An Empirical Method for Optimization of Counterpropagation Neural Network Classifier Design for Fabric Defect Inspection

Abstract

Abstract-Automated, i.e. machine vision based fabric defect inspection systems have been drawing plenty of attention of the researchers in order to replace manual inspection. Two difficult problems are mainly posed by automated fabric defect inspection systems. They are defect detection and defect classification. Counterpropagation neural network (CPN) is a robust classifier and very promising for defect classification. In general, works reported to date have claimed varying level of successes in detection and classification of different types of defects through CPN; but in particular, no claimed has been made for successful application of CPN for fabric defects detection and classification. In those published works, no investigation has been reported regarding to the variation of major performance parameters of NN based classifiers such as learning time and classification accuracy based on network topology and training parameters. As a result, application engineer has little or no guidance to take design decisions for reaching to optimum structure of NN based defect classifiers in general and CPN based in particular. Our work focuses on empirical investigation of interrelationship between design parameters and performance of CPN based classifier for fabric defect classification. It is believed that such work will be laying the ground to empower application engineers to decide about optimum values of design parameters for realizing most appropriate CPN based classifier.

A Preprocessed Counterpropagation Neural Network Classifier for Automated Textile Defect Classification

“…A large number of efforts have been given for automated textile defect inspection [4], [6]- [25]. Most of them have focused on defect detection, where some of them have given attention to classification.…”

“…Habib and Rokonuzzaman [4] have used CPN for textile defect classification. They focused on classifying textile defects using CPN model.…”

“…Counterpropagation Neural Network (CPN) classifier, which is capable of handling complex classification problems with good classification accuracy, has been investigated in different application domains, e.g. on-line handwritten character recognition [1], trademark recognition [2], face detection and recognition [3], and textile defect classification [4]. In this paper, we propose a variant of CPN, named preprocessed CPN (PCPN), which is capable of handling complex classification problems with good classification accuracy, very short training time and simple model complexity.…”

“…Since automated fabric defect inspection system is a real-time system, ANN is a very good choice for defect classification. Although applicability of CPN on textile defect classification has been thoroughly investigated in [4], PCPN can be applied in this context for increasing performance. Likewise it can also be applied on the domains of on-line handwritten character recognition, trademark recognition, face detection and recognition and so on.…”

Batik Classification with Artificial Neural Network Based on Texture-Shape Feature of Main Ornament

“…Instead, the choice of the appropriate activation function can provide ease of subsequent steps in the neural network and produce a better performance. [23].…”