Abstract: A method of de-mosaicing pixel data from an image processor includes generating a pixel block that includes a plurality of image pixels. The method also includes determining a first image gradient between a first set of pixels of the pixel block and a second image gradient between a second set of pixels of the pixel block. The method also includes determining a first adaptive threshold value based on intensity of a third set of pixels of the pixel block. The pixels of the third set of pixels are adjacent to one another. The method also includes filtering the pixel block in a vertical, horizontal, or neutral direction based on the first and second image gradients and the first adaptive threshold value utilizing a plurality of FIR filters to generate a plurality of component images.

Abstract: The embodiments of the present disclosure provide a display substrate, a display panel, and a display device. The display substrate includes: a first base substrate, wherein a plurality of sub-pixel regions arranged in an array are provided on the first base substrate; and a reflective layer provided on one side of the first base substrate, wherein a surface of the reflective layer away from the first base substrate is formed to include a plurality of first bumps and a plurality of second bumps, and the first bump has a size greater than that of the second bump.

Abstract: An array substrate has a plurality of sub-pixel regions. The array substrate includes: a substrate; a first transistor and a second transistor that are disposed on a side of the substrate and located in each sub-pixel region; and a first pixel electrode and a second pixel electrode that are disposed on the side of the substrate and located in the sub-pixel region. The first pixel electrode and the second pixel electrode are insulated from each other; the first pixel electrode is electrically connected to the first transistor, and the second pixel electrode is electrically connected to the second transistor.

Abstract: A method of de-mosaicing pixel data from an image processor includes generating a pixel block that includes a plurality of image pixels. The method also includes determining a first image gradient between a first set of pixels of the pixel block and a second image gradient between a second set of pixels of the pixel block. The method also includes determining a first adaptive threshold value based on intensity of a third set of pixels of the pixel block. The pixels of the third set of pixels are adjacent to one another. The method also includes filtering the pixel block in a vertical, horizontal, or neutral direction based on the first and second image gradients and the first adaptive threshold value utilizing a plurality of FIR filters to generate a plurality of component images.

Abstract: Described is a multiple-camera system and process for re-identifying an agent located in a materials handling facility based on anterior views of agents. An anterior view of a newly detected agent may be partitioned and color signatures generated for each partition. Likewise, stored anterior views of agents (candidate agents) that may potentially be the newly detected agent are partitioned and color signatures generated for each partition. Based on the color signatures, a similarity between the anterior view of the newly detected agent and the candidate agents is determined. The similarity may be used to either determine that the newly detected agent is one of the candidate agents or reduce the set of candidate agents that are considered during a manual review.

Abstract: A computing system is configured to train an object classifier. Monocular image data and ground-truth data are received for a scene. Geometric context is determined including a three-dimensional camera position relative to a fixed plane. Regions of interest (RoI) and a set of potential occluders are identified within the image data. For each potential occluder, an occlusion zone is projected onto the fixed plane in three-dimensions. A set of occluded RoIs on the fixed plane are generated for each occlusion zone. Each occluded RoI is projected back to the image data in two-dimensions. The classifier is trained by minimizing a loss function generated by inputting information regarding the RoIs and the occluded RoIs into the classifier, and by minimizing location errors of each RoI and each occluded RoI of the set on the fixed plane based on the ground-truth data. The trained classifier is then output for object detection.

Abstract: In implementations of the subject matter described herein, a solution for object detection is proposed. First, a feature(s) is extracted from an image and used to identify a candidate object region in the image. Then another feature(s) is extracted from the identified candidate object region. Based on the features extracted in these two stages, a target object region in the image and a confidence for the target object region are determined. In this way, the features that characterize the image from the whole scale and a local scale are both taken into consideration in object recognition, thereby improving accuracy of the object detection.

Abstract: In some examples, a method comprises receiving pixel data from an image capture device having a color filter, wherein the pixel data represents a portion of an image. The method further includes performing wavelet decomposition on the pixel data to produce decomposed pixel data and determining a local intensity of the pixel data. The method also includes determining a noise threshold value based on the local intensity and a noise intensity function that is based on the color filter; determining a noise value for the pixel data based on the decomposed pixel data and the noise threshold value; and correcting the pixel data based on the noise value to produce an output image.

Abstract: An electronic paper is provided. An array substrate in the electronic paper includes a base, as well as a pixel electrode, a thin film transistor, and a shielding electrode that are disposed on the base. An orthographic projection of an active layer in the thin film transistor on the base is within an orthographic projection of the shielding electrode on the base and is within an orthographic projection of the pixel electrode on the base.

Abstract: A flat panel detector is provided, which includes a substrate and a plurality of photodiodes on the substrate. The flat panel detector further includes a first transparent conductive layer disposed on a side of the photodiodes away from the substrate. An orthographic projection of the first transparent conductive layer on the substrate at least partially overlaps the orthographic projection of each photodiode of the plurality of photodiodes on the substrate. The flat panel detector can mitigate or reduce the influence of external static electricity and improve the working stability.

