Abstract: A fingerprint identification method, a fingerprint identification device, a display panel and a readable storage medium are provided. The fingerprint identification method includes: controlling at least one first light emitting unit in a first light emitting array to emit light; receiving, at a plurality of first positions in the first light emitting array, reflected signals caused by the light of the at least one first light emitting unit, respectively, as a plurality of first reflected light signals; and performing a fingerprint identification based on distances between the plurality of first positions in the first light emitting array and the at least one first light emitting unit and the plurality of first reflected light signals.

Abstract: An electrical signal detection module includes a photoelectrical signal application circuitry, an operational amplifier, a gain control circuitry and a master control circuitry. The gain control circuitry includes at least two gain control sub-circuitries connected in parallel to each other, and a discharge switching sub-circuitry connected in parallel to the gain control sub-circuitries. Each gain control sub-circuitry includes a gain switching sub-circuitry and a gain capacitive sub-circuitry connected in series to each other. The master control circuitry is configured to apply a discharge switching signal to the discharge switching sub-circuitry, and apply a gain switching control signal to the corresponding gain switching sub-circuitry. The gain switching sub-circuitry is configured to control a first end and a second end of the gain switching sub-circuitry to be electrically connected to each other in accordance with the gain switching control signal.

Abstract: A display panel and control methods thereof are provided. In one example, the display panel includes, a first substrate and a second substrate opposite to each other, and a solution encapsulated between the first substrate and the second substrate. In some examples, the solution includes opaque charged particles. In some examples, the first substrate includes a first electrode, the first electrode including a plurality of discrete sub-electrodes, and the second substrate includes a second electrode. Further, the control method may include adjusting an electric field between each of the plurality of discrete sub-electrodes and the second electrode, causing the opaque charged particles to undergo a gathering motion or a scattering motion.

Abstract: In one embodiment, a computer system includes a payload sub-system including interfaces to connect with respective devices, transfer data with the respective devices, and receive write transactions from the respective devices, a classifier to classify the received write transactions into payload data and control data, and a payload cache to store the classified payload data, and a processing unit (PU) sub-system including a local PU cache to store the classified control data, wherein the payload cache and the local PU cache are different physical caches in respective different physical locations in the computer system, and processing core circuitry configured to execute software program instructions to perform control and packet processing responsively to the control data stored in the local PU cache.

Abstract: The invention discloses a deep network lung texture recognition method combined with multi-scale attention, which belongs to the field of image processing and computer vision. In order to accurately recognize the typical texture of diffuse lung disease in computed tomography (CT) images of the lung, a unique attention mechanism module and multi-scale feature fusion module were designed to construct a deep convolutional neural network combing multi-scale and attention, which achieves high-precision automatic recognition of typical textures of diffuse lung diseases. In addition, the proposed network structure is clear, easy to construct, and easy to implement.

Abstract: The invention discloses a depth estimation and color correction method for monocular underwater images based on deep neural network, which belongs to the field of image processing and computer vision. The framework consists of two parts: style transfer subnetwork and task subnetwork. The style transfer subnetwork is constructed based on generative adversarial network, which is used to transfer the apparent information of underwater images to land images and obtain abundant and effective synthetic labeled data, while the task subnetwork combines the underwater depth estimation and color correction tasks with the stack network structure, carries out collaborative learning to improve their respective accuracies, and reduces the gap between the synthetic underwater image and the real underwater image through the domain adaptation strategy, so as to improve the network's ability to process the real underwater image.

Abstract: The invention discloses an unsupervised content-preserved domain adaptation method for multiple CT lung texture recognition, which belongs to the field of image processing and computer vision. This method enables the deep network model of lung texture recognition trained in advance on one type of CT data (on the source domain), when applied to another CT image (on the target domain), under the premise of only obtaining target domain CT image and not requiring manually label the typical lung texture, the adversarial learning mechanism and the specially designed content consistency network module can be used to fine-tune the deep network model to maintain high performance in lung texture recognition on the target domain. This method not only saves development labor and time costs, but also is easy to implement and has high practicability.

Abstract: The present invention provides a monocular unsupervised depth estimation method based on contextual attention mechanism, belonging to the technical field of image processing and computer vision. The invention adopts a depth estimation method based on a hybrid geometric enhancement loss function and a context attention mechanism, and adopts a depth estimation sub-network, an edge sub-network and a camera pose estimation sub-network based on convolutional neural network to obtain high-quality depth maps. The present invention uses convolutional neural network to obtain the corresponding high-quality depth map from the monocular image sequences in an end-to-end manner. The system is easy to construct, the program framework is easy to implement, and the algorithm runs fast; the method uses an unsupervised method to solve the depth information, avoiding the problem that ground-truth data is difficult to obtain in the supervised method.

Abstract: An image rectification method includes determining one or more reference points in a raw image captured using a lens for a plurality of target pixels in a target image, obtaining a subsection of the raw image based on the one or more reference points, and calculating a target pixel value for each of the plurality of target pixels based on one or more pixel values of one or more pixels in the subsection of the raw image.

