Abstract
This paper proposes comparative study of two basic
approaches such as Morphological Approach (MA) and
Correlation Approach (CA) and three modified algorithms
over the basic approaches for detection of micronatured defects
occurring in plain weave fabrics. A Hybrid of CA followed by
MA was developed and has shown to overcome the drawbacks
of the basic methods. As automation of MA using DC
Suppressed Fourier Power Spectrum Sum (DCSFPSS),
DCSFPSSMA could not yield improvement in Overall
Detection Accuracy (ODA) for micronatured defects,
automation of modified Hybrid Approach (HA) was proposed
leading to the development of Tribrid Approach (TA). Modified
Hybrid approach involves cascade operation of CA and MA
both automated using DCSFPSS. Texture periodicity of defect
free fabric was obtained using DCSFPSS which was extended
for the design and extraction of defect independent template
for CA and for the design of the size of structuring element
for morphological filtering process. Overall Detection
Accuracy was used by adopting simple binary based defect
search algorithm as the last step in the experimentation to
detect the defects. Overall Detection Accuracy was found to be
~100%/97.41%/ 98.7 % for 247 samples of warp break defect/
double pick/ normal samples and 96.1% /99% for 205 thick
place defect samples/normal samples belonging to two
different plain grey fabric classes. Robustness of the
performance of TA scheme was tested by comparing TA with
two traditional algorithms viz., CA and MA and our previously
proposed hybrid algorithm and DCSFPSSMA. This TA
algorithm outperformed when compared to CA-only, MA-only,
HA and DCSFPSSMA by yielding an overall ODA of more
than 98% for the defect and defect free samples of different
fabric classes. Secondly, the recognition of defect area less
than 1 mm2 which has not been reported in the literature yet,
was possible using this algorithm. We propose to use this
method as a means to grade the grey fabric similar to the
standard fabric grading system.
Users
Please
log in to take part in the discussion (add own reviews or comments).