Real Time Automated Fabric Defect Detection System using Microcontroller

In a Least Developed Country (LDC) like Bangladesh where the textile is the main core of our economy; still there is a major drawback in this sector which is the defect detection of the fabric. In the manual fault detection system with highly trained inspectors, very less percentage of the defects are being detected in upon fabrics in the textile industries. But a real time automatic system can increase this percentage in a maximum number. This research implements a textile defect detector which uses computer vision methodology with the combination of multi-layer neural networks to identify the classification of textile defects and detect it with a real time configured mechanical system containing a microcontroller. The recognizer, suitable for LDC countries, specially for Bangladesh where textile exports earns the maximum for the country's economy. Keywords Real time, neural networks, LDC, QIS, PICProg, PICmicro emulator, Then PicBasic Pro 2.45, percetron network, fuzzified.

• Type: Journal
• Year: 2008
• Where: JCIT
• Authors: Tamnun E. Mursalin, Fajrana Zebin Eishita, Ahmed Ridwanul Islam, Md. Jahangir Alam
• Keywords: JCIT 2008, Real Time, Textile, Textile Defects