Fabric Defect Detection Using Local Homogeneity Analysis and Neural Network

Table 5

Comparison of the proposed method with some previous research.

Literature	Features	Classifier	Accuracy [%]
[29]	Complex symmetric Gabor filter bank and principal component analysis (PCA)	PCA + Euclidean norm	98.8
[31]	Wavelet based feature extraction and morphological operations + Dempster-Shafer theory	MLP neural networks	89.48
[32]	Radial basis function (RBF) network and gray level arrangement in the neighborhood of each pixel + PCA	PCA + RBF network with Gaussian kernel	83.4
[33]	Small scale overcomplete basis set and Gabor filter	Sparse coding	93
Proposed Methodology	Features derived from DCT transform of -image and FFN	PCA + FFN	97.35