Abstract: An image classification method, a computer device, and a medium are disclosed. The method includes: acquiring a middle-level semantic feature of an image to be classified through a visual dictionary; and classifying the image to be classified according to the middle-level semantic feature of the image to be classified using a classification model based on middle-level semantic features.

Abstract: Provided is a method for compressing texture data of a three-dimensional model, including: acquiring data of polygonal surfaces constituting a contour of a target three-dimensional model, and data of a texture image and a phase plane of the contour; acquiring the texture data of texture points in a texture point group corresponding to each polygonal surface, the texture points in the texture point group including first and second texture points; assigning a weight to each texture point in each texture point group according to the texture data of the first texture points in the texture point group; calculating a sum of weights of each texture point in each texture point group; and compressing the texture data, according to a target compressed data amount, and the texture data and the sum of weights of the texture point whose sum of weights is not zero.

Abstract: The present disclosure provides a method for driving a display device, an apparatus for driving a display device, a display device and a computer readable medium. The display device includes a backlight module, and the backlight module includes a plurality of backlight partitions. The driving method may include: determining backlight signal values of the plurality of backlight partitions according to input grayscale values of pixels in an image to be displayed; determining a backlight jump value of each of the plurality of backlight partitions according to the backlight signal values of the plurality of backlight partition; adjusting the backlight signal values of the plurality of backlight partitions according to the backlight jump values to obtain adjusted backlight signal values; and driving the backlight module to emit light using the adjusted backlight signal values of the plurality of backlight partitions.

Abstract: Embodiments of the present disclosure relate to a method for analyzing an imaging quality of an imaging system. The imaging system comprises a spatial light modulator. The spatial light modulator comprises pixel units arranged in an array. The method comprises obtaining a transmittance distribution function of the spatial light modulator based on a structural parameter of the pixel unit, wherein the structural parameter is an aperture ratio. The imaging quality analysis parameter of the imaging system is obtained based on the transmittance distribution function of the spatial light modulator. Then, the imaging quality of the imaging system is analyzed based on the imaging quality analysis parameter.

Abstract: A camera positioning method, device and medium are provided. The method includes: determining positioning configuration information; determining, according to the positioning configuration information, positioning information of the camera by a preset algorithm, the positioning information including distance limitation data which defines a distance between a target and the camera; and determining a position of the camera according to the positioning information, wherein the positioning configuration information includes target data, ratio data of a target image in an image captured by the camera, and camera parameter data.

Abstract: The application discloses a method and a device for calculating parameters of a gaze-point calculation model. The method includes: displaying multiple calibration points in sequence on a device screen, and collecting multiple pupil-coordinates data corresponding to each of at least one calibration point of the multiple calibration points; for each calibration point of the at least one calibration point, screening the multiple pupil-coordinates data corresponding to the calibration point, to obtain at least one pupil-coordinates calibration data corresponding to the calibration point; calculating multiple parameters of the gaze-point calculation model according to coordinates data of each calibration point and the at least one pupil-coordinates calibration data corresponding to the calibration point.

Abstract: Disclosed herein includes a method, an apparatus, a display device and storage medium storing computer executable instructions for positioning a gaze point. The method for obtaining a gaze point in a display device may comprise capturing a real time eye image, obtaining a real time pupil center point from the real time eye image, determining a gaze target zone based on the real time pupil center point and obtaining a gaze point on a target screen generated by the display device based on the real time pupil center point and a mapping ratio for the gaze target zone.

Abstract: The disclosure provides a method for defect classification, including: extracting a low-level feature of a defect region from a defect image; encoding the low-level feature by using a defect dictionary to obtain a middle-level semantic feature corresponding to the low-level feature; classifying a defect in the defect region of the defect image into one of a plurality of defect categories based on the middle-level semantic feature, wherein the defect dictionary includes a defect intra-category dictionary and a defect inter-category dictionary.

Abstract: An image segmentation method, an image segmentation apparatus, an image segmentation device are provided, the image segmentation method including: extracting, from a current frame of a video image, a skeleton two-dimensional estimation and a skeleton three-dimensional estimation of a human three-dimensional skeleton; obtaining a target three-dimensional skeleton based on the skeleton two-dimensional estimation and the skeleton three-dimensional estimation; implementing image segmentation based on the target three-dimensional skeleton; wherein the human three-dimensional skeleton has multiple nodes, and the video image is a two-dimensional image, when calculating the target three-dimensional skeleton in the current frame, by comprehensively considering the skeleton two-dimensional estimation and skeleton three-dimensional skeleton estimation of the human three-dimensional skeleton in the current frame, the accuracy and robustness of the obtained target three-dimensional skeleton can be improved, thereby improv

Abstract: Embodiments of the present disclosure provides an image processing method, comprising: acquiring an initial image comprising an image of pupil; acquiring an accumulative histogram set of grayscale values of pixels in the initial image; determining a threshold for binarizing the initial image according to a grayscale value corresponding to a target region in respective accumulative histograms in the accumulative histogram set, wherein the target region corresponds to the image of pupil in the initial image; and binarizing the initial image according to the threshold. An image processing apparatus and a wearable device are further provided.

Abstract: An image classification method, a computer device, and a medium are disclosed. The method includes: acquiring a middle-level semantic feature of an image to be classified through a visual dictionary; and classifying the image to be classified according to the middle-level semantic feature of the image to be classified using a classification model based on middle-level semantic features.

Abstract: A wearable device, a signal processing method and a signal processing device are disclosed. The wearable device includes a processor and a signal collector electrically connected to the processor. The signal collector includes at least one electroencephalogram sensor configured to collect an electroencephalogram signal and at least one electrooculogram sensor configured to collect an electrooculogram signal. The processor is configured to generate a control signal based on the electroencephalogram signal and the electrooculogram signal, and the electroencephalogram sensor and the electrooculogram sensor are different sensors.