Universiti Teknologi Malaysia Institutional Repository

Neural network paradigm for classification of defects on PCB

Heriansyah, Rudi and Syed Al-Attas, Syed Abdul Rahman and Zabidi, Muhammad Mun'im Ahmad (2003) Neural network paradigm for classification of defects on PCB. Jurnal Teknologi D (39D). pp. 87-104. ISSN 0127-9696

[img] PDF
659Kb

Abstract

A new technique is proposed to classify the defects that could occur on the PCB using neural network paradigm. The algorithms to segment the image into basic primitive patterns, enclosing the primitive patterns, patterns assignment, patterns normalization, and classification have been developed based on binary morphological image processing and Learning Vector Quantization (LVQ) neural network. Thousands of defective patterns have been used for training, and the neural network is tested for evaluating its performance. A defective PCB image is used to ensure the function of the proposed technique.

Item Type:Article
Uncontrolled Keywords:PCB, defects classification, morphological image processing, LVQ
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:Electrical Engineering
ID Code:2086
Deposited By: Pn Norhayati Abu Ruddin
Deposited On:22 Mar 2007 06:15
Last Modified:08 Jun 2011 05:45

Repository Staff Only: item control page