-
公开(公告)号：US20220058427A1
公开(公告)日：2022-02-24
申请号：US17298380
申请日：2019-11-26
发明人： Ziluan Liu , Shuailin Lv , Yunchao Zhang , Chao Qin , Yao Sun
摘要： An image parsing method includes obtaining feature information of an initial image, parsing first feature information in the feature information using a first channel to obtain a first prediction result, parsing second feature information in the feature information using a second channel to obtain a second prediction result, where a size of the first feature information meets a first size range, a size of the second feature information meets a second size range, and the first size range is less than the second size range, and outputting the first prediction result and the second prediction result as a parsing result of the initial image.
-
公开(公告)号：US20200051226A1
公开(公告)日：2020-02-13
申请号：US16483950
申请日：2017-02-06
发明人： Yahui Wang , Xin Chen , Yunchao Zhang
摘要： A method includes photographing a first image, where the first image comprises a document. A first area of the document is obscured by a first obstruction. The method further includes determining a location of the first area based on depth data. The method further includes photographing a second image. The method further includes restoring the obstructed information in the first area based on the second image. The method further includes displaying a third image, wherein the third image comprises the document and the first obstruction is removed from the first area of the document.
-
公开(公告)号：US20190355104A1
公开(公告)日：2019-11-21
申请号：US16338364
申请日：2016-09-29
发明人： Yunchao Zhang , Wenmei Gao
摘要： Embodiments of the present invention relate to the field of image processing, and provide an image correction method and apparatus, to implement image correction with short time and light load, and improve real-time performance of image sequence correction. A solution provided in the embodiments of the present invention includes: capturing an ith frame of image, where i is a positive integer greater than or equal to 1; tracking a quadrilateral area of an initial frame of image in the ith frame of image by using an optical flow constraint equation, to obtain a quadrilateral area of the ith frame of image; and correcting the ith frame of image based on the quadrilateral area of the ith frame of image. The present invention is applied to image correction.
-
公开(公告)号：US11158057B2
公开(公告)日：2021-10-26
申请号：US16473678
申请日：2016-12-30
发明人： Yunchao Zhang , Wenmei Gao
摘要： A method for detecting a document edge is provided. The method includes: obtaining multi-color channel data of each pixel in a color image (103), where the multi-color channel data includes two-dimensional coordinate values of the pixel and a value of the pixel on each color channel; performing line detection on the multi-color channel data of each pixel in the color image (105); and detecting a quadrilateral based on preset condition and some or all of straight lines obtained by performing the line detection (107). According to the foregoing method, a success rate of detecting a document edge can be increased.
-
公开(公告)号：US11074679B2
公开(公告)日：2021-07-27
申请号：US16483950
申请日：2017-02-06
发明人： Yahui Wang , Xin Chen , Yunchao Zhang
IPC分类号： G06T5/50 , G06T7/50 , G06T7/13 , H04N5/232 , H04N1/387 , G06T7/543 , G06T5/00 , G06K9/72 , G06K9/00 , G06T3/60
摘要： A method includes photographing a first image, where the first image comprises a document. A first area of the document is obscured by a first obstruction. The method further includes determining a location of the first area based on depth data. The method further includes photographing a second image. The method further includes restoring the obstructed information in the first area based on the second image. The method further includes displaying a third image, wherein the third image comprises the document and the first obstruction s removed from the first area of the document.
-
公开(公告)号：US12003850B2
公开(公告)日：2024-06-04
申请号：US17427433
申请日：2019-01-31
发明人： Shuailin Lv , Yunchao Zhang , Hongyu Li , Zhiping Jia
CPC分类号： H04N23/64 , G06T7/0002 , H04N5/772
摘要： A method for selecting an image based on burst shooting is provided, which relates to the field of terminal technologies. The method includes: an electronic device displays a preview interface; detects a first operation used to start burst shooting; obtains N images; then performs scene recognition based on K images that meet an image quality screening condition, to determine a shooting scene; and finally determines M images based on the shooting scene, where N is greater than or equal to K, N is greater than or equal to M, N and K are positive integers greater than 1, and M is a positive integer greater than or equal to 1. This technical solution helps improve quality of an image obtained by the electronic device through screening, thereby improving user satisfaction with an image that is automatically obtained through screening during burst shooting by the electronic device.
