Paper Title:

Automatic Solder Joint Defect Classification using the Log-Gabor Filter

Periodical Advanced Materials Research (Volumes 97 - 101)
Main Theme Manufacturing Science and Engineering I
Edited by Zhengyi Jiang and Chunliang Zhang
Pages 2940-2943
DOI 10.4028/
Citation Nang Seng Siri Mar et al., 2010, Advanced Materials Research, 97-101, 2940
Online since March 2010
Authors Nang Seng Siri Mar, Clinton Fookes, K.D.V. Yarlagadda Prasad
Keywords Automatic PCB Inspection, Classification, Feature Extraction, Log-Gabor Filter, Mahalanobis Cosine Distance
Price US$ 28,-
Article Preview
View full size

This paper proposes the validity of a Gabor filter bank for feature extraction of solder joint images on Printed Circuit Boards (PCBs). A distance measure based on the Mahalanobis Cosine metric is also presented for classification of five different types of solder joints. From the experimental results, this methodology achieved high accuracy and a well generalised performance. This can be an effective method to reduce cost and improve quality in the production of PCBs in the manufacturing industry.