Abstract: A method and an image processing device for image color enhancement are proposed. The method includes the following steps. An input image having input pixels is received, where each of the input pixels includes a luminance component and two chrominance components. A saturation gain of each of the input pixels is determined according to the chrominance components thereof. The chrominance components of each of the input pixels are adjusted according to the saturation gain thereof so as to generate enhanced pixels. An enhanced image is outputted according to the enhanced pixels.

Abstract: An image processing method and apparatus, a storage medium and an electronic device are disclosed. The method comprises: acquiring a first face image in a real scene and a second face image in a virtual scene, wherein the second face image is generated at least according to a first value of at least one target parameter, and the at least one target parameter is used for determining at least one attribute of a face image in the virtual scene; extracting at least one first image feature from the first face image, and extracting at least one second image feature from the second face image; acquiring a similarity between the at least one first image feature and the at least one second image feature; adjusting the first value of the at least one target parameter based on the similarity to obtain a target value of the at least one target parameter; and rendering the at least one target parameter according to the target value to obtain the target face image in the virtual scene.

Abstract: Collation device is configured to include a processor, and a storage unit that stores a blurring amount which is set in advance for collation in association with the registered image in advance, in which the processor blurs a face image obtained by imaging an authenticated person with imaging unit with a blurring amount for collation in association with a registered image corresponding to the face image, and uses the image blurred with the blurring amount for collation to perform face authentication. The blurring amount for collation is set such that, a real image blurred by the blurring amount can be authenticated but a photographic image blurred by the blurring amount cannot be authenticated, the real image being a face image obtained by imaging a real face of an authenticated person and the photographic image being a face image obtained by imaging a face photograph of the authenticated person.

Abstract: Embodiments of the present application provide an image-based position detection method, an apparatus, a device and a storage medium. Images captured at the same time by a plurality of photographing devices mounted in different orientations are acquired, where the plurality of photographing devices are synchronous in time; a two-dimensional position of a target object in each of the images is detected; and a three-dimensional position of the target object in an actual space is determined based on the two-dimensional position of the target object in each of the images and internal parameters and external parameters of the plurality of photographing devices. The embodiments of the present application implement a three-dimensional positioning solution based on a plurality of cameras, thereby improving the reliability and accuracy of object positioning.

Abstract: A method, an electronic device and a storage medium for expression driving are disclosed. The method may include: performing facial key point detection on a driven character in a first image to obtain a first facial key point sequence; performing the following processing for each second image of a plurality of second images obtained successively: performing facial key point detection on a driving character in the second image to obtain a second facial key point sequence; obtaining a difference between the second facial key point sequence and an expressionless key point sequence which has been determined previously according to an analysis on the second facial key point sequence for a previous second image, and performing expression drive rendering on the driven character based on the difference and the first facial key point sequence. The technical solution may enhance flexibility, interactivity, accuracy etc.

Abstract: An image fusion method for removing ghost artifacts is provided. The method includes: determining a first fusion weight of a reference pixel in a reference frame, wherein the coordinates of the reference pixel are the same as the coordinates of one of input pixels included in an input frame; determining a reference brightness parameter according to values of all channels of the reference pixel; determining an input brightness parameter according to values of all channels of the input pixel; determining a ghost weight according to an amount that the brightness parameter ratio of the input brightness parameter and the reference brightness parameter deviates from a reasonable range; determining a fusion weight according to the first fusion weight and the ghost weight; and fusing the reference pixel with the input pixel according to the fusion weight to generate a fused pixel in a fused frame.

Abstract: Provided are a camera and an image processing method of the camera. According to an aspect of the present disclosure, an image processing method of a camera includes receiving region information; receiving image data extracted from a corresponding region of an original resolution image corresponding to a region set according to the region information regarding an input image; and analyzing image data of the original resolution image and detecting an object corresponding to a set condition.

Abstract: Embodiments of this application disclose an image fusion method performed by a computing device. The method includes the following steps: obtaining source face image data of a current to-be-fused image and resource configuration information of a current to-be-fused resource, performing image recognition processing on the source face image data, to obtain source face feature points corresponding to the source face image data, and generating a source face three-dimensional grid of the source face image data according to the source face feature points, performing grid fusion by using a resource face three-dimensional grid and the source face three-dimensional grid to generate a target face three-dimensional grid, and performing face complexion fusion by using source complexion data of the source face image data and resource complexion data of resource face image data on the target face three-dimensional grid, to generate fused target face image data.

Abstract: A facial expression synthesis method is provided. The method includes obtaining a to-be-processed facial image of a target object, and processing the to-be-processed facial image by using a face-recognition operation, to obtain skin color information of the to-be-processed facial image; screening out a target expression-material image, from a plurality of expression-material images in an expression-material image library, matching the skin color information; extracting a region image corresponding to a target synthesis region in the target expression-material image; and performing Poisson fusion processing on the region image and the to-be-processed facial image to fuse the region image with the to-be-processed facial image, so as to obtain a target facial image of the target object.

