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

Handwritten content electronization method and device, electronic equipment and storage medium

An electronic and content technology, applied in the field of artificial intelligence, can solve problems such as inability to guarantee accuracy, inability to copy and modify text, unclear source of scanned pictures, etc., to achieve the effect of improving transcription efficiency and saving labor costs

Inactive Publication Date: 2021-01-22
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing scanning technology can only turn the text into pictures, and cannot copy or modify the text; in addition, the software for recognizing the text in the scanned image is also limited by factors such as the source of the scanned image being unclear and irregular. The accuracy of the transcription cannot be guaranteed when converting the image information into text

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
  • Handwritten content electronization method and device, electronic equipment and storage medium
  • Handwritten content electronization method and device, electronic equipment and storage medium
  • Handwritten content electronization method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] figure 1 It is the first schematic flow chart of the method for digitizing handwritten content provided by the embodiment of this application. The method can be executed by a device or electronic device for digitizing handwritten content, and the device or electronic device can be realized by software and / or hardware , the device or electronic device can be integrated in any smart device with network communication function. Such as figure 1 As shown, the method for digitizing handwritten content may include the following steps:

[0029] S101. Input the image to be transcribed into a pre-trained electronic model; use the electronic model to partition the image to be transcribed to obtain at least one region to be identified in the image to be transcribed.

[0030] In a specific embodiment of the present application, the electronic device can input the image to be transcribed into a pre-trained electronic model; the electronic model is used to partition the image to be ...

Embodiment 2

[0037] figure 2 It is a second schematic flowchart of the method for digitizing handwritten content provided by the embodiment of the present application. Further optimization and expansion based on the above technical solution, and may be combined with each of the above optional implementation modes. Such as figure 2 As shown, the method for digitizing handwritten content may include the following steps:

[0038] S201. Input the image to be transcribed into the pre-trained electronic model; detect the image to be transcribed through the image detection sub-model in the electronic model.

[0039] In this step, the electronic device can input the image to be transcribed into the pre-trained electronic model; the image to be transcribed is detected by the image detection sub-model in the electronic model. Specifically, the image detection sub-model in the embodiment of the present application may be the SAPD model, which is an Anchor Free type target detection algorithm, an...

Embodiment 3

[0061] Figure 4 It is a schematic structural diagram of a device for digitizing handwritten content provided in the embodiment of this application. Such as Figure 4 As shown, the device 400 includes: a partition module 401, an identification module 402, and a transcription module 403; wherein,

[0062] The partitioning module 401 is configured to input the image to be transcribed into a pre-trained electronic model; partition the image to be transcribed through the electronic model to obtain at least one of the images to be transcribed area to be identified;

[0063] The identification module 402 is configured to identify the handwritten content in each area to be identified based on the identification sub-model corresponding to each area to be identified, and obtain the recognition result of each area to be identified;

[0064] The transcribing module 403 is configured to transcribe the handwritten content in the image to be transcribed into corresponding electronic cont...

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 a handwritten content electronization method and device, electronic equipment and a storage medium, and relates to the technical field of image recognition and deep learning. According to the specific scheme, the method comprises the steps of inputting a to-be-transwritten image into a pre-trained electronic model; partitioning the to-be-transwritten image through the electronic model to obtain at least one to-be-identified area in the to-be-transwritten image; recognizing the handwritten content in each to-be-recognized area based on the recognition sub-model corresponding to each to-be-recognized area to obtain a recognition result of each to-be-recognized area; and based on the recognition result of each to-be-recognized area, transferring the handwritten contentin the to-be-transferred image into corresponding electronic content. According to the embodiment of the invention, the handwritten content can be quickly and accurately transliterated into the electronic content, so that the labor cost can be saved, and the transliteration efficiency can be improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and further relates to the technical fields of image recognition and deep learning, especially a method, device, electronic equipment and storage medium for digitizing handwritten content. Background technique [0002] At present, professors in most colleges and universities still mainly teach on the blackboard. The reason for this is to attract the attention of college students so that students can better listen to the class. The teaching notes of professors are often handwritten, which contain the teaching ideas of the professors. Some teaching notes in the library are from the 1970s and 1980s. The paper has turned yellow, but the handwriting of the professors is still very neat and beautiful. They are all handwritten by them bit by bit. These notes are priceless. Typically, professors' handwritten notes are kept as hard copies. Paper material is a kind of material with paper...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F3/0481G06F3/0488G06K9/00G06K9/62G06N3/04G06N3/08G06N20/20
CPCG06F3/0481G06F3/04883G06N20/20G06N3/08G06V30/32G06V30/413G06V30/287G06V2201/07G06N3/045G06F18/214
Inventor 冯博豪庞敏辉谢国斌陈兴波
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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