Variance Based Component Analysis for Texture Segmentation

This paper presents a comparative analysis of a new unsupervised PCA-based technique for steel plates texture segmentation towards defect detection. The proposed scheme called Variance Based Component Analysis or VBCA employs PCA for feature extraction, applies a feature reduction algorithm based on variance of eigenpictures and classifies the pixels as defective and normal. While the classic PCA uses a clusterer like Kmeans for pixel clustering, VBCA employs thresholding and some post processing operations to label pixels as defective and normal. The experimental results show that proposed algorithm called VBCA is 12.46% more accurate and 78.85% faster than the classic PCA.

Authors:

• Zeinab Ghasemi
• S. Amirhassan Monadjemi
• Abbas Vafaei

Keywords:

• Principal Component Analysis; Variance Based Component Analysis; Defect Detection; Texture Segmentation.

References:

[1] A. Monadjemi. Towards efficient texture classification and abnormality
detection. PhD Thesis, Department of Computer Science, University of
Bristol, October 2004.
[2] M. Turk, A. Pentland. Eigenfaces for Recognition. Journal of Cognitive
Neuroscience, Vol. 3, No. 1, pp. 71-86, 1991.
[3] A. K. Jain, F. Farrokhnia. Unsupervised Texture Segmentation Using
Gabor Filters. Journal of Pattern Recognition, Vol. 24, No. 12, pp. 1167-
1186, 1991.
[4] Y. Chen, R. Wang. Texture Segmentation Using Independent Component
Analysis of Gabor Features. The 18th International Conference on Pattern
Recognition (ICPR-06), pp. 147-150, 2006.
[5] J. Shlens. A Tutorial on Principal Component Analysis.
http://www.snl.salk.edu/~ shlens/, 2009.
[6] X. Xie. A Review of Recent Advances in Surface Defect Detection using
Texture analysis Techniques. Electronic Letters on Computer Vision and
Image Analysis, Vol. 7, No. 2, pp. 1-22, 2008.
[7] A. Eleyan, H. Demirel. PCA and LDA based Neural Networks for Human
Face Recognition. Face Recognition, Book edited by: Kresimir Delac and
Mislav Grgic, June 2007.