Handwritten form identification system of BP neural network based on dynamic sample selection strategy

A BP neural network and recognition system technology, applied in the field of BP neural network handwriting recognition based on dynamic sample selection strategy, can solve the problems of low practicability and long training time, and achieve the effect of solving the problem of excessive training time

Inactive Publication Date: 2016-10-12
EAST CHINA UNIV OF SCI & TECH
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problems that the existing handwritten character recognition technology based on BP neural network has too long training time and low practicability when processing large data sets, the solution of the present invention

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 form identification system of BP neural network based on dynamic sample selection strategy
  • Handwritten form identification system of BP neural network based on dynamic sample selection strategy
  • Handwritten form identification system of BP neural network based on dynamic sample selection strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The present invention will be further introduced below in conjunction with accompanying drawing and embodiment: the method of the present invention is divided into three major steps altogether.

[0012] Step 1: Data collection and network initialization.

[0013] The system mainly uses the MNIST handwritten digit database as the training sample set, and separates out a small part of untrained samples to verify the correct rate of network recognition, and uses PCA and LDA to reduce the dimensionality of high-dimensional handwritten font data, convert into a vector form as the final training sample and validation set.

[0014] The system determines the structure of the network used according to the size of the large data set, and randomly initializes the weights of neurons in each layer of the network. The initialization of the network structure includes the number of nodes in each layer of the network and the type of activation function used by the network; the initiali...

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 provides a handwritten form identification system of BP neural network based on a dynamic sample selection strategy. Weights of different layers of network neurons are initialized randomly; a gradient descent method is used to optimize the network weight, in first round of iteration, all samples are used to calculate the total gradient, the total gradient is used to update the weights of different layers, and whether a sample serves as a training sample in next round of iteration is determined according to whether the sample is far from a decision boundary, and the training samples selected in the last round are used to calculate the total gradient, update the weights of different layers and select samples for next round of iteration repeatedly till the minimal stop error or the maximal interaction frequency is reached; and the obtained neural network is used to identify an unknown hand-written font sample. Compared with a traditional classification technology, According to sample selection strategy of the invention, the samples are selected dynamically according to the distances to the decision boundary, the amount of training sample is decreased step by step, and an algorithm can effectively solve the problem that training time of the BP network is too long in a big data set.

Description

technical field [0001] The invention relates to the field of pattern recognition, in particular to a BP neural network handwriting recognition method and system based on a dynamic sample selection strategy. Background technique [0002] Optical Character Recognition (OCR) is a practical technology for computers to automatically and quickly identify text on paper and convert it into editable text. Handwritten digit recognition is an important branch of optical character recognition technology. Its research object is how to use computers to automatically recognize Arabic numerals written by people on paper. The main difficulties in handwritten number recognition are: first, there is not much difference in the shape of some numbers, which makes it difficult to distinguish these numbers accurately; It is used by people in all countries and regions, and its writing has obvious regional characteristics. It is difficult to fully achieve a universal digital recognition system with ...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06V30/293G06F18/285G06F18/00G06F18/214
Inventor 李冬冬凤伟王喆范奇曹真
Owner EAST CHINA UNIV OF SCI & 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