S. Convery, T. Lunney, A. Hashim and M. McGinnity
Presents an overview of automated fabric flaw detection immediately after the knitting process. Considers the classification of fabric flaws and how image processing techniques…
Abstract
Presents an overview of automated fabric flaw detection immediately after the knitting process. Considers the classification of fabric flaws and how image processing techniques can be applied to their classification, via an introductory example. Outlines problems associated with automating this inspection process and discusses possible flaw sensing systems and techniques.
Details
Keywords
G.A.W. West, L. Norton‐Wayne and W.J. Hill
Printed circuit boards are scanned with a CCD linescan camera and a motorised table, under the control of a microcomputer. The camera signal is thresholded to produce a binary…
Abstract
Printed circuit boards are scanned with a CCD linescan camera and a motorised table, under the control of a microcomputer. The camera signal is thresholded to produce a binary image of the track pattern, and this image is processed further in the microcomputer. The processing consists partly of comparisons against a stored master track pattern, and partly of an examination of the scanned track pattern alone to detect anomalies such as whiskers and broken tracks. The system will detect all defects so far presented to it, with an acceptable false alarm rate.
L. Norton‐Warne and D. Guentri
Automatic guided vehicles normally require some form of fixed guidance. But in work being performed at City University guidance will be by using machine processed visual…
Recent developments in the hardware and software mean that the automation of visual fabric inspection tasks is becoming feasible at low cost. This paper investigates the…
Abstract
Recent developments in the hardware and software mean that the automation of visual fabric inspection tasks is becoming feasible at low cost. This paper investigates the techniques that can be used to solve the problem of repetitive, tedious and physically demanding human inspection for defects in shirt collars. The faults studied in this work are those found in nine types of defects that can be present on shirt collar panels. Two statistical methods: moving group average, and moving divided group average are proposed. In addition, highlighting and variance techniques are applied to an image with moving group average and signature counting. These techniques gave an indication of fast computation time to detect the defects on the image, which is needed in manufacturing, and could be applied to most automated inspection systems.
Details
Keywords
The assembly of shoe uppers is a labour‐intensive activity requiring highly developed manipulative and supervisory skills to ensure economic production of adequate quality. A…
Abstract
The assembly of shoe uppers is a labour‐intensive activity requiring highly developed manipulative and supervisory skills to ensure economic production of adequate quality. A typical manufacturing unit in the fashion sector might at any instant have in process say 20 – 40 or more shoe styles, each one comprising left and right, each with ten sizes and perhaps as many as 20 components, in the upper alone. Clearly, any form of automation depending on hard tooling is unacceptable in such an environment. Tool changes are too frequent and the cost and logistics of providing and managing the tooling hardware are prohibitive. There are, of course, exceptions to this rule and machinery based on such technology is successful when production runs are long enough. This article describes an aspect of a major project undertaken by British United Shoe Machinery Ltd (BUSM) and a number of universities, with financial support from the ACME Directorate of the Science and Engineering Research Council. The objective of the programme has been to identify and demonstrate automation technologies of sufficient flexibility to be applicable to a broad range of shoemaking environments. This has been successful, and the following discussion describes in particular a product that arises from work at the City University, carried out in the early 1980s and from more recent work at the University of Hull.
The problems of pattern cutting as applied to flexible elastic mesh fabrics (lace) are described within the context of the total manufacturing process. While the design and…
Abstract
The problems of pattern cutting as applied to flexible elastic mesh fabrics (lace) are described within the context of the total manufacturing process. While the design and knitting stages of lace manufacture are highly computerised, providing associated benefits, the cutting room operates with conventional, slow, labour intensive machinery, leading to substantial processing bottlenecks and dependent costs. A new system is presented which uses machine vision to determine the required cutting path on the lace fabric in real‐time via sophisticated, yet high speed, image processing algorithms. The determined cutting path data are used to direct a high speed CO2 laser beam to the correct cutting point with beam velocities of typically 6 m/sec. Simultaneous dual edge cutting is now possible using this new system, leading to lace throughput being increased by a factor of ten typically, with the possibility of processing more sophisticated designs and achieving higher cut edge quality.