Abstract: In accordance with implementations of the subject matter described herein, there is provided a solution for face synthesis. In this solution, a first image about a face of a first user and a second image about a face of a second user are obtained. A first feature characterizing an identity of the first user is extracted from the first image, and a second feature characterizing a plurality of attributes of the second image is extracted from the second image, where the plurality of attributes do not include the identity of the second user. Then, a third image about a face of the first user is generated based on the first and second features, the third image reflecting the identity of the first user and the plurality of attributes of the second image.

Abstract: The disclosure discloses an array substrate, a method for fabricating the same, a liquid crystal display panel, and a display device, where the array substrate includes: a base substrate; a convex component located on the base substrate; a reflection layer overlying the convex component; a thin film transistor located above a film layer at which the reflection layer is located; a pixel electrode located above a film layer at which the thin film transistor is located; and a planarization layer located between the pixel electrode and the reflection layer.

Abstract: The present disclosure provides a shift register unit, a driving method thereof, a gate driving circuit and a display device. The shift register unit includes a pull-up node state maintenance circuitry connected to a pull-up node and a first control voltage input end, and configured to control the pull-up node to be electrically connected to, or electrically disconnected from, the first control voltage input end in accordance with a potential at the pull-up node and an input potential at the first control voltage input end.

Abstract: A method for processing RGB-Infrared (RGB-IR) sensor data is provided that includes receiving a raw RGB-IR image, determining whether to process the raw RGB-IR image in day mode or night mode, generating, when day mode is determined, an infrared (IR) subtracted raw Bayer image from the raw RGB-IR image and processing the IR subtracted raw Bayer image in an image signal processor (ISP), and generating, when night mode is determined, an IR image from the raw RGB-IR image.

Abstract: Electronic paper includes a display panel and a drive component. The display panel may include a plurality of pixels disposed in a display region and a photoelectric conversion transistor disposed in a non-display region. The drive component is electrically connected to the plurality of pixels, and is electrically connected to a current output terminal of the photoelectric conversion transistor.

Abstract: A neural network architecture for attention-based efficient model adaptation is disclosed. A method includes accessing an input vector, the input vector comprising a numeric representation of an input to a neural network. The method includes providing the input vector to the neural network comprising a plurality of ordered layers, wherein each layer in at least a subset of the plurality of ordered layers is coupled with an adaptation module, wherein the adaptation module receives a same input value as a coupled layer for the adaptation module, and wherein an output value of the adaptation module is pointwise multiplied with an output value of the coupled layer to generate a next layer input value. The method includes generating an output of the neural network based on an output of a last one of the plurality of ordered layers in the neural network.

Abstract: A method for local automatic white balance (AWB) of wide dynamic range (WDR) images is provided that includes collecting statistics for local AWB by an image signal processor (ISP) from a first WDR image generated by the ISP, receiving, by the ISP, a plurality of local gain lookup tables (LUTs), one for each color channel, wherein the plurality of local gain LUTs is generated using the statistics, and applying, by the ISP, a gain value to each pixel in a second WDR image generated by the ISP, wherein the gain value for the pixel is determined by the ISP using the local gain LUT for the color channel of the pixel.

Abstract: In some examples, a method comprises receiving pixel data from an image capture device having a color filter, wherein the pixel data represents a portion of an image. The method further includes performing wavelet decomposition on the pixel data to produce decomposed pixel data and determining a local intensity of the pixel data. The method also includes determining a noise threshold value based on the local intensity and a noise intensity function that is based on the color filter; determining a noise value for the pixel data based on the decomposed pixel data and the noise threshold value; and correcting the pixel data based on the noise value to produce an output image.

Abstract: An electrostatic prevention circuit, an array substrate and a display device are provided. The electrostatic prevention circuit includes an electrostatic prevention sub-circuit, and the electrostatic prevention sub-circuit includes a thin film transistor and a capacitor; a gate electrode of the thin film transistor is connected to the capacitor, and the thin film transistor is controlled by a signal passing through the capacitor.

Abstract: In accordance with implementations of the subject matter described herein, there is proposed a solution of visual stylization of stereoscopic images. In the solution, a first feature map for a first source image and a second feature map for a second source image are extracted. The first and second source images correspond to first and second views of a stereoscopic image, respectively. A first unidirectional disparity from the first source image to the second source image is determined based on the first and second source images. First and second target images having a specified visual style are generated by processing the first and second feature maps based on the first unidirectional disparity. Through the solution, a disparity between two source images of a stereoscopic image are taken into account when performing the visual style transfer, thereby maintaining a stereoscopic effect in the stereoscopic image consisting of the target images.