Team: Mohamed Abou-Iiana, PI, Philadelphia University
Yasser A. Gowayed, Auburn University
Claire Beevers, Philadelphia University
Christopher M. Pastore, Philadelphia University
The objective of this research is the development of a computerized system capable
of detecting defects in knitted fabrics during the knitting process. Further,
this system should be able to identify the type and potential source of the
defect, providing the operator with information about how to correct the problem.
The developed systems are capable of identifying defects with greater accuracy
than experts in the knitting industry, promising significant improvements in
quality.
Project Summary
Despite recent advances in computer technology that have brought process
automation to many areas of the textile industry, analyzing knitted fabric structure
to measure fabric parameters, such as courses per unit length, wales per unit
length, cover factor, fabric thickness and weight per unit area, still mainly
depends on manual work. When fabric construction parameters have to be measured
manually, a longer time, a large fabric sample, and many testing tools are required.
Moreover, the results may not be reliable due to variations in testing methods,
tools, and instruments or the tester’s skill.
This study has shown that image analysis has great potential to provide reliable
measurements for objective evaluation of knitted fabric. Using the principles
of image analysis, an automatic fabric evaluation system, which enables automatic
computerized structure-analysis of knitted fabrics, was developed. Fabric construction
parameters, such as courses per unit length, wales per unit length, cover factor,
fabric thickness and weight per unit area, were measured automatically by analyzing
fabric images captured by a CCD camera and preprocessed by Gaussian filtering
and equalization function. The results of the automatic structure analysis correspond
well with the experimental values.
Changes in knitted fabric structure as a result of different relaxation conditions
were documented using the new approach. Also, characteristics of structural
changes in knitted fabrics during manufacturing processes were documented. It
is shown that the developed image capturing and analysis system is capable of
on-line control of knit structures spatial characteristics before and after
wet treatments.
Quality evaluation of knitted fabric is also very important for determining
its commercial value. Even though many researchers have worked on the automation
of quality evaluation, it is still accomplished by human inspection and remains
just at the level of pointing out defects. Many experts are needed for quality
evaluation because the speed of manual inspection is very slow compared with
that of fabric production, and the results may not be the same because decisions
are made by the subjective judgment of each expert. In this study, a quality
evaluation system was developed to detect and classify different knitted fabric
defects, such as hole, needle run, fly, and different barré defects.
For this purpose, a program was built in C programming to classify knitted fabric
defects. A panel of judges evaluated a wide variety of defect and defect free
images subjectively, and the results were compared to the program’s results.
Results show that the program classification is consistent with results obtained
from expert evaluation. In many cases, the program performance was better than
the evaluation from the experts. It is expected that the quality evaluation
system can be used for automatic on-line quality control on the knitted machine
or as a supplement to objective gradation of knitted fabric.
Comparison of the developed software method to expert evaluations
Other Contributors:
Safinaz Youseff, MS;
Suhasini Ram, MS Candidate
James Kaufmann, Research Associate
FOR FURTHER INFORMATION
PROJECT STATISTICS:
# graduate students involved in the research: 4
# undergraduate students involved in the research: 0
# theses completed: 2
# presentations:
# publications:
# papers submitted:
# patent applications (use title in "For Further Information"): 0
# patents granted (use title in "For Further Information"): 0
# notices of invention (use title in "For Further Information"): 0
# copyrights (use title in "For Further Information"): 0
OUTSIDE CONTACTS
# contacts with industry:
# contacts with academic (non-NTC), including those in other disciplines in
the same university:
# contacts with others, including government: