公开(公告)号：US20210049350A1

公开(公告)日：2021-02-18

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：US20200334819A1

公开(公告)日：2020-10-22

申请号：US16651946

申请日：2019-09-19

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Guannan CHEN ,  Lijie ZHANG

IPC: G06T7/10 ,  G06K9/46 ,  G06N3/02

Abstract: The present disclosure provides an image segmentation apparatus, method and relevant computing device. The image segmentation apparatus comprises: a feature extractor configured to extract N image semantic features having different scales from an input image, where N is an integer not less than 3; and a feature processor comprising cascaded dense-refine networks and being configured to perform feature processing on the N image semantic features to obtain a binarized mask image for the input image. A dense-refine network is configured to generate a low-frequency semantic feature from semantic features input thereto by performing densely-connected convolution processing on the semantic features respectively to obtain respective image global features, performing feature fusion on the image global features to obtain a fused image global feature, and performing pooling processing on the fused image global feature to generate and output the low-frequency semantic feature. The semantic features are selected from a group consisting of the N image sematic features and low-frequency semantic features generated by dense-refine networks. The feature processor is configured to obtain the binarized mask image based on low-frequency semantic features generated by the dense-refine networks.

公开(公告)号：US20190005619A1

公开(公告)日：2019-01-03

申请号：US15741781

申请日：2017-06-23

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Pablo Navarrete Michelini ,  Lijie ZHANG ,  Xiaoyu LI

IPC: G06T3/40

Abstract: An image upscaling system includes at least two convolutional neural network modules and at least one synthesizer. The convolutional neural network module and the synthesizer are alternately connected to one another. The first convolutional neural network module receive an input image and the corresponding supplemental image, generate a first number of the feature images, and output them to the next synthesizer connected thereto. Other convolutional neural network modules each may receive the output image from the previous synthesizer and the corresponding supplemental image, generate a second number of feature images, and output them to the next synthesizer connected thereto, or output them from the image upscaling system. The synthesizer may synthesize every n*n feature images in the received feature image into one feature image and output the resultant third number of feature images to the next convolutional neural network module connected thereto or output them from the image upscaling system.

公开(公告)号：US20170065158A1

公开(公告)日：2017-03-09

申请号：US15159132

申请日：2016-05-19

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Zhenglong LI ,  Lijie ZHANG

IPC: A61B1/04 ,  A61B1/06 ,  A61B1/00 ,  A61B1/273

CPC classification number: A61B1/041 ,  A61B1/00004 ,  A61B1/00016 ,  A61B1/00032 ,  A61B1/00071 ,  A61B1/0011 ,  A61B1/06 ,  A61B1/126 ,  A61B1/2736 ,  G02B1/18 ,  G02B23/2484

Abstract: The present invention discloses an endoscope and a method of manufacturing the endoscope, and a medical detection system. The endoscope includes a housing; and a transparent cover structure, which includes a seal cover and at least one dissolution layer, the at least one dissolution layer wrapping around an outer surface of the seal cover, and the dissolution layer including a soluble material that can dissolve in digestive juices, wherein the housing and the transparent cover structure are connected in a sealed manner to form a sealed space, and the sealed space is provided therein with: an optical lens, which is provided in a region of the sealed space close to the transparent cover structure; a light source, which is provided in a region around the optical lens; and an image sensor, which is provided to correspond with the optical lens.

