Methods and apparatus for cross-coupling correction on a touch sensor panel
Cross-coupling correction techniques on a touch sensor panel can be improved using machine learning models (particularly for touch sensor panels with relatively low signal-to-noise ratio). In some examples, the machine learning model can be implemented using a neural network. The neural network can receive a touch image and perform cross-coupling correction to mitigate cross-talk due to routing traces of the touch sensor panel. Mitigating cross-talk can improve touch sensing accuracy, reduce jitter, and/or reduce false positive touch detection.
1. A touch-sensitive device comprising:
a plurality of touch electrodes;
sensing circuitry configured to measure signals at the plurality of touch electrodes to generate a touch image, wherein a signal-to-noise ratio (SNR) for measurement of the signals is less than a threshold SNR; and
machine learning processing circuitry configured to:
in response to an object contacting a first region of the touch-sensitive device and moving across the touch-sensitive device in a first direction:
detect a first input from the object in the first region;
detect a second input from the object in a second region, different than the first region, of the touch-sensitive device; and
ignore the second input from the object in the second region with greater than a threshold accuracy.
2. The touch-sensitive device of claim 1 , where the first region is within a threshold distance from a first edge of the touch-sensitive device and the second region is within a threshold distance from a second edge of the touch-sensitive device opposite the first edge of the touch-sensitive device.
3. The touch-sensitive device of claim 2 , wherein the plurality of touch electrodes includes first touch electrodes in the first region and second touch electrodes in the second region, wherein the second touch electrodes are routed to the sensing circuitry using routing traces within a threshold distance of first touch electrodes such that the object contacting the first region results in cross-coupling to the second touch electrodes in the second region.
4. The touch-sensitive device of claim 1 , wherein the second input in the second region includes movement of a threshold distance across the touch-sensitive device in a second direction different than the first direction with greater than a threshold distance.
5. The touch-sensitive device of claim 4 , wherein the second input triggers activation of a user interface following the movement of the threshold distance.
6. The touch-sensitive device of claim 4 , wherein the second direction is within a threshold angle of orthogonal to the first direction.
7. The touch-sensitive device of claim 1 , wherein the threshold SNR is less than 5.
8. The touch-sensitive device of claim 1 , wherein the threshold accuracy is 99.9%.
9. The touch-sensitive device of claim 1 , wherein the threshold accuracy is 99%.
10. The touch-sensitive device of claim 1 , wherein the plurality of touch electrodes is arranged in a pixelated touch electrode configuration.
11. A method comprising:
measuring signals at a plurality of touch electrodes of a touch-sensitive device to generate a touch image, wherein a signal-to-noise ratio (SNR) for measurement of the signals is less than a threshold SNR; and
in response to an object contacting a first region of the touch-sensitive device and moving across the touch-sensitive device in a first direction:
detecting a first input from the object in the first region;
detecting a second input from the object in a second region, different than the first region, of the touch-sensitive device; and
ignoring the second input from the object in the second region with greater than a threshold accuracy.
12. The method of claim 11 , where the first region is within a threshold distance from a first edge of the touch-sensitive device and the second region is within a threshold distance from a second edge of the touch-sensitive device opposite the first edge of the touch-sensitive device.
13. The method of claim 12 , wherein the plurality of touch electrodes includes first touch electrodes in the first region and second touch electrodes in the second region, wherein the second touch electrodes are routed to the sensing circuitry using routing traces within a threshold distance of first touch electrodes such that the object contacting the first region results in cross-coupling to the second touch electrodes in the second region.
14. The method of claim 13 , wherein the second input in the second region includes movement of a threshold distance across the touch-sensitive device in a second direction different than the first direction with greater than a threshold distance.
15. The method of claim 14 , wherein the second input triggers activation of a user interface following the movement of the threshold distance.
16. The method of claim 14 , wherein the second direction is within a threshold angle of orthogonal to the first direction.
17. The method of claim 11 , wherein the threshold SNR is less than 5.
18. The method of claim 11 , wherein the threshold accuracy is 99.9%.
19. The method of claim 11 , wherein the threshold accuracy is 99%.
20. The method of claim 11 , wherein the plurality of touch electrodes is arranged in a pixelated touch electrode configuration.
21. A non-transitory computer readable storage medium storing instructions, which when executed by a touch-sensitive device including a plurality of touch electrodes and processing circuitry, cause the processing circuitry to:
measure signals at a plurality of touch electrodes to generate a touch image, wherein a signal-to-noise ratio (SNR) for measurement of the signals is less than a threshold SNR; and
in response to an object contacting a first region of the touch-sensitive device and moving across the touch-sensitive device in a first direction:
detect a first input from the object in the first region;
detect a second input from the object in a second region, different than the first region, of the touch-sensitive device; and
ignore the second input from the object in the second region with greater than a threshold accuracy.
22. The non-transitory computer readable storage medium of claim 21 , wherein the threshold accuracy is 99.9%.
23. The non-transitory computer readable storage medium of claim 21 , wherein the plurality of touch electrodes is arranged in a pixelated touch electrode configuration.