Supercharge Your Innovation With Domain-Expert AI Agents!

Image generation method, model training method, related device and electronic equipment

An image generation and image technology, applied in the fields of artificial intelligence, computer vision and deep learning, can solve a large amount of training data and other problems, and achieve the effect of improving the recognition effect

Active Publication Date: 2021-03-30
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, to train a good text recognition model, a large amount of training data is required

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image generation method, model training method, related device and electronic equipment
  • Image generation method, model training method, related device and electronic equipment
  • Image generation method, model training method, related device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0058] like figure 1 As shown, the present application provides an image generation method, comprising the following steps:

[0059] Step S101: Acquire a first image and a second image, the first image includes a first text content, the second image includes a second text content, and the first text content is different from the second text content in style.

[0060] In this embodiment, the image generation method relates to the field of artificial intelligence, especially to the field of computer vision and deep learning technology, which can be widely used in many scenarios of text recognition such as document information, logistics information, and bill information.

[0061] In actual use, the image generating method in the embodiment of the present application may be executed by the image generating device in the embodiment of the present application. The image generating apparatus of the embodiment of the present application may be configured in any electronic device to ...

no. 2 example

[0091] like Figure 8 As shown, the present application provides a model training method, including the following steps:

[0092] Step S801: Acquire a first training image set, the first training image set includes a first training background image and a first training text image, and the first training text image includes a first training text content;

[0093] Step S802: Erase the first training text content in the first training text image based on the text erasing model to obtain a first target image;

[0094] Step S803: determining first difference information between the first target image and the first training background image;

[0095] Step S804: Update the parameters of the text erasure model based on the first difference information.

[0096] In this embodiment, the model training method is used to train the text erasing model.

[0097] In order to train the text erasing model well, usually the number of the first training data set can include multiple, and each ...

no. 3 example

[0116] like Figure 10 As shown, the present application provides a model training method, including the following steps:

[0117] Step S1001: Obtain a second training image set, the second training image set includes: a second training background image, a second training text image containing the second training text content, a third training text image containing the third training text content And a training output text image; the style pattern of the second training text content in the second training text image is different from the style style of the third training text content in the third training text image;

[0118] Step S1002: Based on the text style transfer model, transfer the third training text content in the third training text image to the second training background image in the second target style to obtain a second target image, the second The target style is the style of the second training text content;

[0119] Step S1003: Determine the second differenc...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an image generation method, a model training method, a related device and electronic equipment, and relates to the technical field of artificial intelligence such as computer vision and deep learning. The specific implementation scheme comprises the steps: acquiring a first image and a second image, wherein the first image comprises first text content, and the second imagecomprises second text content; erasing the first text content in the first image by adopting a text erasing model to obtain a background image of the first image; and based on the background image ofthe first image and the second image, migrating the second text content in the second image to the background image of the first image in a first target style by adopting a text style migration modelto obtain a third image, the first target style being the style of the first text content. According to the technology provided by the invention, the problem that the model training precision cannot be met due to less training data during text recognition model training in the OCR technology is solved, and the recognition effect of the text recognition model is improved.

Description

technical field [0001] This application relates to the field of artificial intelligence, in particular to the technical fields of computer vision and deep learning, and in particular to an image generation method, a model training method, related devices and electronic equipment. Background technique [0002] With the rapid development of society, people need to process more and more text information in production and life, such as certificate information, logistics information and bill information, etc. In order to reduce people's labor and improve processing efficiency, artificial intelligence technology is used to It has become a trend to realize the automatic recognition of text information. [0003] At present, Optical Character Recognition (OCR) technology is a key technology for recognizing text in images in the field of artificial intelligence. As an important step in OCR technology, text recognition directly determines people's recognition of Judgment of text infor...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/20G06K9/62G06N20/20
CPCG06N20/20G06V10/22G06F18/214Y02D10/00
Inventor 赵艳梅
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com