Unlock instant, AI-driven research and patent intelligence for your innovation.

Handwritten text recognition method and computer storage medium

A text recognition and text image technology, which is applied in the field of handwritten text recognition methods and computer storage media, can solve problems such as poor robustness, variable scales, and missing characters in recognition, so as to improve extraction ability and expression ability, and enhance robustness. Rod, improve the effect of leak identification

Active Publication Date: 2021-06-18
BEIJING CENTURY TAL EDUCATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The text recognition method in the prior art has a good recognition effect on written and printed text, but the recognition effect on handwritten text is poor, and cannot adapt to the style changes of handwritten fonts
Specifically, handwritten text lines also have fonts with variable scales and font intervals with different densities, resulting in serious missing characters in recognition
In addition, text recognition of low-quality handwritten text images such as blurred images of handwritten fonts, distorted images of handwritten fonts, and images of handwritten fonts with variable sizes is less robust

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 text recognition method and computer storage medium
  • Handwritten text recognition method and computer storage medium
  • Handwritten text recognition method and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] refer to figure 1 , shows a flowchart of steps of a handwritten text recognition method according to Embodiment 1 of the present invention.

[0021] Specifically, the handwritten text recognition method provided by the embodiment of the present invention includes the following steps:

[0022] In step S101, the image contour features of the handwritten text image to be recognized are encoded by the encoder based on the feature pyramid network in the first handwritten text recognition model, so as to obtain image contour features of multiple different scales of the handwritten text image data, and perform multi-scale feature fusion on the plurality of image contour feature data of different scales to obtain the image contour feature fusion data of the handwritten text image.

[0023] In this embodiment, the first handwritten text recognition model can be understood as a neural network model for handwritten text recognition. The first handwritten text recognition model c...

Embodiment 2

[0050] An embodiment of the present invention also provides a computer-readable medium, the computer storage medium stores a readable program, and the readable program includes: an encoder based on a feature pyramid network in the first handwritten text recognition model, treating Encoding the image contour features of the recognized handwritten text image to obtain multiple image contour feature data of different scales of the handwritten text image, and performing multi-scale feature fusion on the multiple different scale image contour feature data to obtain An instruction for obtaining image contour feature fusion data of the handwritten text image; for performing residual decoding on the image contour feature fusion data of the handwritten text image through a residual decoder in the first handwritten text recognition model, Instructions for obtaining the character posterior probability distribution data of the handwritten text in the handwritten text image; used to pass th...

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

Embodiments of the present invention provide a handwritten text recognition method and a computer storage medium. Wherein, the method includes: using an encoder based on a feature pyramid network in the first handwritten text recognition model, encoding the image contour features of the handwritten text image to be recognized, so as to obtain multiple image contour features of the handwritten text image at different scales Data, and perform multi-scale feature fusion on multiple image contour feature data of different scales to obtain image contour feature fusion data of handwritten text images; through the residual decoder in the first handwritten text recognition model, the handwritten text image Image contour feature fusion data is used for residual decoding to obtain the character posterior probability distribution data of handwritten text in the handwritten text image; through the connection time series classification layer in the first handwritten text recognition model, based on the handwritten text in the handwritten text image Character posterior probability distribution data, handwritten text recognition results for handwritten text images.

Description

technical field [0001] The embodiments of the present invention relate to the field of intelligent text recognition, in particular to a handwritten text recognition method and a computer storage medium. Background technique [0002] Since handwritten text images in real scenes are very complex, the images often contain distorted or overlapping characters, characters of different fonts, sizes and colors, and complex background noise. Therefore, textual information in images for text recognition tasks is essential for visual semantic understanding tasks. However, handwritten text recognition is different from traditional OCR (Optical Character Recognition, optical character recognition). The main reason is that everyone has different writing habits, which are reflected in font, size, density and even direction. [0003] The text recognition methods in the prior art have a good recognition effect on written and printed text, but poor recognition effect on handwritten text, and...

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): G06K9/00G06K9/46G06K9/48G06K9/62G06N3/04G06N3/08
Inventor 姜明刘霄熊泽法
Owner BEIJING CENTURY TAL EDUCATION TECH CO LTD