Fabric Defects Detecting in Textile Industries

Course Code : QTEX - 4021

Course Name : Textile Quality Management

Submitted To
Ms. Israt Zerin
Lecturer
Dept. of Textile Engineering

Submitted By
Name:- Iqbal Hossain
Id:- 2016100400011
Batch:- 32nd

Submission Date
20th September 2020
Introduction :-
In the textile manufacturing industry, fabric defect detection becomes a necessary and essential
step in quality control. The investment in this field is more than economical when reduction in
labor cost and associated benefits are considered. Moreover, the development of a wholly
automated inspection system requires efficient and robust algorithms. To overcome this problem,
in this paper, we present some fabric defect detection scheme. . In this assignment, here it is
summarized four journals about fabric defect detecting for upgrading quality of fabric and
improvement of quality control by help of modern coloration monitoring, automation, reducing
cost.

Objects of this Assignment:-

 To know about different types of fabric defect detection system.
 To know how could we reduce time and cost while inspecting fabric.
 To know how a Digital Image Processing system detect fabric defects.
 To know the uses of Morphological Operations on Bit Plane and its effect on fabric fault
detection.
 To know about Diffractive Optics for Fabric Fault Detection.
 To know about the uses of Micro-controller in detecting fabric defect.
 To know about financial analysis and application of Quality control in fabric fault -
detection.

Fabric Fault Detection Using Digital Image Processing

Due to this method, at the time of manufacturing itself we get high quality fabric it implies the
high speed of production.The detection of local fabric defects is one of the most problems in
computer vision.For this problem the solution is that at the time of manufacturing fabric in textile
the faults present on fabric are identified by MATLAB software using some Image Processing
techniques. Image Processing is very helpful because all the techniques applied on the faulty image
is useful to acquire fault free image.
Here we can see some fabric faults---
In this process the camera is used to take the picture from the area of interest. The acquired image
is then proposed to the MATLAB software in which the image is stored for the the image
processing operations such as gray conversion, histogram, histogram equalization, binary
conversion, feature extraction-edge etc.
In the right we can see the process cycle of this method-
By applying this process it is easy to identify faults on
fabric image with high accuracy , less time consuming
and less man power. But this process requires skilled
man power and if power cut occurs the time for system
restart is more because of this the fault detection cannot
be possible.
In this paper MATLAB software was used.In textile industry we can detect the fault though
wirelessly in real image & can be remove the fault by using advanced control system.

 Fabric Fault Detection Using Morphological Operations on Bit Plane

The defects in fabric are generally classified into three subdivisions according to their occurrence
in the fabric. They are, (i) weft-way defects (ii) warp-way defects and (iii) defects with no
directional dependence.
In manual fault detection systems with trained inspectors, very less percentage of the defects are
being detected, and thus insufficient and costly. Therefore, automated visual inspection systems
are a long felt need in the textile industry. The development of an automated web inspection system
requires robust and efficient fabric defect detection techniques. For the detection of fabric defects,
the pre-processed image is decomposed into its bit planes. The lower order bit planes are found to
carry significant information of the location and shape of defects. Then we find the exact location
by means of weighted morphology. Robustness with respect to the changes in parameters of the
algorithm has been examined. The test results obtained exhibit accurate defect detection with low
false alarms,thus showing the effectiveness and robustness of the proposed detection scheme.
A method for defect detection and localization in woven fabric is proposed in this paper based on
bitplane decomposition and weighted morphology. The algorithm is superior to the existing ones
in terms of computational time and accuracy

Diffractive Optics for Fabric Fault Detection

Based on the optical detection of the Fourier power spectrum to reveal and identify defects in
textile structures. The optical set-up analyses the local behavior of the texture, which is converted
in a power spectrum. This system can be easily inserted in an automatic inspection device, which
determines the presence of a defect comparing the actual power spectrum with that of the good
fabric assumed as a reference. The processing of data is rather simple since it is based on the
number and position of peaks in the spectrum.
Harvey L.Kasdan was one of the first researchers
to study diffractive systems, The work of Kasdan
shows that it is possible with an optical Fourier
transform (OFT) to detect the defects. The power
spectrum of the fabric with a defect is different
from that of the good fabric: peaks changes in
intensity, shape and position. The Fig.2 is
obtained by placing in front of a lens

With the use of a proper stop the position of the peaks and on the shape of them, as follows. The
image is converted in an array with a grey tone associated to each pixel. The sum of the grey tone
of pixels belonging to each row is made and curves are obtained as those shown in Fig. 7 and 8.
These curves are one- dimensional signals corresponding to image frames of the fabric. The signal
changes if a defect is displayed in the fabric. In Fig.7, the signal for good fabric (broken line) is
compared with the signal of a defect, that due to a missing yarn. The peaks are closer: the distance
is reduced of 30%.
With the use of the proper stop, we increased the signal of the defect, compared with the signal of
them good fabric. From this curve the distance of the peaks is deduced: a change in this distance
gives information on the nature of the defect appearing in the fabric.