Abstract translation: 本发明公开了一种内窥镜和内窥镜的制造方法以及医疗检测系统。 内窥镜包括壳体; 以及透明盖结构，其包括密封盖和至少一个溶解层，所述至少一个溶解层围绕所述密封盖的外表面缠绕，并且所述溶解层包括可溶解在消化液中的可溶性材料，其中 所述壳体和所述透明盖结构以密封方式连接以形成密封空间，并且所述密封空间设置有：光学透镜，设置在靠近所述透明盖结构的所述密封空间的区域中; 光源，其设置在光学透镜周围的区域中; 以及被提供以对应于光学透镜的图像传感器。

公开(公告)号：US20160358318A1

公开(公告)日：2016-12-08

申请号：US14891943

申请日：2015-05-18

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Lijie ZHANG ,  Naifu WU

IPC: G06T5/00 ,  G06T7/00 ,  G06K9/00 ,  G06K9/62 ,  H04N7/14 ,  H04N7/15

CPC classification number: G06T5/006 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00288 ,  G06K9/0061 ,  G06K9/036 ,  G06K9/6202 ,  G06K9/6277 ,  G06T2207/30201 ,  H04N7/144 ,  H04N7/147 ,  H04N7/15

Abstract: The present invention provides an image correction method, an image correction apparatus and a video system. The image correction method comprises: obtaining an actual face image; obtaining a target sample image matching with the actual face image; and correcting each eye area of the actual face image according to the target sample image such that orientation of each eye area of the corrected actual face image coincides with orientation of a corresponding eye area of the target sample image. The present invention may enable pupil portions of eye areas in a received face image to look toward a camera, thereby realizing an equal communication and improving sensory experience.

Abstract translation: 本发明提供一种图像校正方法，图像校正装置和视频系统。 图像校正方法包括：获得实际面部图像; 获得与实际面部图像匹配的目标样本图像; 并且根据目标样本图像校正实际面部图像的每个眼睛区域，使得校正的实际脸部图像的每个眼睛区域的取向与目标样本图像的相应眼睛区域的方向一致。 本发明可以使接收到的脸部图像中的眼睛区域的瞳孔部分朝向照相机观看，从而实现相等的通信和改善感觉体验。

公开(公告)号：US20160253978A1

公开(公告)日：2016-09-01

申请号：US14761753

申请日：2014-09-30

Applicant: BOE TECHNOLOGY GROUP CO., LTD. ,  K-TRONICS (SU ZHOU) TECHNOLOGY CO., LTD.

Inventor： Shuhuan YU ,  Xiao ZHANG ,  Lijie ZHANG ,  Xitong MA ,  Peng CHENG

IPC: G09G5/00

CPC classification number: G09G5/006 ,  G09G3/006 ,  G09G3/2092 ,  G09G2300/0426 ,  G09G2360/06 ,  G09G2370/12

Abstract: There is provided an IC board and a display apparatus. Switching components (01; 02) are added between the internal interfaces (J1, J2 . . . Jn; j1, j2 . . . jn) corresponding to the backend data processing chips (U2; U3) and the frontend data processing chip (U1), or a switching component (02) is added between the internal interfaces (j 1, j2 . . . jn) corresponding to the backend data processing chip (U2) and another backend data processing chip (U3). The switching components (01; 02) can ensure normal signal transmission between the backend data processing chips (U2; U3) and the frontend data processing chip (U1) or between the backend data processing chips (U2; U2) when no external test signal is input into the internal interfaces, i.e., when the IC board operates normally; and interrupt the signal transmission between the backend data processing chips (U2; U3) and the frontend data processing chip (U1) or between the backend data processing chips (U2; U3) when the internal interfaces j1, j2 . . . jn are input with an external test signal such that the impedance of the signal transmission path in the backend data processing chips (U2; U3) during the external testing remains consistent to avoid abnormal transmission of the external test signals and the signals during normal operation.

