Pattern Classification of Fabric Defects Using a Probabilistic Neural Network and Its Hardware Implementation using the Field Programmable Gate Array System

Journal Title: Fibres and Textiles in Eastern Europe - Year 2017, Vol 25, Issue 1

Abstract

This study proposes a fabric defect classification system using a Probabilistic Neural Network (PNN) and its hardware implementation using a Field Programmable Gate Arrays (FPGA) based system. The PNN classifier achieves an accuracy of 98 ± 2% for the test data set, whereas the FPGA based hardware system of the PNN classifier realises about 94±2% testing accuracy. The FPGA system operates as fast as 50.777 MHz, corresponding to a clock period of 19.694 ns.

Authors and Affiliations

Abul Hasnat, Anindya Ghosh, Amina Khatun, Santanu Halder

Keywords

Related Articles

Comparison of the Structure and Properties of Wool and Cashmere Fibres under Potassium Permanganate Treatment

In this study, the weight loss and tensile property of wool fibers and cashmere fibers before and after various potassium permanganate solution treatment were investigated. The scale morphology and crystallization index...

Coating of Seeds with Collagen Hydrolysates from Leather Waste

The subject of this paper is improvement in the growth and yield of three different types of legumes and rape in drought conditions by coating seeds with hydrolysed collagen from tanning waste. In addition, the impact o...

Selection of Clothing for a Cold Environment by Predicting Thermophysiological Comfort Limits

Results are presented from a study on the prediction of the insulation abilities of outerwear clothing for cold protection from the point of view of the thermophysiological comfort of the wearer. The Required Clothing In...

Evaluation of Cotton Fibre Properties in Compact Yarn Spinning Processes and Investigation of Fibre and Yarn Properties

Fibre properties are influential factors for yarn properties. Cotton, whose physical properties vary depending on the cultivation region, is still a very common fibre used in the textile industry. Properties such as fibr...

Badanie zależności pomiędzy liczbą i pozycją splotów nabieranych i wytrzymałością dzianin wykonanych na szydełkarce cylindrycznej

Zagadnienie tłumienia hałasu uzyskuje coraz większe znaczenie w badaniach naukowych, technologicznych i zagadnieniach ogólnych ponieważ poziom dźwięku określa jakość ludzkiej egzystencji i dlatego izolacja akustyczna jes...

Download PDF file
  • EP ID EP199554
  • DOI 10.5604/01.3001.0010.1709
  • Views 79
  • Downloads 0

How To Cite

Abul Hasnat, Anindya Ghosh, Amina Khatun, Santanu Halder (2017). Pattern Classification of Fabric Defects Using a Probabilistic Neural Network and Its Hardware Implementation using the Field Programmable Gate Array System. Fibres and Textiles in Eastern Europe, 25(1), 42-48. https://europub.co.uk./articles/-A-199554