Handwritten character recognition method based on expanded nonlinear kernel residual network

A technology of handwritten characters and recognition methods, which is applied in the field of deep learning and machine learning, can solve problems such as inability to extract expressive ability, and achieve the effects of easy implementation, performance improvement, and simple implementation

Inactive Publication Date: 2017-09-15
HUBEI UNIV OF TECH
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method cannot extract features with good expressive ability when the amount of handwritten digital data increases.

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 based on expanded nonlinear kernel residual network
  • Handwritten character recognition method based on expanded nonlinear kernel residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The above-mentioned content of the present invention will be described in further detail below through the embodiment form, but this should not be interpreted as the scope of the above-mentioned theme of the present invention is limited to the following embodiments, all technologies realized based on the above-mentioned content of the present invention belong to this invention the scope of the invention.

[0033] figure 1 It is a flow chart of handwritten character recognition based on the extended nonlinear kernel residual network of the present invention.

[0034] In this example, if figure 1 As shown, the present invention is based on the handwritten character recognition method of extended nonlinear kernel residual network, comprises the following steps:

[0035] (1) Example verification with the standard handwritten digit recognition library MNIST

[0036] (2) Initialize various parameters: the convolution layer uses a 7*7 convolution kernel, and the sliding ste...

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 a handwritten character recognition method based on an expanded nonlinear kernel residual network. A novel deep learning method, namely an algorithm based on the expanded nonlinear kernel residual network is provided by utilizing structural characteristics of a deep network, and the handwritten character recognition method based on the expanded nonlinear kernel residual network is proposed by applying the deep learning algorithm to handwritten character recognition. Through the method, the correlation between sample data and expected data can be described deeply, and digital image features can be automatically learned from original data efficiently; next, an appropriate intra-class unsupervised clustering algorithm is introduced into the method, and existing technical defects of the deep learning network in the handwritten character recognition field are overcome. The method is simple and easy to implement, and network training efficiency is improved while handwritten character recognition performance is improved.

Description

technical field [0001] The invention relates to the technical fields of deep learning and machine learning, in particular to a handwritten character recognition method based on an extended nonlinear kernel residual network. Background technique [0002] As an important branch of image recognition applications, handwritten digit recognition is gradually showing its importance in production and life. Handwritten digit recognition can be used to read bank check information, envelope postal code information, customs and other occasions that need to process a large number of character information entry. Therefore, people's requirements for the handwritten digit recognition system established by the computer are also constantly increasing. To complete the task of recognizing Arabic numerals, the prerequisite for the handwritten digit recognition system is to build a handwritten digit recognition model, so the most basic problem in the research of handwritten digit recognition meth...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V30/10G06N3/045G06F18/23G06F18/2414
Inventor 武明虎饶哲恒曾春艳刘敏赵楠孔祥斌刘聪万相奎宋冉冉李想周志虎
Owner HUBEI UNIV OF TECH
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