A word code generation method, recognition method, device, storage medium

A word code and word sentence technology, applied in the field of machine vision recognition, can solve the problems of abrupt vision, users do not know the intention of the QR code, loss, etc., and achieve the effect of avoiding recognition errors

CN109766978BActive Publication Date: 2020-06-16YUESHI NETWORK TECH DEV CO LTD
14 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2020-06-16

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a word code generation method, a recognition method, a device and a storage medium, and belongs to the field of machine vision recognition. Word code generation method: input the target words and sentences and the corresponding target files, split each text of the target words and sentences based on the stroke connection points, and obtain the split sequence; randomly select a number of split sequences to process attribute values ​​abnormally, generate word codes, and Establish association with the target file corresponding to the word code, and output the word code; word code recognition method: obtain the image containing the word code, and identify the target sentence in it; split the target word and sentence according to the same rule and identify all the abnormal split sequences, and judge the word code For example, the code generation based on the system design can be read directly, otherwise, the target word and sentence sequence and the abnormal sequence corresponding to the word code will be used to call the target file entered in advance by the word code. The feature is that the same word and sentence can generate a large number of words with different machine vision features. Code, word code form is still text, human eye recognition word meaning and machine recognition are integrated.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] Embodiments of the present invention relate to the field of machine vision recognition, and in particular to a word code generation method, recognition method, device, and storage medium. Background technique

[0002] With the development of information technology, two-dimensional codes and barcodes have been widely used due to their wide coding range, large information capacity, and easy use.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that the existing two-dimensional code technology has at least the following problems: two-dimensional codes only exist for machine recognition, which means that using two-dimensional codes will occupy additional layout space, two-dimensional codes The shape of the two-dimensional code is a dark square, which is visually abrupt. Embedding articles and printed materials will obviously destroy the reading experience, making typesetting difficult and requiring high ...

Examples

Embodiment Construction

[0057] The implementation mode of the present invention is illustrated by specific specific examples below, and those who are familiar with this technology can easily understand other advantages and functions of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention. rather than all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0058] In the present invention, the split sequence is obtained by splitting the target words and sentences based on the stroke connection points, a number of split sequence elements are randomly obtained from the split sequence, and the split sequence elements are treated differently to adjust the thickness, stroke, shape, The color value, shape and attribute values ​​are ...