Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Picture character recognition method and recognition device

A text recognition and recognition method technology, applied in the field of picture text recognition methods and recognition devices, can solve the problems of lack of training samples, poor text recognition model training effect, low text recognition accuracy, etc. Enhance and improve efficiency

Pending Publication Date: 2019-11-05
ZHONGAN INFORMATION TECH SERVICES CO LTD
View PDF10 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem mainly solved by the present invention is how to overcome the problems of poor text recognition model training effect and low text recognition accuracy caused by lack of training samples

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
  • Picture character recognition method and recognition device
  • Picture character recognition method and recognition device
  • Picture character recognition method and recognition device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Please refer to figure 1 , the present application discloses a method for recognizing text in pictures, which includes steps S100-S300, which will be described respectively below.

[0042] Step S100, acquiring a picture of a text line to be recognized, where the picture of a text line to be recognized contains text.

[0043] It should be noted that a text line picture refers to a picture containing text content distributed in rows or columns, and there is only one line of text or one column of text. In addition, the word here is a broad concept, including the language characters of various countries, punctuation marks, numbers, Greek symbols and other characters that have the function of information recognition.

[0044] It should be noted that the text in the picture of the text line to be recognized can be e-mail address, phone number, mailing address, name, slogan, poem, foreign word, logo, etc., which is not limited here.

[0045] Step S200, inputting the picture ...

Embodiment 2

[0075] Please refer to Figure 5 , on the basis of the recognition method disclosed in Embodiment 1, this application correspondingly discloses a picture and text recognition device 1, which mainly includes an acquisition unit 11, a recognition unit 12 and an output unit 13, which will be described separately below.

[0076] The acquiring unit 11 is configured to acquire a picture of a text line to be recognized, and the picture of a text line to be recognized includes text. It should be noted that the text in the picture of the text line to be recognized can be e-mail address, phone number, mailing address, name, slogan, poem, foreign word, logo, etc., which is not limited here.

[0077] The recognition unit 12 is connected with the acquisition unit 11, and is used for inputting the picture of the text line to be recognized into the pre-established image character recognition model to recognize the text in the picture of the text line to be recognized. Among them, the image ...

Embodiment 3

[0084] Please refer to Figure 7 , on the basis of the recognition method for pictorial characters disclosed in Embodiment 1 of the present application, the present application also requests protection for a recognition system 2 for pictorial characters, which mainly includes a memory 21 and a processor 22, wherein the memory 21 uses In order to store the program, the processor 22 is used to implement the identification method in the first embodiment by executing the program stored in the memory 21, that is, to realize steps S100-S300 in the first embodiment, and to realize step S400.

[0085] Those skilled in the art can understand that all or part of the functions of the various methods in the foregoing implementation manners can be realized by means of hardware, or by means of computer programs. When all or part of the functions in the above embodiments are implemented by means of a computer program, the program can be stored in a computer-readable storage medium, and the s...

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 relates to a picture character recognition method and device, and the method comprises the steps: obtaining a to-be-recognized text line picture, inputting the to-be-recognized text linepicture into a pre-built picture character recognition model, so as to obtain a character in the to-be-recognized text line picture through recognition, and outputting the character in the to-be-recognized text line picture, wherein the picture character recognition model is obtained by training a deep neural network by using a plurality of text line pictures for training, and the text line pictures for training are obtained by performing expansion change processing on standard text line pictures. The text line picture for training is obtained by performing expansion change processing on thestandard text line picture; therefore, the training sample set of the picture character recognition model is more suitable for practical application, and compared with the training samples obtained byrandomly combining characters, the number of the training samples is greatly reduced, but the efficiency of generating the training samples and the training model is greatly improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for recognizing pictures and characters and a device for recognizing them. Background technique [0002] The field of optical character recognition (OCR) has always been an important branch in the field of computer vision, and has great demand in the fields of finance and education. In the existing optical character recognition methods, there are situations based on single character recognition, and there are situations based on text line recognition. Among them, the method based on word recognition has the problems of difficulty in accurately segmenting words and inability to synthesize context, resulting in the fact that the accuracy of word recognition in practical applications is often unsatisfactory. In addition, the method based on text line recognition requires a large number of high-quality training samples to train a better text line recognitio...

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): G06K9/34G06K9/62G06N3/08G06N3/04
CPCG06N3/08G06V30/153G06V30/10G06N3/045G06F18/214
Inventor 彭宇翔朱帆
Owner ZHONGAN INFORMATION TECH SERVICES CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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