Title: Detection of fabric defects using fuzzy decision tree

Authors: Madasu Hanmandlu; Dilip K. Choudhury; Sujata Dash

Addresses: Department of Electrical Engineering, IIT, Delhi, India ' GIET - Gandhi Institute of Engineering and Technology, Gunupur, Odissa, India ' GIFT - Gandhi Institute for Technology, Bhubaneswar, India

Abstract: This paper presents the representation of fabric texture by four features: Local Binary Patterns (LBP), Local Directional Patterns (LDP), Scale Invariant Feature Transform (SIFT) and Speeded up Robust Features (SURF). The features extracted by these approaches are used in the Fuzzy Decision Tree (FDT) to detect defects in fabrics. We employ both fuzzy Gini index and fuzzy Shannon entropy as the splitting criteria. Two membership functions: Gaussian and trapezoidal are employed for the fuzzification of the genuine and imposter scores. A stopping criterion is devised to terminate the FDT. It is found that LDP features outperform LBP, SIFT and SURF features in the classification of defects in fabrics.

Keywords: LBP; local binary patterns; LDP; local directional patterns; SIFT; SURF; Gaussian; trapezoidal; fuzzy Gini index; fuzzy Shannon entropy; FDT; fuzzy decision trees; defect detection; fabric defects; fabric texture; feature extraction; fabrics.

DOI: 10.1504/IJSISE.2016.076230

International Journal of Signal and Imaging Systems Engineering, 2016 Vol.9 No.3, pp.184 - 198

Received: 21 May 2013
Accepted: 09 Apr 2014

Published online: 30 Apr 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article