-
1.发明授权公开(公告)号：US11295115B2
公开(公告)日：2022-04-05
申请号：US16937175
申请日：2020-07-23
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Yanhong Wu , Guannan Chen , Lijie Zhang
IPC: G06K9/00
Abstract: The present disclosure discloses a method for generating a face image, an electronic device, and a non-transitory computer-readable storage medium, the method includes: receiving a first face image and target facial expression information, and determining first facial expression information corresponding to the first face image; selecting a first reference face image matched with the first facial expression information and a second reference face image matched with the target facial expression information from a face image library; respectively extracting feature points in the first reference face image and the second reference face image, and determining face deformation information between the first reference face image and the second reference face image based on the feature points; and extracting feature points in the first face image, and generating a second face image based on the face deformation information and the feature points in the first face image.
-
公开(公告)号：US11244151B2
公开(公告)日：2022-02-08
申请号：US16639934
申请日：2019-10-10
Applicant: BOE Technology Group Co., Ltd.
Inventor： Guannan Chen , Honghong Jia , Lijie Zhang
Abstract: A computer-implemented method of recognizing a facial expression of a subject in an input image is provided. The method includes filtering the input image to generate a plurality of filter response images; inputting the input image into a first neural network; processing the input image using the first neural network to generate a first prediction value; inputting the plurality of filter response images into a second neural network; processing the plurality of filter response images using the second neural network to generate a second prediction value; weighted averaging the first prediction value and the second prediction value to generate a weighted average prediction value; and generating an image classification result based on the weighted average prediction value.
-
公开(公告)号：US20210365710A1
公开(公告)日：2021-11-25
申请号：US16959786
申请日：2020-01-06
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Dan Zhu , Hanwen Liu , Pablo Navarrete Michelini , Lijie Zhang
Abstract: An image processing method is disclosed. The image processing method may include inputting a first image and a third image to a pre-trained style transfer network model, the third image being a composited image formed by the first image and a second image; extracting content features of the third image and style features of the second image, normalizing the content features of the third image based on the style features of the second image to obtain target image features, and generating a target image based on the target image features and outputting the target image by using the pre-trained style transfer network model.
-
公开(公告)号：US11069047B2
公开(公告)日：2021-07-20
申请号：US16447547
申请日：2019-06-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Hanwen Liu , Pablo Navarrete Michelini , Lijie Zhang , Dan Zhu
Abstract: An image processing method implemented by a computing device is described herein, which includes acquiring an image to be processed and a target style of image, the image to be processed being an image of a second resolution level, and inputting the image to be processed and the target style into a trained image processing neural network for image processing to obtain a target image of the target style, the target image being an image of a first resolution level. The resolution of the image of the first resolution level is higher than that of the image of the second resolution level.
-
公开(公告)号：US10134441B2
公开(公告)日：2018-11-20
申请号：US15122539
申请日：2016-01-29
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Zhenglong Li , Xuewen Lv , Lijie Zhang
IPC: G11B27/00 , H04N5/93 , H04N9/80 , G11B27/036 , H04N21/478 , H04N21/234 , H04N21/81 , H04N21/84 , H04N21/462
Abstract: The present invention provides a method and a system for overlaying an image in a video stream. The method comprising steps of: acquiring an image element signature including at least one image element from the video stream; determining whether the image element signature matches an image to be overlaid; and overlaying the image when the image element signature is determined to match the image to be overlaid.
-
Patent Agency Ranking
公开(公告)号：US10115180B2
公开(公告)日：2018-10-30
申请号：US15030588
申请日：2015-12-10
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Ran Duan , Lijie Zhang
Abstract: The present application discloses an image interpolation method for interpolating a pixel and enhancing an edge in an image, comprising detecting an edge position in an image; obtaining edge characteristics associated with the edge position; determining whether an interpolation point is located within an edge region based on the edge characteristics of an array of p×q pixels surrounding the interpolation point, wherein p and q are integers larger than 1; determining edge direction of an interpolation point located within the edge region, wherein the edge direction is normal to gradient direction; classifying the edge direction accordingly to in angle subclasses and n angle classes; wherein each angle class comprises one or more subclasses, m and n are integers, and n≤m; selecting a one-dimensional horizontal interpolation kernel based on the angle class; performing a horizontal interpolation using the selected one-dimensional horizontal interpolation kernel; and performing a vertical interpolation using a one-dimensional vertical interpolation kernel.
-
公开(公告)号：US20170357106A1
公开(公告)日：2017-12-14
申请号：US15519630
申请日：2016-10-26
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Lijie Zhang , Zhenglong Li , Xuewen Lv
Abstract: The present application discloses an apparatus for protecting a user's eye from blue light radiation, the apparatus includes a radiation detector configured to convert blue light from a light source into a photo voltage having a voltage value; a processor coupled to the radiation detector and configured to calculate a cumulative radiation intensity based on the voltage value cumulated over a time interval, and to compare the cumulative radiation intensity with a threshold value; and a controller coupled to the processor, configured to adjustably control blocking of at least a portion of blue light from the user's eye when the cumulative radiation intensity exceeds the threshold value.