Abstract: Provided is an image restoration apparatus and method. The image restoration apparatus may store an image restoration model including a convolutional layer corresponding to kernels having various dilation gaps, and may restore an output image from a target image obtained by rearranging a compound eye vision (CEV) image by the image restoration model.

Abstract: A device control apparatus includes an imaging unit configured to capture an image of an occupant in a vehicle, a first recognition unit configured to recognize a posture of the occupant based on the image captured by the imaging unit, a second recognition unit configured to recognize a state of a hand including at least a shape of the hand of the occupant based on the image captured by the imaging unit, a discrimination processing unit configured to specify a device to be controlled and an operation to be executed based on the posture of the occupant recognized by the first recognition unit and the state of the hand recognized by the second recognition unit, and a controller configured to issue a control command corresponding to the specified device to be controlled and the specified operation to be executed.

Abstract: The present disclosure provides a method and a device for adaptively controlling a multimedia blackboard, a medium, and an electronic apparatus. In the present disclosure, a three-dimensional model of a target space is established, and a distribution area of the students in a classroom may be obtained by an adaptive algorithm based on the three-dimensional model and an angle of the multimedia blackboard may be automatically controlled to ensure that the students can watch the multimedia blackboard better and reduce the fatigue feeling about the class, which helps in improving an efficiency of having the class.

Abstract: The present disclosure provides an obstacle type recognizing method and apparatus, a device and a storage medium, wherein the method comprises: obtaining 3D point cloud data corresponding to a to-be-recognized obstacle; mapping the 3D point cloud data and its dimension data to a four-dimensional array; recognizing a type of the obstacle through a deep learning algorithm based on the four-dimensional array. The solution of the present disclosure can be applied to determine the type of the obstacle such as a person, a bicycle or a motor vehicle; and recognize a small-sized vehicle, a medium-sized vehicle and a large-sized vehicle; and improve the accuracy of a recognition result.

Abstract: The present disclosure relates to a method and a system for standardizing a hemodynamics measurement result and a non-transitory computer-readable recording medium. According to one aspect of the present disclosure, provided is a method for standardizing a measurement result obtained from a device for monitoring hemodynamics, the method comprising the steps of: capturing an image of a subject wearing a monitoring device; defining a photogrammetric coordinate system on the captured image, and converting a preset local coordinate system on the monitoring device into the photogrammetric coordinate system; and converting the photogrammetric coordinate system into a standard coordinate system which is based on a standard space.

Abstract: An image processor includes an accepting unit that accepts designation of at least part of a three dimensional microscope image data, and an image generator that generates three dimensional magnified image data based on the designation. In the image processor, the image generator may sequentially output a first magnified image based on at least part of data of the three dimensional magnified image data, and a second magnified image based on the at least part of data of the three dimensional magnified image data which has at least part of data different from the first magnified image.

Abstract: Techniques for compacting an ML model by replacing a linear transformation layer and a convolutional layer with a modified convolution layer. Determining the modified convolutional layer may include determining a modified bias and/or a modified filter. In some examples, before merging the layers, an output of the linear transformation layer may be provided as input to the convolution layer (e.g., the linear transformation layer may precede the convolutional layer). The linear transformation lay may include, for example, a batch normalization layer, a pooling layer, and/or the like.

Abstract: Object localization based on spatial relationships can be performed by obtaining a plurality of 3D coordinates within a 3D space, generating a feature vector for each coordinate based on quantified spatial relationships between the corresponding coordinate and one or more other coordinates among the plurality of coordinates, and applying a regression process to the feature vectors to produce a locating function for relating quantified spatial relationships among the plurality of coordinates and a location within the 3D space.

Abstract: In one embodiment, a method includes receiving a machine-learning model trained to detect a specified motion using multiple videos, wherein each video has at least one frame labeled as a moment of perception of the specified motion, identifying an object-of-interest depicted in an input video, detecting a motion of the object-of-interest, determining that the detected motion is the specified motion, and classifying one of the frames of the input video as the moment of perception of the specified motion.

Abstract: Frame packing techniques are disclosed for multi-directional images and video. According to an embodiment, a multi-directional source image is reformatted into a format in which image data from opposing fields of view are represented in respective regions of the packed image as flat image content. Image data from a multi-directional field of view of the source image between the opposing fields of view are represented in another region of the packed image as equirectangular image content. It is expected that use of the formatted frame will lead to coding efficiencies when the formatted image is processed by predictive video coding techniques and the like.

Abstract: Embodiments herein describe a framework for classifying images. In some embodiments, it is determined whether an image includes synthetic image content. If it does, characteristics of the image are analyzed to determine if the image includes characteristics particular to panoramic images (e.g., possess a threshold equivalency of pixel values among the top and/or bottom boundaries of the image, or a difference between summed pixel values of the pixels comprising the right vertical boundary of the image and summed pixel values of the pixels comprising the left vertical boundary of the image being less than or equal to a threshold value). If the image includes characteristics particular to panoramic images, the image is classified as a synthetic panoramic image. If the image is determined to not include synthetic image content, a neural network is applied to the image and the image is classified as one of non-synthetic panoramic or non-synthetic non-panoramic.