Abstract: An input device is provided. The input device comprises a printed circuit board (PCB) assembly comprising: touch sensors configured to detect a user input from a user; a haptic coil configured to provide haptic feedback to the user in response to detecting the user input; and a near-field communication (NFC) antenna configured to facilitate NFC communications, wherein the haptic coil and the NFC antenna are on a same PCB of the PCB assembly.

Abstract: A method is provided. The method comprises obtaining, by a processing system and using a piezoelectric device, piezoelectric signals associated with user input on a sensing region of an input device; obtaining, by the processing system and using a corrective device, corrective signals associated with the user input on the sensing region of the input device; determining, by the processing system and based on the piezoelectric signals and the corrective signals, one or more events to be performed in response to the user input; and performing, by the processing system, the one or more events.

Abstract: This disclosure provides methods, devices, and systems for low-light imaging. In some implementations, an image processor may be configured to reduce or remove noise associated with an image based, at least in part, on a neural network. For example, the neural network may be trained to infer a denoised representation of the image. In some aspects, the image processor may scale the brightness level of the image to fall within a normalized range of values associated with the neural network. In some other aspects, a machine learning system may scale the brightness levels of input images to match the brightness levels of ground truth images used to train the neural network. Still further, in some aspects, the machine learning system may scale the brightness levels of the input images and the brightness levels of the ground truth images to fall within the normalized range of values during training.

Abstract: This disclosure provides methods, devices, and systems for low-light imaging. The present implementations more specifically relate to selecting images that can be used for training a neural network to infer denoised representations of images captured in low light conditions. In some aspects, a machine learning system may obtain a series of images of a given scene, where each of the images is associated with a different SNR (representing a unique combination of exposure and gain settings). The machine learning system may identify a number of saturated pixels in each image and classify each of the images as a saturated image or a non-saturated image based on the number of saturated pixels. The machine learning system may then select the non-saturated image with the highest SNR as the ground truth image, and the non-saturated images with lower SNRs as the input images, to be used for training the neural network.

Abstract: A method is provided. The method comprises obtaining, by a processing system and using a piezoelectric device, piezoelectric signals associated with user input on a sensing region of an input device; obtaining, by the processing system and using a corrective device, corrective signals associated with the user input on the sensing region of the input device; determining, by the processing system and based on the piezoelectric signals and the corrective signals, one or more events to be performed in response to the user input; and performing, by the processing system, the one or more events.

Abstract: This disclosure provides methods, devices, and systems for training machine learning models. The present implementations more specifically relate to techniques for automating the annotation of data for training machine learning models. In some aspects, a machine learning system may receive a reference image depicting an object of interest with one or more annotations and also may receive one or more input images depicting the object of interest at various distances, angles, or locations but without annotations. The machine learning system maps a set of points in the reference image to a respective set of points in each input image so that the annotations from the reference image are projected onto the object of interest in each input image. The machine learning system may further train a machine learning model to produce inferences about the object of interest based on the annotated input images.

Abstract: A memory device includes a first word and a second word. The first word has a first subset of a plurality of elements. The first subset of the plurality of elements each have a first set of sequential index values along a first dimension of a tensor, a first single index value for a second dimension of the tensor, and a second single index value for a third dimension of the tensor. The second word has a second subset of the plurality of elements. The second subset of the plurality of elements each have the first set of sequential index values along the first dimension of the tensor that is the same as the first word, the first single index value for the second dimension of the tensor that is the same as the first word, and a third single index value for the third dimension of the tensor that is different than the second single index value for the first word. The second word is adjacent to the first word in memory.

Abstract: An input device is provided. The input device comprises a printed circuit board (PCB) assembly comprising: touch sensors configured to detect a user input from a user; a haptic coil configured to provide haptic feedback to the user in response to detecting the user input; and a near-field communication (NFC) antenna configured to facilitate NFC communications, wherein the haptic coil and the NFC antenna are on a same PCB of the PCB assembly.

Abstract: This disclosure provides methods, devices, and systems for low-light imaging. The present implementations more specifically relate to selecting images that can be used for training a neural network to infer denoised representations of images captured in low light conditions. In some aspects, a machine learning system may obtain a series of images of a given scene, where each of the images is associated with a different SNR (representing a unique combination of exposure and gain settings). The machine learning system may identify a number of saturated pixels in each image and classify each of the images as a saturated image or a non-saturated image based on the number of saturated pixels. The machine learning system may then select the non-saturated image with the highest SNR as the ground truth image, and the non-saturated images with lower SNRs as the input images, to be used for training the neural network.

Abstract: This disclosure provides methods, devices, and systems for low-light imaging. In some implementations, an image processor may be configured to reduce or remove noise associated with an image based, at least in part, on a neural network. For example, the neural network may be trained to infer a denoised representation of the image. In some aspects, the image processor may scale the brightness level of the image to fall within a normalized range of values associated with the neural network. In some other aspects, a machine learning system may scale the brightness levels of input images to match the brightness levels of ground truth images used to train the neural network. Still further, in some aspects, the machine learning system may scale the brightness levels of the input images and the brightness levels of the ground truth images to fall within the normalized range of values during training.