Abstract translation: 提供了IC板和显示装置。 在与后端数据处理芯片（U2; U3）和前端数据处理芯片（U1）对应的内部接口（J1，J2 ... Jn; j1，j2 ... jn）之间添加切换部件（01; 02） ）或相应于后端数据处理芯片（U2）和另一后端数据处理芯片（U3）的内部接口（j 1，j2 ... jn）之间添加切换部件（02）。 当没有外部测试信号（01; 02）时，开关组件（01; 02）可以确保后端数据处理芯片（U2; U3）和前端数据处理芯片（U1）之间或后端数据处理芯片（U2; U2）之间的正常信号传输 输入到内部接口，即当IC板正常工作时; 并在内部接口j1，j2之间中断后端数据处理芯片（U2; U3）和前端数据处理芯片（U1）之间或后端数据处理芯片（U2; U3）之间的信号传输。 。 。 jn与外部测试信号一起输入，使得在外部测试期间后端数据处理芯片（U2; U3）中的信号传输路径的阻抗保持一致，以避免在正常操作期间外部测试信号和信号的异常传输。

公开(公告)号：US20230171435A1

公开(公告)日：2023-06-01

申请号：US17615156

申请日：2021-01-20

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Lijie ZHANG ,  Guannan CHEN

IPC: H04N19/80 ,  H04N19/117 ,  H04N19/172 ,  H04N19/139 ,  H04N19/52 ,  H04N19/105 ,  H04N19/436

CPC classification number: H04N19/80 ,  H04N19/117 ,  H04N19/172 ,  H04N19/139 ,  H04N19/52 ,  H04N19/105 ,  H04N19/436

Abstract: The present disclosure relates to the field of image processing technology, and in particular, to image encoding, decoding methods and devices, an encoder-decoder. The method includes: acquiring a visual saliency heat map of an image of a current frame, and filtering, by using the visual saliency heat map of the image of the current frame, the image of the current frame to obtain a target image; acquiring, by using the target image and an input image of a next frame, a motion estimation vector and a target prediction image of the input image of the next frame; and encoding a difference image between the input image of the next frame and the target prediction image and the motion estimation vector.

公开(公告)号：US20230147596A1

公开(公告)日：2023-05-11

申请号：US17434381

申请日：2021-02-09

Applicant: BOE Technology Group Co., Ltd.

Inventor： Yanhong WU ,  Lijie ZHANG

IPC: G06T11/00 ,  G06T5/20 ,  G06T7/90

CPC classification number: G06T11/001 ,  G06T5/20 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2210/62

Abstract: Embodiments of the present disclosure provide a method and apparatus for filtering image colors, an electronic device and a storage medium. The method includes: acquiring an image to be filtered, wherein a pixel point in the image to be filtered is represented by a hue value, a saturation value and a value; acquiring a retaining proportion of the pixel point in the image to be filtered, wherein a retaining proportion of any pixel point is used to indicate a degree of a saturation of the pixel point to be retained, and is positively correlated with a similarity between a hue of the pixel point and a hue to be retained of the pixel point; and acquiring a filtered image by adjusting the saturation value of the pixel point in the image to be filtered based on the retaining proportion of the pixel point in the image to be filtered.

公开(公告)号：US20220319233A1

公开(公告)日：2022-10-06

申请号：US17642781

申请日：2021-03-10

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Yanhong WU ,  Guannan CHEN ,  Pablo NAVARRETE MICHELINI ,  Lijie ZHANG

IPC: G06V40/16

Abstract: An expression recognition method is described that includes acquiring a face image to be recognized, and inputting the face image into N different recognition models arranged in sequence for expression recognition and outputting an actual expression recognition result, the N different recognition models being configured to recognize different target expression types, wherein N is an integer greater than 1.

公开(公告)号：US20220165053A1

公开(公告)日：2022-05-26

申请号：US17417127

申请日：2020-12-29

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Yanhong WU ,  Guannan CHEN ,  Lijie ZHANG

IPC: G06V10/82 ,  G06V10/77 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06N3/04

Abstract: The present disclosure provides an image classification method, apparatus, and device, and a readable storage medium. The image classification method includes: processing an image to be processed, by using a first convolutional network, to obtain a first feature map; processing the first feature map, by using a residual network, to obtain a second feature map, wherein the residual network includes a depth separable convolutional layer; and processing the second feature map, by using a second convolutional network, to determine a category label of the image to be processed.