the simultaneous detection of a plurality of touching locations, e.g. multiple fingers or pen and finger
• CPC Class Codes: G06F 2203/04808 Several contacts: gestures triggering a specific function, e.g. scrolling, zooming, right-click, when the user establishes several contacts with the surface simultaneously; e.g. using several fingers or a combination of fingers and pen
• CPC Class Codes: G06F 3/03545 Pens or stylus
• CPC Class Codes: G06F 3/041 Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
• CPC Class Codes: G06F 3/0418 for error correction or compensation, e.g. based on parallax, calibration or alignment
• CPC Class Codes: G06F 3/04186 Touch location disambiguation
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures

Abstract

The techniques described herein implement a classification process to evaluate information associated with a tool input (e.g., from an input tool such as a pen or a stylus) and a user touch input (e.g., from a finger or a palm of a hand) to determine whether the user touch input is an intended or an unintended touch input. The information evaluated may be associated with an arrival of the tool input relative to an arrival of the user touch input. The information evaluated may also be associated with a movement of the tool input relative to a movement of the user touch input. In various implementations, the techniques may calculate an evaluation score and compare the evaluation score to a confidence classification threshold. If a confident classification cannot be achieved, the techniques further the classification process as more information associated with the inputs is received.

Claims

1. A system comprising:

a touch surface configured to receive a plurality of inputs including at least a tool input associated with an input tool and a user touch input;

one or more processors communicatively coupled to the touch surface;

memory communicatively coupled to the one or more processors;

a classification module stored in the memory and executable by the one or more processors to;

implement a first classifier to evaluate information associated with the tool input and the user touch input to determine whether the user touch input is an intended touch input or an unintended touch input, wherein the first classifier evaluates the information to determine an inter-arrival time between a first time when the tool input arrives at the touch surface and a second time when the user touch input arrives at the touch surface; and

in response to the first classifier being unable to determine whether the user touch input is the intended touch input or the unintended touch input, implement at least one subsequent classifier to evaluate additional information to determine whether the user touch input is the intended touch input or the unintended touch input, wherein the additional information evaluated is associated with a movement of the tool input relative to a movement of the user touch input.

2. The system of claim 1, wherein:

the input tool comprises one of an active pen or an active stylus; and

the user touch input is based on contact from a finger or a palm of a hand of a user.

3. The system of claim 1, wherein:

if the inter-arrival time is less than an inter-arrival time threshold, then at least part of the evaluation of the first classifier indicates that the user touch input is the unintended touch input; and

if the inter-arrival time is greater than or equal to the inter-arrival time threshold, then at least part of the evaluation of the first classifier indicates that the user touch input is the intended touch input.

4. The system of claim 1, wherein the first classifier evaluates the information to determine an inter-arrival distance between a first position where the tool input arrives at the touch surface and a second position where the user touch input arrives at the touch surface.

5. The system of claim 4, wherein:

if the inter-arrival distance is less than an inter-arrival distance threshold, then at least part of the evaluation of the first classifier indicates that the user touch input is the unintended touch input; and

if the inter-arrival distance is greater than or equal to the inter-arrival distance threshold, then at least part of the evaluation of the first classifier indicates that the user touch input is the intended touch input.

6. The system of claim 1, wherein the at least one subsequent classifier evaluates the additional information to determine a difference between a first direction of movement of the tool input and a second direction of movement of the user touch input.

7. The system of claim 6, wherein:

if the difference is less than a direction difference threshold, then at least part of the evaluation of the at least one subsequent classifier indicates that the user touch input is the unintended touch input; and

if the difference is greater than or equal to the direction difference threshold, then at least part of the evaluation of the at least one subsequent classifier indicates that the user touch input is the intended touch input.

8. The system of claim 1, wherein the at least one subsequent classifier evaluates the additional information to determine a difference between a first velocity of movement of the tool input and a second velocity of movement of the user touch input.

9. The system of claim 8, wherein:

if the difference is less than a velocity difference threshold, then at least part of the evaluation of the at least one subsequent classifier indicates that the user touch input is the unintended touch input; and

if the difference is greater than or equal to the velocity difference threshold, then at least part of the evaluation of the at least one subsequent classifier indicates that the user touch input is the intended touch input.

10. A method comprising:

determining that a first input of a plurality inputs received at a touch surface is associated with an active input tool;

determining that at least a second input of the plurality of inputs is associated with user touch; and

evaluating, by one or more processors, at least one factor associated with the first input and the second input to classify the second input as an intended touch input or an unintended touch input, wherein the at least one factor is associated with a determination of an inter-arrival distance between a first position where the first input arrives at the touch surface and a second position where the second input arrives at the touch surface.

11. The method of claim 10, further comprising:

calculating an evaluation score based at least in part on the evaluation of the at least one factor;

comparing the evaluation score to at least one confidence threshold;

if, based on the comparing, the evaluation score satisfies the at least one confidence threshold, classifying the second input as the intended touch input or the unintended touch input; and

if, based on the comparing, the evaluation score fails to satisfy the at least one confidence threshold, evaluating at least one second factor associated with the first input and the second input, the at least one second factor being associated with a first movement of the first input relative to a second movement of the second input.

12. The method of claim 10, wherein the at least one factor is associated with a determination of an inter-arrival interval between a first time when the first input arrives at the touch surface and a second time when the second input arrives at the touch surface.

13. The method of claim 10, wherein the at least one factor is associated with a determination of a difference between a first direction of movement of the first input and a second direction of movement of the second input.

14. The method of claim 10, wherein the at least one factor is associated with a determination of a difference between a first velocity of movement of the first input and a second velocity of movement of the second input.

15. The method of claim 10, wherein the at least one factor is associated with a first determination of a first number of inputs in a first section of the touch surface relative to a second determination of a second number of inputs in a second section of the touch surface.

16. The method of claim 10, wherein the at least one factor is associated with a determination of a number of short-lived inputs.

17. A device comprising:

one or more processors;

memory storing computer-readable instructions that, when executed by the one or more processors, configure the device to perform operations comprising;

implementing a first classifier to evaluate a plurality of first classifier factors at least one of which is associated with a first arrival of a tool input relative to a second arrival of a touch input, the plurality of first classifier factors to classify the touch input as being either an intended touch input or an unintended touch input, wherein each first classifier factor of the plurality of first classifier factors has a corresponding weight to calculate an evaluation score;

determining, based at least in part on the evaluation score, that the first classifier is unable to confidently classify the touch input as being either the intended touch input or the unintended touch input; and

implementing a subsequent classifier to evaluate a plurality of second classifier factors associated with the tool input and the touch input, wherein the plurality of second classifier factors includes at least one first classifier factor with a corresponding weight adjusted to decrease an evaluation score influence of the at least one first classifier factor during the implementation of the subsequent classifier.

18. The device of claim 17, wherein:

one or more second classifier factors of the plurality of second classifier factors are based at least in part on movement of the tool input relative to movement of the touch input; and

the corresponding weights are set based at least in part on learned user input information.

19. The device of claim 17, wherein at least one first classifier factor determines an inter-arrival time between a first time when the tool input arrives at a touch surface and a second time when the touch input arrives at the touch surface.

20. The device of claim 17, wherein at least one first classifier factor determines an inter-arrival distance between a first position at which the tool input arrives at a touch surface and a second position at which the touch input arrives at the touch surface.