TY - JOUR
T1 - Fabric Defect Classification Based on LBP and GLCM
AU - Lei Zhang, Junfeng Jing & Hongwei Zhang
JO - Journal of Fiber Bioengineering and Informatics
VL - 1
SP - 81
EP - 89
PY - 2015
DA - 2015/08
SN - 8
DO - http://doi.org/10.3993/jfbi03201508
UR - https://global-sci.org/intro/article_detail/jfbi/4688.html
KW - LBP
KW - Gray-level Co-occurrence Matrix (GLCM)
KW - BP Neural Network
KW - Defect Classification
AB - Inevitably there will be various types of fabric defect exists in textile production line. In order to
distinguish and classify the types of defects more efficiently and accurately, an algorithm which combines
Local Binary Patterns (LBP) and Gray-level Co-occurrence Matrix (GLCM) is proposed in this paper
for fabric defect classification. The most pivotal step of the algorithm is to extract the local and global
feature values of defect images. Firstly the local feature information of the image is extracted by adopting
LBP algorithm. And then the overall texture information of the image is described via GLCM algorithm.
In this way, the fabric image can be fully described from global and local. Finally, the two-part feature
information are structured as a whole as the input of BP Neural Network. Thus the trained BP Neural
Network can be used to classify the different types of defects. Experimental results show that the
algorithm has higher classification accuracy.