Abstract: A touch panel and a driving method thereof, and a touch device are provided. The touch panel includes a first base substrate, a second base substrate, a first electrode, a piezoelectric layer and a second electrode. The second base substrate is opposite to the first base substrate. The first electrode is on a side of the first base substrate facing away from the second base substrate, and is configured to provide a reference. The piezoelectric layer is between the first electrode and the first base substrate. The second electrode is between the first base substrate and the second base substrate. The piezoelectric layer is configured to generate first charges on a side thereof close to the second electrode upon being pressed, and the second electrode is configured to couple the first charges at a pressed position and output a touch signal.

Abstract: The embodiments of the present disclosure provide a display panel, a display device, and a method for displaying Braille information. The display panel includes a plurality of scan lines, data lines, and display circuits arranged at intersections of the plurality of scan lines and the plurality of data lines. The display circuit includes a switch configured to be turned on or off according to a scan signal from the scan line, and a dot element coupled to the switch. The dot element includes a substrate, an electrode provided on the substrate, a thermosensitive layer provided on the electrode, and a dot key arranged on the thermosensitive layer. The electrode is coupled to the switch, and configured to be applied with a data signal from the data line when the switch is turned on. The thermosensitive layer is configured to be heated by the electrode to protrude the dot.

Abstract: A fingerprint identification module may include an array substrate (201), a plurality of point light sources (202) on the array substrate (201), and a plurality of photosensors (203) on the array substrate (201). The array substrate (201) may include a switch array (204) and a light emitting unit array (205) on the switch array (204). The plurality of point light sources (202) is configured to emit light to irradiate different regions of a finger at different times.

Abstract: A device for identifying a pattern over a first surface includes a photosensitive layer, and a light-guiding layer disposed between the photosensitive layer and the first surface. The photosensitive layer includes a plurality of photosensitive elements, each configured to convert incident light into an electrical signal. The light-guiding layer includes a plurality of light-guiding units, each positionally corresponding to one of the plurality of photosensitive elements. Each light-guiding unit includes a plurality of light-transmitting portions, each configured to guide a light beam reflected from a feature of the pattern positionally corresponding thereto to transmit therethrough and reach one of the plurality of photosensitive elements corresponding to the each of the plurality of light-guiding units. The device can be used for identification of fingerprint, as well as other biometric or non-biometric features, and has a reduced thickness and an improved accuracy for pattern identification.

Abstract: An optical structure, a display substrate and a display device are provided. The optical structure includes a first medium layer being transparent and an opaque layer which is arranged on the first medium layer and includes a plurality of vias. The optical structure is configured to allow light rays passing through each of the plurality of via to project to a corresponding light ray receiving area respectively.

Abstract: A fingerprint identification sensor may include a substrate (100), at least a photosensitive element (200) above the substrate (100), and at least a light source assembly (300). The light source assembly (300) may include a point light source (310) and a diffusing structure (320). The diffusing structure (320) may be configured to reduce intensity of light received by the photosensitive element (200) from a center region of the point light source (310).

Abstract: Provided is a method based on deep neural network to extract appearance and geometry features for pulmonary textures classification, which belongs to the technical fields of medical image processing and computer vision. Taking 217 pulmonary computed tomography images as original data, several groups of datasets are generated through a preprocessing procedure. Each group includes a CT image patch, a corresponding image patch containing geometry information and a ground-truth label. A dual-branch residual network is constructed, including two branches separately takes CT image patches and corresponding image patches containing geometry information as input. Appearance and geometry information of pulmonary textures are learnt by the dual-branch residual network, and then they are fused to achieve high accuracy for pulmonary texture classification. Besides, the proposed network architecture is clear, easy to be constructed and implemented.

Abstract: The present disclosure provides a touch control substrate, a touch screen, an electronic device, and a touch control method. The touch control substrate comprises a base substrate, and a plurality of touch control units on the base substrate in an array; each touch control unit comprises a touch control electrode and a sensing structure electrically connected to the touch control electrode; and in response to being touched, the touch control electrode transmits voltage to the sensing structure, to cause tactility change of the sensing structure.

Abstract: The present disclosure generally relates to the field of display technology, and in particular to a fingerprint recognition device and a display device having the fingerprint recognition device. A fingerprint recognition device includes a substrate; a plurality of point light sources on the substrate, which are configured to emit light; a plurality of light sensors on the substrate, which are configured to generate an electrical signal based on the light emitted from the plurality of point light sources and reflected from a touch surface, and a display layer on the plurality of light sensors.

Abstract: The present disclosure is related to an ultrasonic fingerprint detection assembly. The ultrasonic fingerprint detection assembly may include an ultrasonic fingerprint detection circuit and a living body detection circuit. The living body detection circuit may be configured to carry out living body detection at a rest stage of the ultrasonic fingerprint detection circuit.

Abstract: The present disclosure provides an ultrasonic fingerprint sensor, a display substrate, a driving method thereof and a display device. The ultrasonic fingerprint sensor includes: a base substrate; a driving structure provided on the base substrate and configured to transmit an ultrasonic signal; a receiving structure provided on the base substrate and configured to receive the ultrasonic signal reflected by a finger, and convert the ultrasonic signal into an electrical signal for determining fingerprint information, the driving structure and the receiving structure are provided in a same plane. Since the driving structure and the receiving structure of the ultrasonic fingerprint sensor of the present disclosure are in a same plane, the driving structure can be closer to the touch body (for example, a finger), which is advantageous for the ultrasonic waves generated by the driving structure to reach the finger to improve the touch accuracy.