Characteristics Of Butt Welding Imperfections Joint Using Co-Occurrence Matrix

The goal of this paper is to study the characteristics of the butt joint imperfections with different types of joint shapes (curve, straight and tooth saw work piece) according to their class categories (good welds, excess welds, insufficient welds and no welds). The work piece is placed in a center...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd Shah, Hairol Nizam, Kamis, Zalina, Sulaiman, Marizan, Ab Rashid, Mohd Zamzuri, Mohd Aras, Mohd Shahrieel, Ahmad, Azhar
Format: Article
Language:en
Published: National Institute Of Science Communication And Information Resources (NISCAIR) 2019
Subjects:
Online Access:http://eprints.utem.edu.my/id/eprint/24096/2/marizan_99.pdf
http://eprints.utem.edu.my/id/eprint/24096/
http://nopr.niscair.res.in/bitstream/123456789/48849/3/IJMS%2048%287%29%201164-1169.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The goal of this paper is to study the characteristics of the butt joint imperfections with different types of joint shapes (curve, straight and tooth saw work piece) according to their class categories (good welds, excess welds, insufficient welds and no welds). The work piece is placed in a center position on the workbench. The distance between camera and workpiece is set as 300 mm during welding imperfections process and the entire work piece image is taken from the same distance to maintain the accuracy. The input feature vector is determined by feature co-occurrence matrix consisting of energy, correlation, homogeneity and contrast both no scaled and scaled by 0.5. Results show that no welds class categories exhibit higher homogeneity compared to the other class categories. This is because the homogeneity value depends on bright and dark parts of a certain size and also include some changes from dark to bright. Meanwhile, insufficient welds class categories produced larger contrast value, but good weld class categories recorded higher contrast value.