Skip to main navigation Skip to search Skip to main content

Recognition and classification of ultrasonic aluminum wire joint based on image morphology and C-SVM

  • Rui Wang
  • , Long Zhili*
  • , Zhou Xing
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen

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

Abstract

Aiming at the quality inspection of ultrasonic aluminum wire joint, this paper proposes a method of ultrasonic aluminum wire joint quality identification based on PCA and C-SVM. Firstly, extracting the ultrasonic aluminum joint image from the ultrasonic welding element image by applying image morphological operations and image histogram equalization, and then reducing the dimension of the ultrasonic aluminum joint image data by applying PCA, finally identifying the quality of the joint by applying C-SVM with Gauss-RBF kernel function. Experimental results show that this method has a high accuracy.

Original languageEnglish
Title of host publication18th International Conference on Electronic Packaging Technology, ICEPT 2017
EditorsChenxi Wang, Yanhong Tian, Tianchun Ye
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages898-903
Number of pages6
ISBN (Electronic)9781538629727
DOIs
StatePublished - 19 Sep 2017
Externally publishedYes
Event18th International Conference on Electronic Packaging Technology, ICEPT 2017 - Harbin, China
Duration: 16 Aug 201719 Aug 2017

Publication series

Name18th International Conference on Electronic Packaging Technology, ICEPT 2017

Conference

Conference18th International Conference on Electronic Packaging Technology, ICEPT 2017
Country/TerritoryChina
CityHarbin
Period16/08/1719/08/17

Keywords

  • Machine Vison
  • PCA
  • SVM
  • Ultrasonic Aluminum wire welding

Fingerprint

Dive into the research topics of 'Recognition and classification of ultrasonic aluminum wire joint based on image morphology and C-SVM'. Together they form a unique fingerprint.

Cite this