-
8.发明申请公开(公告)号：US20160364840A1
公开(公告)日：2016-12-15
申请号：US14771340
申请日：2015-01-04
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Lijie Zhang
CPC classification number: G06T3/4007 , G06T3/40 , G06T3/4053 , G06T5/50 , G06T2207/10024 , G06T2207/20064 , G06T2207/20221 , H04N1/3876 , H04N1/6008
Abstract: Embodiments of the disclosure provide an image amplifying method, an image amplifying device, and a display apparatus, and relate to field of image processing technique, the method comprises: obtaining, by an image amplifying device, high-frequency and low-frequency components of a source image; performing, by the image amplifying device, pixel interpolation on the low-frequency components of the source image through a first interpolation algorithm, to obtain a low-frequency sub-image; performing, by the image amplifying device, pixel interpolation on the high-frequency components of the source image through a second interpolation algorithm, to obtain a high-frequency sub-image; and merging, by the image amplifying device, the low-frequency and high-frequency sub-images, to obtain a merged image; wherein the first interpolation algorithm and the second interpolation algorithm adopt different algorithms, so that it can ensure image quality of the amplified image while reducing the operation amount. Embodiments of the disclosure are applied to image amplification.
Abstract translation: 本发明的实施例提供一种图像放大方法，图像放大装置和显示装置，涉及图像处理技术领域，该方法包括：通过图像放大装置获得高频和低频分量的高频和低频分量 源图像; 通过图像放大装置通过第一插值算法对源图像的低频分量进行像素插值，以获得低频子图像; 通过图像放大装置通过第二插值算法对源图像的高频分量进行像素插值，以获得高频子图像; 并通过图像放大装置合并低频和高频子图像，以获得合并图像; 其中第一插值算法和第二插值算法采用不同的算法，从而可以在减少操作量的同时确保放大图像的图像质量。 本公开的实施例应用于图像放大。
-
公开(公告)号：US09425810B2
公开(公告)日：2016-08-23
申请号：US14361405
申请日：2013-12-20
Inventor： Xitong Ma , Xiao Zhang , Shuhuan Yu , Lijie Zhang
CPC classification number: H03L7/18 , H03L7/0992 , H03L7/183 , H03L7/193
Abstract: A frequency signal generating system comprises a digital phase-locked loop for receiving a source frequency signal; a loop filter for filtering out high frequency components of a signal output from the digital phase-locked loop; and a voltage controlled oscillator for outputting a target frequency signal according to a signal from the loop filter, wherein an output terminal of the voltage controlled oscillator is connected to a first output terminal of the digital phase-locked loop so that the target frequency signal output from the voltage controlled oscillator is fed back to the digital phase-locked loop, the digital phase-locked loop performs frequency-dividing and phase-detecting on the source frequency signal and the fed back target frequency signal so that the target frequency signal output from the voltage controlled oscillator and the source frequency signal satisfy a definite mathematical relationship therebetween.
Abstract translation: 频率信号发生系统包括用于接收源频率信号的数字锁相环; 用于滤除从数字锁相环输出的信号的高频分量的环路滤波器; 以及压控振荡器，用于根据来自环路滤波器的信号输出目标频率信号，其中压控振荡器的输出端连接到数字锁相环的第一输出端，使得目标频率信号输出 从压控振荡器反馈到数字锁相环，数字锁相环对源极频率信号和反馈目标频率信号进行分频和相位检测，使得目标频率信号从 压控振荡器和源极频率信号之间具有确定的数学关系。
-
公开(公告)号：US12125182B2
公开(公告)日：2024-10-22
申请号：US17754192
申请日：2021-04-27
Applicant: BOE Technology Group Co., Ltd.
Inventor： Guannan Chen , Dan Zhu , Lijie Zhang
CPC classification number: G06T5/90 , G06T7/90 , G06T9/00 , G06V10/44 , G06V10/56 , H04N1/6019 , G06T2207/10024 , G06T2207/20081 , G06T2207/20208
Abstract: The present disclosure provides an image processing method and an image processing apparatus. The image processing method includes: obtaining a to-be-converted SDR image; using a first convolutional network to perform feature analysis on the SDR image, to obtain N weights of the SDR image; where the N weights are respectively configured to characterize proportions of color information of the SDR image to color information characterized in preset N 3D lookup tables, the N 3D lookup tables are configured to characterize color information of different types; obtaining a first 3D lookup table for the SDR image according to the N weights and the N 3D lookup tables; using the first 3D lookup table to adjust the color information of the SDR image to obtain an HDR image; and using a second convolutional neural network to perform refinement correction on the HDR image to obtain an output image.
-
-
-
-
-
-
-
-
-
Search Results
75
records
(took 0.031 seconds)