Abstract: Fingerprint sensors include a plurality of optical sensor elements, a collimator filter disposed above the plurality of optical sensor elements, and a display disposed above the collimator filter, wherein the display is a fingerprint imaging light source. The collimator filter has a plurality of apertures, and the plurality of optical sensor elements is configured to receive light transmitted through one aperture of the plurality of apertures.

Abstract: A method for determining an amount of ambient light illumination is disclosed. The method includes: estimating a contribution per color component in an optical sensing region of an input frame to be displayed on a display device, wherein the optical sensing region corresponds to a location of an optical sensor in the display device, wherein the input frame comprises digital information for each color component for each pixel of the input frame; causing the optical sensor to detect an amount of illumination in the optical sensing region based on illuminating the display device with a representation of the input frame; and determining the amount of ambient light illumination based on the estimated contribution per color component in the optical sensing region of the input frame and the amount of illumination in the optical sensing region detected by the optical sensor.

Abstract: A method and apparatus for voice search. A voice search system for a voice-enabled device captures one or more images of a scene, detects a user in the one or more images, determines whether the position of the user satisfies an attention-based trigger condition for initiating a voice search operation, and selectively transmits a voice query to a network resource based at least in part on the determination. The voice query may include audio recorded from the scene and/or the one or more images captured of the scene. The voice search system may further determine whether the trigger condition is satisfied as a result of a false trigger and disable the voice-enabled device from transmitting the voice query to the network resource based at least in part on the trigger condition being satisfied as the result of a false trigger.

Abstract: Systems and methods for performing operations based on acoustic locationing are described. An example device includes one or more microphones configured to sense sound waves propagating in an environment. The example device also includes one or more processors and one or more memories coupled to the one or more processors. The one or more memories store instructions that, when executed by the one or more processors, cause the device to recover sound wave information from the sensed sound waves, detect a presence of one or more persons in the environment based on the received sound wave information, determine an operation to be performed by one or more smart devices based on the detected presence of one or more persons, and instruct the one or more smart devices to perform the operation.

Abstract: Systems and methods for performing operations based on acoustic locationing are described. An example device includes one or more microphones configured to sense sound waves propagating in an environment. The example device also includes one or more processors and one or more memories coupled to the one or more processors. The one or more memories store instructions that, when executed by the one or more processors, cause the device to recover sound wave information from the sensed sound waves, detect a presence of one or more persons in the environment based on the received sound wave information, determine an operation to be performed by one or more smart devices based on the detected presence of one or more persons, and instruct the one or more smart devices to perform the operation.

Abstract: Fingerprint sensors include a plurality of optical sensor elements, a collimator filter disposed above the plurality of optical sensor elements, and a display disposed above the collimator filter, wherein the display is a fingerprint imaging light source. The collimator filter has a plurality of apertures, and the plurality of optical sensor elements is configured to receive light transmitted through one aperture of the plurality of apertures.

Abstract: Systems and methods for optical imaging are disclosed. The optical fingerprint sensor includes an image sensor array; a collimator filter layer disposed above the image sensor array, the collimator filter layer having an array of apertures; and an illumination layer disposed above the collimator filter layer. The collimator filter layer filters reflected light such that only certain of the reflected light beams reach optical sensing elements in the image sensor array. Employing the collimator filter layer prevents blurring while allowing for a lower-profile image sensor.

Abstract: A method and apparatus for voice search. A voice search system for a voice-enabled device captures one or more images of a scene, detects a user in the one or more images, determines whether the position of the user satisfies an attention-based trigger condition for initiating a voice search operation, and selectively transmits a voice query to a network resource based at least in part on the determination. The voice query may include audio recorded from the scene and/or the one or more images captured of the scene. The voice search system may further determine whether the trigger condition is satisfied as a result of a false trigger and disable the voice-enabled device from transmitting the voice query to the network resource based at least in part on the trigger condition being satisfied as the result of a false trigger.

Abstract: A method for determining an amount of ambient light illumination is disclosed. The method includes: estimating a contribution per color component in an optical sensing region of an input frame to be displayed on a display device, wherein the optical sensing region corresponds to a location of an optical sensor in the display device, wherein the input frame comprises digital information for each color component for each pixel of the input frame; causing the optical sensor to detect an amount of illumination in the optical sensing region based on illuminating the display device with a representation of the input frame; and determining the amount of ambient light illumination based on the estimated contribution per color component in the optical sensing region of the input frame and the amount of illumination in the optical sensing region detected by the optical sensor.

Abstract: Devices and method are provided that facilitate improved input device performance. Specifically, the systems and methods are configured to identify a portion of an image of sensor values as corresponding to at least one sensed object in the sensing region, determine a polygon corresponding to the identified portion of the image, and determine a contact characterization of the at least one sensed object based on the polygon. The determination of a polygon corresponding to a sensed object facilitates improved contact characterization of the sensed object. For example, the determined polygon may be used to determine if the sensed object is actually more than one object. As a second example, the determined polygon may be used to determine the orientation of the sensed object. In addition, determined polygons may be used to more accurately track changes in the position of the sensed object.