公开(公告)号：US20210004629A1

公开(公告)日：2021-01-07

申请号：US16822085

申请日：2020-03-18

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Yipeng SUN ,  Chengquan ZHANG ,  Zuming HUANG ,  Jiaming LIU ,  Junyu HAN ,  Errui DING

IPC: G06K9/46 ,  G06K9/62 ,  G06K9/32

Abstract: The present disclosure proposes an end-to-end text recognition method and apparatus, computer device and readable medium. The method comprises: obtaining a to-be-recognized picture containing a text region; recognizing a position of the text region in the to-be-recognized picture and text content included in the text region with a pre-trained end-to-end text recognition model; the end-to-end text recognition model comprising a region of interest perspective transformation processing module for performing perspective transformation processing for the text region. The technical solution of the present disclosure does not need to serially arrange a plurality of steps, and may avoid introducing the accumulated errors and may effectively improve the accuracy of the text recognition.

公开(公告)号：US20210398335A1

公开(公告)日：2021-12-23

申请号：US17241398

申请日：2021-04-27

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Tianshu HU ,  Jiaming LIU ,  Shengyi HE ,  Zhibin HONG

IPC: G06T11/60 ,  G06T3/40 ,  G06T7/30 ,  G06T5/50

Abstract: A face editing method, an electronic device and a readable storage medium, which relate to the field of image processing and deep learning technologies, are disclosed. A face editing implementation in the present disclosure includes: acquiring a face image in an image to be processed; converting an attribute of the face image according to an editing attribute to generate an attribute image; segmenting semantically the attribute image, and then processing a semantic segmentation image according to the editing attribute to generate a mask image; and merging the attribute image with the image to be processed using the mask image to generate a result image.

公开(公告)号：US20210398334A1

公开(公告)日：2021-12-23

申请号：US17241211

申请日：2021-04-27

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Shengyi HE ,  Jiaming LIU ,  Tianshu HU ,  Zhibin HONG

IPC: G06T11/60 ,  G06T11/40 ,  G06T7/194 ,  G06T7/174 ,  G06N3/08 ,  G06N3/04

Abstract: A method for creating an image editing model, an electronic device and a computer-readable storage medium, which relates to the fields of image processing and deep learning technologies, are disclosed. According to an embodiments, the method for creating an image editing model includes: acquiring a training sample including a first image and a second image corresponding thereto; creating a generative adversarial network including a generator and a discriminator, and the generator includes a background image generation branch, a mask image generation branch and a foreground image generation branch; and training the generative adversarial network with the first image and the second image corresponding thereto, and taking the generator in the trained generative adversarial network as the image editing model.