Real Time Automated Fabric Defect Detection System using Microcontroller

In the least developed countries like Bangladesh, most defects arising in the production process of
a textile material are still detected by human inspection.The identification rate is about 70%. In
addition, the effectiveness of visual inspection decreases quickly with fatigue. Digital image
processing techniques have been increasingly applied to textured samples analysis over the last ten
years . Wastage reduction through accurate and early stage detection of defects in fabrics is also
an important aspect of quality improvement. Below chart summarizes the Real Time Automated
Fabric Defect Detection System using Microcontroller.

Conclusion:-
In this assignment, here described four types of topic according to detecting defects of fabrics.
These are summary of four journals with help of some information of other journal. Methods of
these papers are try to describe shortly and we as a textile engineering student can apply this
knowledge in future.
Based Papers:-
 Fabric Fault Detection Using Digital Image Processing
 Automatic Fabric Fault Detection Using Morphological Operations on Bit Plane
 Diffractive Optics for Fabric Fault Detection
 Real Time Automated Fabric Defect Detection System using Microcontroller

References:-

 Kumar, "Computer-Vision-Based Fabric Defect Detection: A Survey," IEEE Trans. Ind.

Electron., vol. 55, no. I, pp. 348-363, Jan. 2008.
 Thilepa R.: A Paper on Automatic Fabrics Fault Processing Using Image Processing
Technique in MATLAB, Signal & Image Processing: An International Journal (SIPIJ), Vol.
1, No. 2, December, 2010, pp. 88 - 99.
 B.Karunamoorthy,Dr.D.Somasundareswari,S.P.Sethu “AUTOMATED PATTERNED
FABRIC FAULT DETECTION USING IMAGE PROCESSING TECHNIQUE
INMATLAB”.International Journal of Advanced Research in Computer Engineering &
Technology (IJARCET) .Volume 4. Issue 1, January 2015
 S. Priya ,T. Ashok kumar and Varghese Paul, "A novel approach to fabric defect detection
using digital image processing," Proc. of iEEE Int . Con! on ICSCCN ,pp228- 232, July
20 1 1.
 R.Haralick, S. Sternberg, and X. Zhuang, "Image analysis using mathematical
morphology", IEEE Trans Pattern Analysis and Machine intelligence. Vol 9, no
4,532,1987.
 K. Srinivasan, P. H. Dastoor, P. Radhakrishnaiah, and S.Jayaraman, "FDAS: A knowledge-
based framework for analysis of defects in woven textile structures", J. Textile inst., pt. I,
vol. 83, no. 3, pp. 43 1-448, 1992
 H. Sari-Sarraf and J.S. Goddard, ”Vision systems for on-loom fabric inspection”, IEEE
Transactions on Industrial Applications, Vol. 35, 1999, pp.1252–1259.
 J.G. Campbell and F. Murtagh, ”Automatic vision inspection of woven textiles using a two-
stage defect detector”, Optìcal. Egnineering, Vol. 37, 1998, pp.2536–2542.
 A. Abouelela, I. Abbas, I. El deeb, and S.Nassar, ”A statistical approach for textile
faultdetection” IEEE Int. Conference on Syst., Man,Cybern, Vol.. 4, Ocotber 2000,
pp.2857–2862.
 M. Ralló, M. S. Millán, J. Escofet, “Wavelet based techniques for textile inspection”, Opt.
Eng. 26(2), 838-844 (2003)
 T. S. Newman and A. K. Jain, “A Survey of Automated Visual Inspection,” Computer
Vision and Image Understanding, vol. 61, 1995, pp. 231–262.
 Ciamberlini C., Francini F., Longobardi G., Sansoni P., Tiribilli, B. "Defect detection in
textured materials by optical filtering with structured detectors and selfadaptable masks",
Opt. Eng. 35(3), 838-844 (1996)