-
公开(公告)号:US11620496B2
公开(公告)日:2023-04-04
申请号:US16069376
申请日:2017-11-17
摘要: A convolutional neural network, and a processing method, a processing device, a processing system and a medium for the same. The method includes: using an activation recorder layer as an activation function layer in the convolutional neural network, wherein in response to that a probe image with contents is inputted to the convolutional neural network, the activation recorder layer performs an activation operation the same as the activation function layer does and records an activation result of the activation operation; modifying the convolutional neural network, wherein step of modifying includes replacing the activation recorder layer with a hidden layer that uses the recorded activation result; and inputting an analysis image to the modified convolutional neural network as an input image, so as to output an output image of the modified convolutional neural network, thereby analyzing a forward effect or a backward effect between the input image and the output image, the analysis image being a pixel-level binary image.
-
公开(公告)号:US11216913B2
公开(公告)日:2022-01-04
申请号:US16855063
申请日:2020-04-22
发明人: Hanwen Liu , Pablo Navarrete Michelini , Dan Zhu , Lijie Zhang
摘要: The present disclosure discloses a convolutional neural network processor, an image processing method and an electronic device. The method includes: receiving, by the first convolutional unit, the input image to be processed, extracting the N feature maps with different scales in the image to be processed, sending the N feature maps to the second convolutional unit, and sending the first feature map to the processing unit; fusing, by the processing unit, the received preset noise information and the first feature map, to obtain the second feature map, and sending the second feature map to the second convolutional unit; and fusing, by the second convolutional unit, the received N feature maps with the second feature map to obtain the processed image.
-
公开(公告)号:US11216910B2
公开(公告)日:2022-01-04
申请号:US16073712
申请日:2017-12-19
摘要: An image processing system, an image processing method and a display device are provided. The image processing system includes at least one resolution conversion sub-system. The resolution conversion sub-system includes a CNN module, a combiner and an activation module connected in a cascaded manner. The CNN module is configured to perform convolution operation on an input signal to acquire a plurality of first feature images having a first resolution. The combiner is configured to combine the first feature images into a second feature image having a second resolution greater than the first resolution. The activation module is connected to the combiner and configured to perform a selection operation on the second feature image using an activation function.
-
公开(公告)号:US11138466B2
公开(公告)日:2021-10-05
申请号:US16338830
申请日:2018-08-20
摘要: An image processing method includes: obtaining an input image; performing image conversion processing on the input image by using a generative neural network; and outputting an output image that has been subjected to image conversion processing. The input image has N channels, N being a positive integer greater than or equal to 1; input of the generative neural network includes a noise image channel and N channels of the input image; output of the generative neural network is an output image including N channels.
-
公开(公告)号:US20210233214A1
公开(公告)日:2021-07-29
申请号:US16755044
申请日:2019-08-19
发明人: Hanwen Liu , Pablo Navarrete Michelini , Dan Zhu , Lijie Zhang
摘要: A neural network is provided. The neural network includes 2n number of sampling units sequentially connected; and a plurality of processing units. A respective one of the plurality of processing units is between two adjacent sampling units of the 2n number of sampling units. A first sampling unit to an n-th sample unit of the 2n number of sampling units are DeMux units. A respective one of the DeMux units is configured to rearrange pixels in a respective input image to the respective one of the DeMux units following a first scrambling rule to obtain a respective rearranged image. An (n+1)-th sample unit to a (2n)-th sample unit of the 2n number of sampling units are Mux units. A respective one of the Mux units is configured to combine respective m′ number of input images to the respective one of the Mux units to obtain a respective combined image.
-
公开(公告)号:US20180211371A1
公开(公告)日:2018-07-26
申请号:US15717225
申请日:2017-09-27
CPC分类号: G06T5/40 , G06T5/50 , G06T2207/10016 , G06T2207/20182 , H04N5/21 , H04N9/646
摘要: The disclosure discloses an apparatus and method for correcting a flicker in a video, and a video device, the method including: determining a correction weight for correcting grayscale values of a current frame of video image according to a ratio of a variance of a histogram of mapped grayscale values of a last frame of video image to a variance of a histogram of grayscale values of the last frame of video image, and a contrast enhancement upper limit parameter input by a user, and/or a largest percentage of the number of pixels with a same grayscale among a total number of pixels in the histogram of the grayscale values of the last frame of video image, and the contrast enhancement upper limit parameter input by the user; and, determining resulting grayscale values of the current frame of video image according to the correction weight.
-
7.
公开(公告)号:US11587343B2
公开(公告)日:2023-02-21
申请号:US17044275
申请日:2020-04-20
发明人: Lijie Zhang , Guannan Chen , Hanwen Liu , Dan Zhu
IPC分类号: G06V30/244 , G06F40/109 , G06V30/32 , G06V30/28
摘要: A method and a system for converting a font of a Chinese character in an image, a computer device and a medium are disclosed. A specific implementation of the method includes: acquiring a stroke of a to-be-converted Chinese character in the image and spatial distribution information of the stroke; and generating a Chinese character in a target font that corresponds to the to-be-converted Chinese character in the image according to the stroke of the to-be-converted Chinese character, the spatial distribution information of the stroke and standard stroke information of the target font, to replace the to-be-converted Chinese character.
-
公开(公告)号:US11461639B2
公开(公告)日:2022-10-04
申请号:US16336995
申请日:2018-08-16
摘要: A training method of a neural network for implementing image style transfer, an image processing method and an image processing device are disclosed. The training method includes: acquiring a first training input image and a second training input image; performing a style transfer process on the first training input image by the neural network to obtain a training output image; based on the first training input image, the second training input image and the training output image, calculating a loss value of parameters of the neural network through a loss function; and modifying the parameters of the neural network according to the loss value, where the loss function satisfies a predetermined condition, obtaining a trained neural network, where the loss function doesn't satisfy the predetermined condition, continuing to repeatedly perform above training process, the loss function including a weight-bias-ratio loss function.
-
公开(公告)号:US20210334642A1
公开(公告)日:2021-10-28
申请号:US16604410
申请日:2019-04-23
发明人: Pablo Navarrete Michelini , Dan Zhu , Hanwen Liu
摘要: The present disclosure generally relates to the field of deep learning technologies. An apparatus for generating a plurality of correlation images may include a feature extracting unit configured to receive a training image and extracting at least one or more of feature from the training image to generate a first feature image based on the training image; a normalizer configured to normalize the first feature image and generate a second feature image; and a shift correlating unit configured to perform a plurality of translational shifts on the second feature image to generate a plurality of shifted images, correlate each of the plurality of shifted images with the second feature image to generate the plurality of correlation images.
-
公开(公告)号:US20210097645A1
公开(公告)日:2021-04-01
申请号:US16465294
申请日:2018-12-17
发明人: Pablo Navarrete Michelini , Dan Zhu , Hanwen Liu
摘要: The present disclosure relates to an image processing method. The image processing method may include upscaling a feature image of an input image by an upscaling convolutional network to obtain a upscaled feature image; downscaling the upscaled feature image by a downscaling convolutional network to obtain a downscaled feature image; determining a residual image between the downscaled feature image and the feature image of the input image; upscaling the residual image between the downscaled feature image and the feature image of the input image to obtain an upscaled residual image; correcting the upscaled feature image using the upscaled residual image to obtain a corrected upscaled feature image; and generating a first super-resolution image based on the input image using the corrected upscaled feature image.
-
-
-
-
-
-
-
-
-