Effect of Color Space, Color Channels, and Sub-Image Block Size on the Performance of Wavelet-Based Texture Analysis Algorithms: An Application to Corrosion Detection on Steel Structures

It is well-recognized that the corrosion of metallic structures has a significant impact (i.e., direct cost of approximately $276 billion per year) on the U.S. economy, including infrastructure, transportation, utilities, production and manufacturing, etc. There is an urgent need to develop more reliable ways to detect corrosion. Image processing techniques have been used extensively to detect corrosion in structures; however, it is essential to evaluate the effect of different parameters on the performance of vision-based corrosion detection systems. This study evaluates the effect of several parameters, including color space, color channels, and sub-image block size on the performance of color wavelet-based texture analysis algorithms for detecting corrosion.

[1]  Alberto Ortiz,et al.  Combination of weak classifiers for metallic corrosion detection and guided crack location , 2010, 2010 IEEE 15th Conference on Emerging Technologies & Factory Automation (ETFA 2010).

[2]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[3]  Jing Li Wang,et al.  Color image segmentation: advances and prospects , 2001, Pattern Recognit..

[4]  Gaurav S. Sukhatme,et al.  A survey and evaluation of promising approaches for automatic image-based defect detection of bridge structures , 2009 .

[5]  Stéphane Mallat,et al.  Multifrequency channel decompositions of images and wavelet models , 1989, IEEE Trans. Acoust. Speech Signal Process..

[6]  Nicholas J. Carino,et al.  Health monitoring of civil infrastructures , 2003 .

[7]  Walter H. Buchsbaum,et al.  Color TV servicing , 1975 .

[8]  Paul Scheunders,et al.  Classification of Corrosion Images by Wavelet Signatures and LVQ Networks , 1995, CAIP.

[9]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[10]  Vikram Pakrashi,et al.  ROC dependent event isolation method for image processing based assessment of corroded harbour structures , 2010 .

[11]  Gregg Podnar,et al.  Image understanding algorithms for remote visual inspection of aircraft surfaces , 1997, Electronic Imaging.

[12]  Fátima N. S. de Medeiros,et al.  On the Evaluation of Texture and Color Features for Nondestructive Corrosion Detection , 2010, EURASIP J. Adv. Signal Process..

[13]  B. S. Manjunath,et al.  Color image segmentation , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[14]  H. Furuta,et al.  Neural network analysis of structural damage due to corrosion , 1995, Proceedings of 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society.

[15]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[16]  Ronie Navon,et al.  Automated inspection and restoration of steel bridges—a critical review of methods and enabling technologies , 2002 .

[17]  S. S. Kim,et al.  Morphological analysis and classification of types of surface corrosion damage by digital image processing , 2005 .