Title :
Feature selection for steel defects classification
Author :
Jeong, Daun ; Kang, Dongyeop ; Won, Sangchul
Author_Institution :
Grad. Inst. of Ferrous Technol., POSTECH, Pohang, South Korea
Abstract :
In this paper, features of steel defects data are selected using a wrapper algorithm to increase classification performance. The data are constructed using images of steel defects which are classified two classes as defects and pseudo defects. The suggested algorithm selects features which are relevant to class using the kappa statistic. This measure is suggested to improve accuracy of minor class because steel defects data are highly imbalanced. The several algorithms were compared with the algorithm to show performances.
Keywords :
feature extraction; flaw detection; image classification; object detection; statistical analysis; steel; support vector machines; feature selection; image classification; kappa statistic; steel defect classification; support vector machine; wrapper algorithm; Accuracy; Electronic mail; Kernel; Pattern recognition; Steel; Support vector machines; Training data; Backward selection; Feature selection; Imbalanced data; Kappa statistic; SVM; Wrapper method;
Conference_Titel :
Control Automation and Systems (ICCAS), 2010 International Conference on
Conference_Location :
Gyeonggi-do
Print_ISBN :
978-1-4244-7453-0
Electronic_ISBN :
978-89-93215-02-1
