Abstract: A capacitive fingerprint sensor is configured to be integrated in a display. The capacitive fingerprint sensor includes a plurality of transmitter electrodes. Each respective transmitter electrode including at least one transmitter conductor formed in a first metal layer of a sensor stack and disposed between pixels of a display. The capacitive fingerprint sensor further includes a plurality of receiver electrodes. Each respective receiver electrode including at least one receiver conductor formed in a second metal layer of a sensor stack and disposed between pixels of the display. The receiver electrodes have an orientation different from the transmitter electrodes.

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: A method of capacitive sensing includes obtaining a capacitive touch profile from multiple receiver electrodes disposed in a sensing region of an input device and obtaining an active pen profile, different from the capacitive touch profile, from the multiple receiver electrodes. The method also includes adjusting, using the capacitive touch profile, the active pen profile to obtain a corrected active pen profile and determining a position of an active pen in the sensing region, using the corrected active pen profile.

Abstract: This disclosure provides methods, devices, and systems for neural network inferencing. The present implementations more specifically relate to performing inferencing operations on high dynamic range (HDR) image data in a lossless manner. In some aspects, a machine learning system may receive a number (K) of bits of pixel data associated with an input image and subdivide the K bits into a number (M) of partitions based on a number (N) of bits in each operand operated on by an artificial intelligence (AI) accelerator, where N<K. For example, the K bits may represent a pixel value associated with the input image. In some implementations, the AI accelerator may perform an inferencing operation based on a neural network by processing the M partitions, in parallel, as data associated with M channels, respectively, of the input image.

Abstract: Embodiments described herein provide a combined multi-source time difference of arrival (TDOA) tracking and voice activity detection (VAD) mechanism that is applicable for generic array geometries, e.g., a microphone array that lies on a plane. The combined multi-source TDOA tracking and VAD mechanism scans the azimuth and elevation angles of the microphone array in microphone pairs, based on which a planar locus of physically admissible TDOAs can be formed in the multi-dimensional TDOA space of multiple microphone pairs. In this way, the multi-dimensional TDOA tracking reduces the number of calculations that was usually involved in traditional TDOA by performing the TDOA search for each dimension separately.

Abstract: An input device that includes multiple electrodes disposed in a sensing region of the input device and a sensing circuit coupled to a first electrode and configured to detect an input object proximate the sensing region. The sensing circuit includes an amplifier having an inverting input coupled to the first electrode, a non-inverting input coupled to a drive signal, and an output generating a resulting signal. The sensing circuit includes a feedback capacitor coupled between the output and the inverting input of the amplifier. The drive signal comprises a first sinusoidal signal having a first operating frequency and a second sinusoidal signal having a second operating frequency. The resulting signal is determined by the feedback capacitor and a capacitance of the first electrode caused by the input object. The resulting signal generates a sensing signal on the first electrode.

Abstract: This disclosure provides methods, devices, and systems for transmitting and receiving image data. The present implementations more specifically relate to repurposing non-video interfaces to receive image data. In some aspects, an image processing device may be coupled to an image source via an audio interface. For example, the audio interface may be an inter-IC sound (I2S) serial bus interface having at least a serial data input and a word select (WS) input. In some implementations, the serial data input may be coupled to receive image data from the image source and the WS input may be coupled to receive a WS signal that tracks a horizontal synchronization (HSYNC) signal associated with the image data. Accordingly, the image processing device may capture (or store) frames of received image data, where the beginning of each frame is aligned with an edge of the WS signal (and thus, the HSYNC signal).

Abstract: Systems and methods provide input and output mode control for audio processing on a user device. Audio processing may be configured by monitoring audio activity on a device having at least one microphone and a digital audio processing unit, collecting information from the monitoring of the activity, including an identification of at least one application utilizing audio processing, and determining a context for the audio processing, the context including at least one of a hardware, software, audio signal and/or environmental context. An audio signal processing configuration is determined based on the application and determined context, an associated audio signal processing mode is selected, and an optimized audio signal generated.

Abstract: A method is provided. The method comprises: obtaining, by a processing system and using a set of rotation electrodes that interact with the knob interface, first resulting signals and second resulting signals; determining, by the processing system, an initial state of the knob interface using the first resulting signals and the second resulting signals; obtaining, by the processing system and using the set of rotation electrodes, third resulting signals indicating a first rotational state of the knob interface, based at least in part on the knob interface being rotated from the initial state to the first rotational state; determining, by the processing system, the rotational direction of the knob interface using the first resulting signals, the second resulting signals, and the third resulting signals; and adjusting, by the processing system, a setting using the determined rotational direction.

