Feature selection for surface defect classification of extruded aluminum profiles

This research investigates detection and classification of two types of the surface defects in extruded aluminium profiles; blisters and scratches. An experimental system is used to capture images and appropriate statistical features from a novel technique based on gradient-only co-occurrence matrices (GOCM) are proposed to detect and classify three distinct classes; non-defective, blisters and scratches. The developed methodology makes use of the Sobel edge detector to obtain the gradient magnitude of the image (GOCM). A comparison is made between the statistical features extracted from the original image (GLCM) and those extracted from the gradient magnitude (GOCM). This paper describes in detail every step of the image processing with example pictures illustrating the methodology. The features extracted from the image processing are classified by a two-layer feed-forward artificial neural network. The artificial neural network training is tested using different combinations of statistical features with different topologies. Features are compared individually and grouped. Results are discussed, achieving up to 98.6 % total testing accuracy.

[1]  Hui-Fuang Ng.  Automatic thresholding for defect detection , 2006, Pattern Recognit. Lett..

[2]  Hong Zheng,et al.  Automatic inspection of metallic surface defects using genetic algorithms , 2002 .

[3]  Germán Castellanos-Domínguez,et al.  Reviewing, selecting and evaluating features in distinguishing fine changes of global texture , 2014, Pattern Analysis and Applications.

[4]  Irwin Sobel,et al.  An Isotropic 3×3 image gradient operator , 1990 .

[5]  Antoniya Georgieva,et al.  Intelligent Visual Recognition and Classification of Cork Tiles With Neural Networks , 2009, IEEE Transactions on Neural Networks.

[6]  Abul Fazal M. Arif,et al.  Analysis of Product Defects in a Typical Aluminum Extrusion Facility , 2004 .

[7]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Praminda Caleb-Solly,et al.  Adaptive surface inspection via interactive evolution , 2007, Image Vis. Comput..

[9]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

[10]  I. M. Elewa,et al.  Assessment of welding defects for gas pipeline radiographs using computer vision , 2004 .

[11]  Du-Ming Tsai,et al.  An anisotropic diffusion-based defect detection for sputtered surfaces with inhomogeneous textures , 2005, Image Vis. Comput..

[12]  Sofia Knapic,et al.  Classification modeling based on surface porosity for the grading of natural cork stoppers for quality wines , 2015 .

[13]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[14]  T. Sheppard.  Extrusion of Aluminium Alloys , 1999 .

[15]  S. Lam.  Texture feature extraction using gray level gradient based co-occurence matrices , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[16]  Franz Pernkopf,et al.  Image Acquisition Techniques for Automatic Visual Inspection of Metallic Surfaces , 2003 .

[17]  Du-Ming Tsai,et al.  Micro-crack inspection in heterogeneously textured solar wafers using anisotropic diffusion , 2010, Image Vis. Comput..

[18]  Nedyalko Petrov,et al.  Self-organizing maps for texture classification , 2011, Neural Computing and Applications.

[19]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[20]  Yi Lu Murphey,et al.  An intelligent real-time vision system for surface defect detection , 2004, ICPR 2004.

[21]  Colin D. Simpson,et al.  Industrial Electronics , 1936, Nature.

[22]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[23]  Ajay Kumar,et al.  Computer-Vision-Based Fabric Defect Detection: A Survey , 2008, IEEE Transactions on Industrial Electronics.

[24]  Shekhar R. Suralkar,et al.  Overview: Methods of Automatic Fabric Defect Detection , 2012 .

[25]  E. R. Davies.  Computer and Machine Vision: Theory, Algorithms, Practicalities , 2012 .

[26]  Zhang Xuewu,et al.  A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM , 2011 .