Machine learning approach for automated visual inspection of machine components
Machine learning approach for automated visual inspection of machine components
复制标题
DOI：
10.1016/j.eswa.2010.09.012
复制
发表时间：
2011-04-01
影响因子：
8.5
通讯作者：
Sugumaran, V.
中科院分区：
文献类型：
--
作者：
Ravikumar, S.;Ramachandran, K. I.;Sugumaran, V.
零件表面的视觉检测是机器视觉的一个主要应用。目视检测可用于识别划痕、裂纹、气泡等缺陷，以及测量刀具磨损和焊接质量。机器视觉的机器学习方法有助于机器视觉系统设计过程的自动化。该方法包括图像采集、预处理、特征提取和分类。研究表明，有一个特征库，分类器可以用来对数据进行分类。然而，只有它们的最佳组合才能产生最高的分类精度。本研究对不同已知条件下的图像进行采集、预处理和直方图特征提取。比较了C4.5分类器算法和朴素贝叶斯算法的分类精度，并给出了分类结果。研究表明，C4.5算法具有更好的性能。(C)2010爱思唯尔有限公司。保留所有权利。
Visual inspection on the surface of components is a main application of machine vision. Visual inspection finds its application in identifying defects such as scratches, cracks bubbles and measurement of cutting tool wear and welding quality. Machine learning approach to machine vision helps in automating the design process of machine vision systems. This approach involves image acquisition, preprocessing, feature extraction and classification. Study shows a library of features, and classifiers are available to classify the data. However, only the best combination of them can yield the highest classification accuracy. In this study, images with different known conditions were acquired, preprocessed, and histogram features were extracted. The classification accuracies of C4.5 classifier algorithm and Naive Bayes algorithm were compared, and results are reported. The study shows that C4.5 algorithm performs better. (C) 2010 Elsevier Ltd. All rights reserved.