Open AccessAutomatic Detection of Surface Defects in Industrial Materials Based on Image Processing
Author(s) -
R Srividhya,
K. Shanmugapriya,
K. Sindhu Priya
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.34.18717
Subject(s) - artificial intelligence , image processing , computer science , matlab , computer vision , process (computing) , image (mathematics) , field (mathematics) , image segmentation , digital image processing , segmentation , transfer of learning , pattern recognition (psychology) , mathematics , pure mathematics , operating system
In the field of industry, corrosion and defects are amongst the most frequent operations. Industrial Materials have periodic defects that are difficult to detect during production even by experienced human inspectors. Defects are difficult to detect during production even by experienced human inspectors. Usually, the colour transfer process contains an image segmentation phase and an image construction phase. Therefore, we introduce an image processing method for automatically detecting the defects in surfaces. We show how barely visible defect can be optically enhanced to improve annual assessment as well as how descriptor-based image processing and machine learning can be used to allow automated detection. Image enhancement is performed by applying manual calculation. We implement this simulation using MATLAB R2013a. Results show that the proposed allows training both tested classifiers with good classification rates around 98.9%.