Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

OCR model training method, system and device based on image expansion

A model training and image technology, applied in the field of image processing, can solve problems such as speeding up the development efficiency of different board requirements, and achieve the effect of reducing the difficulty of training

Inactive Publication Date: 2021-02-26
北京云从科技有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the above-mentioned defects, the present invention is proposed to solve or at least partly solve the technical problem of how to automatically generate a large number of OCR model training data training sets that meet the requirements based on a small number of samples, so as to quickly obtain a large number of simulation data samples and Accelerate the development efficiency of different board requirements

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
  • OCR model training method, system and device based on image expansion
  • OCR model training method, system and device based on image expansion
  • OCR model training method, system and device based on image expansion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] In order to facilitate the understanding of the invention, the present invention will be described more comprehensively and in detail below in conjunction with the accompanying drawings and embodiments, but those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention, and are not intended to Limit the protection scope of the present invention.

[0067] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of both. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor can...

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 belongs to the technical field of image processing, and particularly provides an OCR model training method, system and device based on image expansion. The objective of the invention isto solve the problems that an existing OCR model requires a large amount of customized images and the number of samples of a data training set of the images is large. To achieve the purpose, the method comprises the steps: setting parameters required by image expansion according to the type of an image sample, carrying out the background enhancement expansion and new field generation expansion onreal data corresponding to the parameters of each real image sample to obtain expansion data, and constructing a corresponding expansion image sample based on the expansion data; inputting the extended image sample into the OCR model for model training, so that the OCR model can be trained for character recognition only by a few sampling images.

Description

technical field [0001] The present invention relates to the technical field of image processing in computer vision, in particular to an image expansion-based OCR model training method, system and device. Background technique [0002] OCR (Optical Character Recognition, Optical Character Recognition) is an important application field in computer vision. Due to its characteristics of supervised network, it needs a large amount of training data support to obtain a good model and its recognition effect. Therefore, in the field of OCR, a huge data training set containing various scenes is crucial to obtain a good OCR model. [0003] However, the scenarios contained in the same layout are complex and diverse, and due to various reasons such as confidentiality of the training data, it is impossible to obtain a large enough amount of training data, that is, it is impossible to obtain many samples, and in many cases there are only a few pieces of training data for reference. Due to ...

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): G06K9/62G06K9/34G06T5/00
CPCG06V30/153G06F18/214G06T5/70
Inventor 马明宇
Owner 北京云从科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com