NEURAL NETS AND FUZZY LOGIC

An automated on-line inspection system using advanced vision technology, neural networks, fuzzy logic and wavelets to identify defects in fabrics has made its debut in Phoenix City, Alabama, USA. The system is the brainchild of researchers at the Georgia Institute of Technology. It could ultimately be the basis for an integrated electronic feedback system that […]

An automated on-line inspection system using advanced vision technology, neural networks, fuzzy logic and wavelets to identify defects in fabrics has made its debut in Phoenix City, Alabama, USA.

The system is the brainchild of researchers at the Georgia Institute of Technology. It could ultimately be the basis for an integrated electronic feedback system that would monitor and control quality processes throughout the manufacturing cycle.

The system uses special lighting and high-speed cameras to scan fabric as it comes off the loom. Software algorithms have been developed which are capable of detecting and classifying defects.

`We extract signatures from the images that are characteristic of the type of defect that might be present,’ explains Dr George Vachtsevanos, of Georgia’s school of electrical and computer engineering. `Then we use a new wavelet/neural network package for this signature extraction, along with fuzzy logic decision support systems.’

The technology has been licensed to Appalachian Electronic Instruments of West Virginia. Ultimately, it could be used for medical diagnostics and inspection in the metals, food processing, pulp and paper industries.

{{Georgia Inst. of Technology,Tel: 001 404 894 3444; Fax: 6983.361 on enquiry card}}