Abstract: An input device that includes multiple electrodes disposed in a sensing region of the input device and a sensing circuit coupled to a first electrode and configured to detect an input object proximate the sensing region. The sensing circuit includes an amplifier having an inverting input coupled to the first electrode, a non-inverting input coupled to a drive signal, and an output generating a resulting signal. The sensing circuit includes a feedback capacitor coupled between the output and the inverting input of the amplifier. The drive signal comprises a first sinusoidal signal having a first operating frequency and a second sinusoidal signal having a second operating frequency. The resulting signal is determined by the feedback capacitor and a capacitance of the first electrode caused by the input object. The resulting signal generates a sensing signal on the first electrode.

Abstract: A processing system including an amplifier configured to generate, from multiple spatial-common-mode-processed signals, a spatial common mode estimate and multiple feedback signals. The processing system includes multiple charge integrators configured to obtain resulting signals from the capacitive sensor electrodes, each of the resulting signals including a spatial common mode component and a residual noise component. The charge integrators generate multiple spatial-common-mode-processed signals by mitigating the spatial common mode component and the residual noise component in the resulting signals using the feedback signals. The processing system includes a programmable gain amplifier configured to determine the spatial common mode estimate.

Abstract: A display driver includes a driver circuit and a sensing controller. The driver circuit is configured to drive a display panel according to display information. The display panel defines a sensing region. The sensing controller interface circuit is configured to transmit an output vertical sync signal to a proximity sensing controller. The proximity sensing controller is configured to generate positional information of an input object based at least in part on a resulting signal received from a sensor electrode disposed in the sensing region. The output vertical sync signal comprises encoding the display information in the output vertical sync signal.

Abstract: A touchscreen display device includes: a display; a flexible printed circuit; touch sensing electrodes connected to the flexible printed circuit; and a multi-functional ambient light sensor package mounted on the flexible printed circuit. The multi-functional ambient light sensor package includes: an ambient light sensor; transmitter and receiver circuitry connected to the touch sensing electrodes via the flexible printed circuit; and a controller configured to obtain capacitance information from the touch sensing electrodes and ambient light information from the ambient light sensor via a single chip. The multi-functional ambient light sensor package may be packaged as a wafer-level chip-scale package (WLCSP).

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 controlling motion-activated switches. The present implementations more specifically relate to relay controller that prevent motion-activated switches from turning off devices associated with an environment in which people are present. In some aspects, a motion-activated switch may include a relay controller coupled to a motion sensor, a camera, and a relay. The motion sensor outputs a motion trigger to the relay controller responsive to detecting motion in an environment. The motion trigger may cause the relay controller to acquire one or more images of the environment, via the camera, and selectively toggle the relay based on the acquired images. For example, the relay controller may close the relay responsive to identifying an image that includes an object of interest or may open the relay controller may open the relay responsive to identifying an image that does not include an object of interest.

Abstract: A display device includes a display panel, a backlight module, and backlight control circuitry. The backlight module is configured to illuminate the display panel, the backlight module comprising a plurality of light sources. The backlight control circuitry is configured to control first luminance of a first light source of the plurality of light sources based at least in part on a first weighted average of brightness values for a first set of pixels of the display panel.

Abstract: A voltage clamp is disclosed. The voltage clamp may include a plurality of transistors to limit the voltage between a power supply and ground. In addition, the voltage clamp may include a positive feedback signal to reduce turn-on time of the plurality of transistors.

Abstract: A processing system configured to detect an input object proximate the processing system. The processing system includes sensor circuitry configured to make a determination, when the processing system is in a low ground mass (LGM) state, that a large object is proximate to sensor electrodes of the processing system. The sensor circuitry is further configured, in response to a determination that a large object is proximate the sensor electrodes while the processing system is in the LGM state, to drive a first group of sensor electrodes with one of an inverted signal or a non-inverted signal and drive a second group of sensor electrodes with a static DC voltage.

Abstract: In general, in one aspect, one or more embodiments relate to an input device that includes a proximity sensing panel including sensor electrodes, and a proximity sensing circuit. The proximity sensing circuit is configured to determine that an image refresh rate to an equal or lower frequency than a beacon signal rate. The input-display device is configured to align transmitting a beacon signal on proximity sensing panel to during non-refresh period of a display or perform an additional image refresh frame on the display panel immediately before a next Vsync signal and a corresponding non-refresh period.

Abstract: A classification training system comprises a neural network configured to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module configured to train the neural network using the training dataset. The classification training module includes a forward pass processing module, and a backward pass processing module. The backward pass processing module is configured to determine whether a current frame is in a region of target (ROT), determine ROT information such as beginning and length of the ROT and update weights and biases using a cross-entropy cost function and a tunable many-or-one detection (MOOD) cost function, that comprises a tunable hyperparameter for tuning the classifier for a particular task. The backward pass module further computes a soft target value using ROT information and computes a signal output error using the soft target value and network output value.