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

Handwritten character recognition method

A recognition method and text technology, applied in the fields of digital ink recognition, character and pattern recognition, neural learning methods, etc., can solve the problems of reducing the recognition accuracy and loss of handwritten digits, and achieve excellent feature learning ability, improve accuracy, and improve representation. effect of ability

Inactive Publication Date: 2015-08-19
SOUTHWEST JIAOTONG UNIV
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this strategy may cause the information that is beneficial to the recognition of handwritten digits to be lost due to random zeroing, thereby reducing the recognition accuracy of handwritten digits

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 character recognition method
  • Handwritten character recognition method
  • Handwritten character recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Such as figure 1 The recognition method of handwritten characters of the present invention is shown, taking the handwritten numerals of 0~9 as an example, the steps include:

[0034] a. Normalize handwritten input data, in order to facilitate the rapid processing of subsequent data, you can first define a neural network with n layers of depth and the number of neurons in each layer of neural network, where n is a natural number; establish an autoencoder model, and Initialize the weights and biases of the autoencoder model. The role of the autoencoder model is to reproduce the handwritten input signal as closely as possible. In order to reproduce handwritten input signals, the autoencoder model must capture the most important factors that can represent the input data, that is, extract feature information that can characterize the input data. E.g figure 2 The automatic encoder model proposed by Bengio et al., whose mathematical description can be expressed as: y=f θ ...

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 handwritten character recognition method. The method comprises steps: a, handwritten input data are normalized, a neuronal number is defined, an automatic encoder model is built, and weight and bias are initialized; b, through compressing a perceptual model, data compression and sampling are carried out; c, obtained data are automatically encoded and decoded, handwritten input data are rebuilt, and errors between the rebuilt data and original handwritten input data are minimized; d, the built models are stacked layer by layer to form an n-layer neuron feature depth learning model, depth feature learning is carried out on the n-layer neuron traversal, wherein n is a natural number; and e, the recognized handwritten character is outputted. Through simulating features of sensing objects by human brain visual neurons, compression perception and depth learning are combined, detailed features representing handwritten characters are dug automatically, the representation ability of the handwritten character and the model learning efficiency are effectively improved, and the recognition precision and the recognition efficiency of a handwritten character, especially a handwritten number, are greatly improved.

Description

technical field [0001] The invention relates to a method for recognizing handwritten characters, and is particularly suitable for but not limited to a method for recognizing handwritten numbers. Background technique [0002] With the rapid development of information technology, handwritten characters, especially handwritten digit recognition technology, are widely used in e-commerce, automatic machine input and wireless terminals, and are becoming more and more popular. However, because the strokes of the numbers are simple and the differences are relatively small, it is difficult to recognize numbers with similar shapes such as 3 and 8, 5 and 6, etc., and different individuals who write numbers have different writing habits, even if the same person writes each time The results will also be different, which causes the shape of the same number to vary greatly, which not only increases the difficulty of recognition, but also doubles the number patterns to be recognized, greatl...

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 Applications(China)
IPC IPC(8): G06K9/00G06N3/08
CPCG06N3/08G06V30/333G06V30/36
Inventor 余志斌庞荣孙永奎金炜东
Owner SOUTHWEST JIAOTONG UNIV
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