Skip to main navigation Skip to search Skip to main content

A new method for general work piece recognition based on Neural Network

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a new method for general work piece recognition based on Wavelet Neural Network is proposed. The composition of the experimental system is introduced and the operating principle is analyzed. The invariant moment is a highly concentrated image feature, which have the characteristics of invariant to translation and rotation. In the selection of the classifier, the Wavelet Neural Network is adopted in that this method has the great advantage of fast training speed and high recognition rate relative to BP Neural Network. Ada-boost is employed because no matter which kind of neural network is used, we can use it to improve the recognition accuracy of the neural network. This is a very wide range of network performance improvement method. The experimental results illustrate that the image recognition method based on wavelet neural network + ada-boost has better ability of classification.

Original languageEnglish
Title of host publicationProceedings of the 28th Chinese Control and Decision Conference, CCDC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3428-3433
Number of pages6
ISBN (Electronic)9781467397148
DOIs
StatePublished - 3 Aug 2016
Event28th Chinese Control and Decision Conference, CCDC 2016 - Yinchuan, China
Duration: 28 May 201630 May 2016

Publication series

NameProceedings of the 28th Chinese Control and Decision Conference, CCDC 2016

Conference

Conference28th Chinese Control and Decision Conference, CCDC 2016
Country/TerritoryChina
CityYinchuan
Period28/05/1630/05/16

Keywords

  • Ada-boost
  • BP neural network
  • Invariant moments
  • Wavelet neural network
  • image recognition

Fingerprint

Dive into the research topics of 'A new method for general work piece recognition based on Neural Network'. Together they form a unique fingerprint.

Cite this