An Improved Training Method for Character Recognition Based on Center Loss

A technology of character recognition and training method, which is applied in the field of optical character recognition, can solve the problems of poor recognition results of near-shaped characters, etc., and achieve the effect of improving the recognition rate, making features more easily separable, and accurate recognition rate

Active Publication Date: 2021-11-16
WHALE CLOUD TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can achieve ideal recognition results in most cases, but the recognition results for near-form characters are usually poor.

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
  • An Improved Training Method for Character Recognition Based on Center Loss
  • An Improved Training Method for Character Recognition Based on Center Loss
  • An Improved Training Method for Character Recognition Based on Center Loss

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] In order to further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention, and are mainly used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments, for reference Those of ordinary skill in the art should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0053]According to an embodiment of the present invention, an improved training method for character recognition based on center loss is provided.

[0054] Now in conjunction with accompanying drawing and specific embodiment the present invention is further described, as Figure 1-4 As shown, the text recognition improvement training m...

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 an improved training method for character recognition based on center loss. The method comprises the following steps: S1, performing training on a character recognition data set until convergence, and obtaining a pre-training model; S2, extracting the last The features of the layers are connected to obtain the feature center of the word, and the feature center of the acquired word is used to construct the feature center of a dictionary; S3, continue to train the pre-trained model until convergence. Beneficial effects: the center loss training model module adopted by the present invention can make the feature space of the same character more compact, and for similar characters, it can make them closer to their respective feature centers, making it easier for the similar characters to be recognized Differentiation can improve the accuracy of the model in character recognition without changing the model size and inference speed.

Description

technical field [0001] The invention relates to the field of optical character recognition, in particular to an improved training method for character recognition based on center loss. Background technique [0002] Text recognition technology is a very widely used method to recognize text from images. It mainly uses image processing and pattern recognition technologies to recognize optical characters in pictures and translate them into computer text. It is widely used in production and life, such as ID card, driver's license, passport, form, invoice and other image recognition containing text information. [0003] At present, the most widely used text recognition technology is a method of training with a convolutional recurrent neural network as the backbone network, coupled with a time-domain classification loss function or an attention-based loss function. This method can achieve ideal recognition results in most cases, but the recognition results for near-form characters...

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): G06K9/00G06K9/62G06N3/04
CPCG06V30/413G06V30/10G06N3/045G06F18/214
Inventor 廖翔宇张翊吴名朝
Owner WHALE CLOUD TECH 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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap