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

Distorted character recognition method and device, storage medium and processor

A technology of character recognition and recognition method, applied in the field of character recognition, can solve the problems of limitation of distorted character recognition and low efficiency of distorted character recognition, and achieve the effect of improving the recognition rate of distorted characters

Active Publication Date: 2020-05-05
龙马智芯(珠海横琴)科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a distorted character recognition method and device, a storage medium and a processor to at least solve the technical problem of low recognition efficiency of distorted characters due to restrictions on distorted character recognition in the related art

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
  • Distorted character recognition method and device, storage medium and processor
  • Distorted character recognition method and device, storage medium and processor
  • Distorted character recognition method and device, storage medium and processor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] In the related art, the processing method for distorted text and text pictures is only for recognizing the text on slightly curved scanned documents such as thicker books, and the recognition method is to correct the distorted text, and then for the corrected Image OCR text recognition. However, in this method, since the distorted text needs to be corrected first, a larger workload for correcting the distorted text image is required, resulting in lower recognition efficiency of the distorted text.

[0027] Based on the above problems, a distorted text recognition method is proposed in the embodiment of the present invention. The pre-processed distorted text training set is learned through a convolutional neural network model to obtain a distorted text recognition model, and the trained distorted text recognition model is used To perform text recognition on distorted text images to be recognized, there is no need to correct and then perform OCR recognition. This method h...

Embodiment 2

[0069] According to an embodiment of the present invention, a distorted character recognition device for implementing the above distorted character recognition method is also provided, such as Figure 4 As shown, the device includes:

[0070] 1) Acquisition unit 40, used to obtain the text picture to be recognized, wherein the text picture to be recognized contains distorted text to be recognized;

[0071] 2) recognition unit 42, used for recognizing the text picture to be recognized by the distorted character recognition model trained in advance, to obtain the recognition result;

[0072] 3) A determination unit 44, configured to determine the text in the text picture to be recognized according to the recognition result.

[0073] Optionally, the device also includes:

[0074] 1) a processing unit, which is used to distort a preset number of first text pictures containing text before identifying the text picture to be recognized by a pre-trained distorted text recognition mo...

Embodiment 3

[0078] The embodiment of the invention also provides a storage medium. Optionally, in this embodiment, the above-mentioned storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the distorted character recognition method as described above

[0079] Optionally, in this embodiment, the storage medium is configured to store program codes for performing the following steps:

[0080] S1, acquiring a text picture to be recognized, wherein the text picture to be recognized contains distorted text to be recognized;

[0081] S2, using the pre-trained distorted character recognition model to recognize the character picture to be recognized, and obtain the recognition result;

[0082] S3. Determine the text in the text picture to be recognized according to the recognition result.

[0083] Optionally, for a specific example in this embodiment, reference may be made to the example described in...

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 distorted character recognition method and device, a storage medium and a processor. Wherein, the method includes: obtaining a text picture to be recognized, wherein the text picture to be recognized contains distorted text to be recognized; using a pre-trained distorted text recognition model to recognize the text picture to be recognized to obtain a recognition result; The recognition result determines the text in the text picture to be recognized. The invention solves the technical problem of low recognition efficiency of distorted characters due to restrictions on the recognition of distorted characters in the related art.

Description

technical field [0001] The present invention relates to the field of character recognition, in particular to a distorted character recognition method and device, a storage medium and a processor. Background technique [0002] With the development of the times, multimedia technology is becoming more and more mature, and information applications are becoming more and more extensive. There is an increasing demand for converting traditional paper materials into electronic documents in office, study, and life. Under normal circumstances, we use cameras, scanners and other imaging devices to convert paper text into images, then use image processing technology to process the images, and finally use optical character recognition (OCR) technology to obtain electronic documents. OCR technology accelerates its conversion efficiency. [0003] However, OCR technology also has its limitations. The image recognition effect for distorted text is poor, and the recognition accuracy is betwee...

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 Patents(China)
IPC IPC(8): G06K9/34G06K9/40G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V30/153G06V10/267G06V10/30G06V30/10G06N3/045G06F18/214
Inventor 聂镭王竹欣张峰聂颖郑权
Owner 龙马智芯(珠海横琴)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