公开(公告)号：US11907475B2

公开(公告)日：2024-02-20

申请号：US17448866

申请日：2021-09-24

Applicant: Apple Inc.

Inventor： Hojjat Seyed Mousavi ,  Behrooz Shahsavari ,  Bongsoo Suh ,  Utkarsh Gaur ,  Nima Ferdosi ,  Baboo V. Gowreesunker

IPC: G06F3/041 ,  G06F3/0354 ,  G06N3/04 ,  G06F3/044 ,  G06N20/20 ,  G06F18/214

CPC classification number: G06F3/0418 ,  G06F3/03545 ,  G06F3/0446 ,  G06F3/04162 ,  G06F3/04166 ,  G06F18/214 ,  G06N3/04 ,  G06N20/20 ,  G06F3/0442 ,  G06F2203/04101

Abstract: In some examples, an electronic device can use machine learning techniques, such as convolutional neural networks, to estimate the distance between a stylus tip and a touch sensitive surface (e.g., stylus z-height). A subset of stylus data sensed at electrodes closest to the location of the stylus at the touch sensitive surface including data having multiple phases and frequencies can be provided to the machine learning algorithm. The estimated stylus z-height can be compared to one or more thresholds to determine whether or not the stylus is in contact with the touch sensitive surface. In some examples, the electronic device can use machine learning techniques to estimate the (x, y) position and/or tilt and/or azimuth angles of the stylus tip at the touch sensitive surface based on a subset of stylus data.

公开(公告)号：US20240103633A1

公开(公告)日：2024-03-28

申请号：US18370837

申请日：2023-09-20

Applicant: Apple Inc.

Inventor： Bongsoo Suh ,  Behrooz Shahsavari ,  Charles Maalouf ,  Hojjat Seyed Mousavi ,  Laurence Lindsey ,  Shivam Kumar Gupta

IPC: G06F3/01 ,  G06N3/0464

CPC classification number: G06F3/017 ,  G06N3/0464

Abstract: Embodiments are disclosed for hold gesture recognition using machine learning (ML). In an embodiment, a method comprises: receiving sensor signals indicative of a hand gesture made by a user, the sensor data obtained from at least one sensor of a wearable device worn by the user; generating a first embedding of first features extracted from the sensor signals; predicting a first part of a hold gesture based on a first ML gesture classifier and the first embedding; generating a second embedding of second features extracted from the sensor signals; predicting a second part of the hold gesture based on a second ML gesture classifier and the second embedding; predicting a hold gesture based at least in part on outputs of the first and second ML gesture classifiers and a prediction policy; and performing an action on the wearable device or other device based on the predicted hold gesture.

公开(公告)号：US11287926B1

公开(公告)日：2022-03-29

申请号：US17161499

申请日：2021-01-28

Applicant: Apple Inc.

Inventor： Behrooz Shahsavari ,  Bongsoo Suh ,  Utkarsh Gaur ,  Nima Ferdosi ,  Baboo V. Gowreesunker

IPC: G06F3/041 ,  G06F3/0354 ,  G06F3/044 ,  G06K9/62 ,  G06N3/04

Abstract: In some examples, an electronic device can use machine learning techniques, such as convolutional neural networks, to estimate the distance between a stylus tip and a touch sensitive surface (e.g., stylus z-height). A subset of stylus data sensed at electrodes closest to the location of the stylus at the touch sensitive surface including data having multiple phases and frequencies can be provided to the machine learning algorithm. The estimated stylus z-height can be compared to one or more thresholds to determine whether or not the stylus is in contact with the touch sensitive surface.