Methods and systems for automated structured keyboard layout generation

    公开(公告)号:US12154198B2

    公开(公告)日:2024-11-26

    申请号:US17727335

    申请日:2022-04-22

    Abstract: A method includes: obtaining an image of a keyboard layout; detecting, from the image, a plurality of key boundaries; determining a label string for a portion of the image defined by a corresponding key boundary from the plurality of key boundaries; selecting, for the determined label string, a corresponding key action; generating a keyboard layout definition for the image of the keyboard layout, the keyboard layout definition including a key definition for the corresponding key boundary, the key definition having: (i) a position for rendering of a key, (ii) a label configured to be rendered at the position of the key, and (iii) an action configured to be caused by selection of the key; and communicating the keyboard layout definition for deployment to a mobile device.

    Virtual keypads for hands-free operation of computing devices

    公开(公告)号:US11442582B1

    公开(公告)日:2022-09-13

    申请号:US17193610

    申请日:2021-03-05

    Abstract: A method includes: detecting, at a computing device coupled to an image sensor, an input request; in response to detecting the input request, capturing a reference image via the image sensor, the reference image containing a virtual keypad having a set of virtual keys; detecting, in the reference image, the set of virtual keys; capturing, via the image sensor, a key-press image of the virtual keypad; detecting, in the key-press image, a subset of the virtual keys; comparing the set of virtual keys and the subset of virtual keys to identify a key-press obscuring one of the virtual keys; and returning input data corresponding to the obscured virtual key.

    Virtual Keypads for Hands-Free Operation of Computing Devices

    公开(公告)号:US20220283667A1

    公开(公告)日:2022-09-08

    申请号:US17193610

    申请日:2021-03-05

    Abstract: A method includes: detecting, at a computing device coupled to an image sensor, an input request; in response to detecting the input request, capturing a reference image via the image sensor, the reference image containing a virtual keypad having a set of virtual keys; detecting, in the reference image, the set of virtual keys; capturing, via the image sensor, a key-press image of the virtual keypad; detecting, in the key-press image, a subset of the virtual keys; comparing the set of virtual keys and the subset of virtual keys to identify a key-press obscuring one of the virtual keys; and returning input data corresponding to the obscured virtual key.

    Method and apparatus for providing multimodal input data to client applications

    公开(公告)号:US11423215B2

    公开(公告)日:2022-08-23

    申请号:US16219696

    申请日:2018-12-13

    Abstract: A method of providing multimodal input data to client applications in a data capture device with multiple input assemblies includes: storing, in a memory of the device: a client application defining input fields; and a plurality of input profiles each containing an input field identifier and a modality identifier corresponding to one of the input assemblies. Via execution of the client application, the device controls a display to simultaneously render a plurality of the input fields; determines an active one of the rendered input fields and obtains an active field identifier of the active input field; retrieves an active one of the input profiles containing a field identifier that matches the active input field identifier; controls one of the input assemblies corresponding to the modality identifier of the active input profile to obtain input data; and populates the active input field with the obtained input data.

Patent Agency Ranking