-
公开(公告)号：US20240171826A1
公开(公告)日：2024-05-23
申请号：US18552736
申请日：2022-03-30
发明人： Shuailin Lv , Feiran Sun , Dajun Ding , Weixiang Hu , Yunchao Zhang
IPC分类号： H04N21/485 , G06F3/16 , H04N21/422
CPC分类号： H04N21/4852 , G06F3/165 , H04N21/42203
摘要： Embodiments of this application provide a volume adjustment method and an electronic device. The volume adjustment method includes: receiving target volume used when a media playing device plays content; obtaining an audio signal, where the audio signal includes a first signal and a second signal, the first signal is a sound signal that is collected by a wearable device worn by a user and that is generated when the media playing device plays the content, and the second signal is a noise signal collected by the wearable device; determining adjusted volume based on the audio signal and the target volume; and sending the adjusted volume to a target device through a communication connection to the target device, where the adjusted volume is used to update volume used when the media playing device plays the content.
-
公开(公告)号：US11704771B2
公开(公告)日：2023-07-18
申请号：US16759870
申请日：2017-12-01
发明人： Yunchao Zhang , Shuai Chen , Zhiping Jia , Lei Miao
CPC分类号： G06T3/4053 , G06T3/4046 , H04N23/69
摘要： An image processing method and a device, where the image processing method is performed by a terminal having a digital zoom function, and the method includes determining a target zoom magnification based on a selection input of a user, collecting a to-be-processed image, and processing the to-be-processed image using a target super-resolution convolutional neural network model to obtain a processed image corresponding to the target zoom magnification, where the target super-resolution convolutional neural network model is obtained by training a super-resolution convolutional neural network model using a high-definition training image, a low-definition training image, and a mask image.
-
公开(公告)号：US11734953B2
公开(公告)日：2023-08-22
申请号：US17298380
申请日：2019-11-26
发明人： Ziluan Liu , Shuailin Lv , Yunchao Zhang , Chao Qin , Yao Sun
IPC分类号： G06V40/16 , G06V10/44 , G06V10/764 , G06V10/80 , G06V10/82 , G06T3/00 , G06T3/40 , G06F18/25
CPC分类号： G06V40/168 , G06F18/253 , G06T3/0006 , G06T3/40 , G06V10/454 , G06V10/764 , G06V10/809 , G06V10/82 , G06V40/171 , G06T2207/30201
摘要： An image parsing method includes obtaining feature information of an initial image, parsing first feature information in the feature information using a first channel to obtain a first prediction result, parsing second feature information in the feature information using a second channel to obtain a second prediction result, where a size of the first feature information meets a first size range, a size of the second feature information meets a second size range, and the first size range is less than the second size range, and outputting the first prediction result and the second prediction result as a parsing result of the initial image.
-
10.发明授权公开(公告)号：US11503208B2
公开(公告)日：2022-11-15
申请号：US17041696
申请日：2018-03-26
发明人： Lei Song , Xin Guo , Xiaomeng Chen , Yunchao Zhang , Xin Chen
IPC分类号： H04N5/232
摘要： An intelligent assistant control method is provided: starting, by a terminal device, a lens; displaying, by the terminal device, a preview interface on a display screen, where the preview interface includes a to-be-photographed object; and if the terminal device determines that the preview interface has been stably displayed for preset duration, displaying, by the terminal device, first prompt information of a photographing mode in the preview interface, where the first prompt information is used to recommend a first photographing mode to a user, and the first photographing mode is determined by the terminal device based on scene information of the to-be-photographed object.
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.022 秒)
