Fabric Fault Detection Using Image Processing Matlab
Volumn 2

Fabric Fault Detection Using Image Processing Matlab

Prasad Dakhole1, Shruti kalode2, Ankit Patel3

Dept.of Electronics Engineering

Tulsiramji Gaikwad Patil College of Engineering & Technology,

Nagpur, India


Detection of location of Fabric fault using digital image processing. Fabric defect detection has been carried out manually with visual inspection for a long time. In the manual fault detection system very less percentage of the defects are been detected while a real time automatic system can increase this to a maximum number. Fabric analysis is performed on the basis of digital images of the fabric. The recognizer acquires digital fabric images by image acquisition device and converts the image into binary image by restoration and threshold techniques. To upgrade this process the fabrics when processed in textiles the fault present on the fabrics can be identified using feature extraction techniques with MATALB. This image processing technique is done using MATLAB. This research thus implements a textile defect detector with system vision methodology in image processing.

Keywords: Histogram, Thresholding, graph based segmentation, feature extraction.


The city Tirupur in Tamilnadu consists of at present 3000 sewing units, 450 knitting units and 100s of dyeing units at present for fabrics processing. These units involve both manual and automation for all processes. The annual income for the past year 2008 stands at Rs.8000 crore.This city is also named as Manchester of South India [12]. Since the city yields a major income on textiles and fabrics, it is given more importance to this field here.In this paper a fabric faulty part is taken for analysis from textiles. For this process we have used Matlab 7.3 in image processing software. Here we can analyze all faults present on fabrics such as hole, scratch, dirt spot, fly, crack point, color bleeding etc… automatically. Several authors have considered defect detection on textile materials.Kang et al. [16], [17] analyzed fabric samples from the images obtained from transmission and reflection of light to determine its interlacing pattern. In addition if the faults are to be identified manually the time consumption is more comparatively less and the percentage of fault identification is deduced to a lower rate. Also it has been observed that the price of textile fabric is reduced by 45% to 65% due to defects[13] . Machine vision automated
Inspection system for textile defects has been in the research industry for longtime [14], [15]. Recognition of patterns independent of position, size, brightness and orientation in the visual field has been the goal of much recent work. Hence the efficiency is also reduced in this process. To overcome all these drawbacks this automation process can be implemented.

Indian textile and clothing exports to US is lowest in Nov 2009:

The above table [11] shows the details of income to India by the textile field. Hence if this automaton process of fault identification process using Matlab is implemented we can deduce the fault in a major way.

Growth Rate of Manufacturing and Textile sector in India:

The above tables [11] are the reports produced by FICCI (Fiber Consumption of Indian Society).There by automation using Matlab in image processing we can increase the manufacturing %ge in an enormous way efficiently. In our paper a defective fabric image is taken and noise filtering is done at the initial stage. Then the output filtered image is converted into gray scale image. Now the gray scale image is processed for histogram process and finally Thresholding is done using Matlab 7.3 software.

An image may be defined as a two –dimensional function, f(x, y), where x and y are spatial (plane) coordinates, and the amplitude of f at any pair coordinates (x, y) is called the intensity or gray level of the image at that point. [1].When x, y, and the amplitude values of all finite, discrete quantities; we call the image as a digital image. The Image Processing technique is a collection of functions that extend the capability of the MATLAB in numeric computing environment.

The toolbox supports a wide range of image processing operations, including: open image file, add noise of a given type (e.g. salt &pepper, Gaussian, Speckles…) to intensity image, 2-D median filtering and adaptive filtering, Image analysis and enhancement, Color Image decomposition into RGB Channels, Image histogram, Image segmentation, image Multithresholding,, image movie , signal plotting and etc… , Many of the toolbox functions are MATLAB M-files, Model files and a series of MATLAB statements that implement specialized image processing algorithms. Then Histogram is done for the image and finally thresholding is done for the same image using this image processing toolbox.


The digital analysis of two-dimensional images of fabric is based on processing the image acquirement, with the use of a computer. The image is described by a two-dimensional matrix of real or imaginary numbers presented by a definite number of bytes. The system of digital image processing may be presented schematically as shown in Figure below

The method used in this paper is processed using MATLAB with image processing toolbox. The toolbox supports a wide range of image processing operations, including: open image file, add noise to intensity image, 2-D median filtering and adaptive filtering, Image analysis and enhancement, Color Image decomposition into RGB Channels, Image histogram, Image segmentation, signal plotting and etc.The given Algorithm shows the general flow of the Various Modules of Matlab Software:Textile fabric surface image is acquired by using a CCD camera from top of the surface from a distance adjusted so as to get the best possible view of the surface.

A. Image acquisition: Acquire Input color fabric image to the MATLAB in image processing system. The image formats are .tif, .Jpeg, and .png. In this paper we used color images (RGB images) and separated into their components (Red, Green, and Blue).

B. Contrast Enhancement: The Image Processing Toolbox contains several image enhancement routines.

  • Step 1: Load Images

Read an images: fabric.jpg and detect.jpg.

  • Step 2: Resize Images

To make the image comparison easier, resize the images to have the same width & hight.

  • Step 3: Enhance Grayscale Images

Histogram Equalization is Applied to Enhance the Contrast of Fabric Surface.

Histogram Equalization:

  • Histogram is a representation of the distribution of color in an image and it represents the number of pixels that have colors in each of a fixed list of color ranges.
  • Histogram equalization is a method for stretching the contrast by uniformly distribution the gray values enhances the quality of an image.
  • It enhances the contrast of images by transforming the values in an intensity image.

The contrast enhancement can be limited in order to avoid amplifying the noise which might be present in the image.

C. Noise Removal: Whenever an image is converted from one form to another many types of noise can be present in the image. Noise is random variation of brightness or color information in images. The Wiener filtering method is used to filter the noise present in the image.Wiener2 low pass filters an intensity image that has been degraded by constant power additive noise .It uses pixel wise adaptive method based on statistics estimated from a local neighborhood of each pixel.

D. Image segmentation: Image segmentation is the process of partitioning a digital image into multiple segments. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. The result of image segmentation is a set of segments that collectively cover the entire image, or a set of contours extracted from the image ( edge detection). Each of the pixels in a region are similar with respect to some characteristic or computed property, such as color, intensity or texture.

E. As binary images are easy to operate, other storage format images are often converted into binary images are used for enhancement or edge detection. All images can be neatly segmented into foreground and background using simple thresholding. The purpose of thresholding is to extract those pixels from some image which represent an object (such as graphs, maps). This way can be determined by looking at an intensity histogram of the image.

Thresholding are two types:

  • Global Thresholding
  • Local Thresholding

A. Graph based segmentation :The next step is to use the regions extracted by preprocessing and to extract segments that correspond to the defects. The general concept of graph based methods and measures the evidence of a boundary between two regions by computing :

 (a) Intensity differences across the boundary and

 (b) Intensity differences between neighboring pixels within each region.

This is mainly due to the use of the local thresholding method that performs well even when there is no uniform background in the images. The graph based segmentation returned each of the detected objects as a different segment colored randomly. The detected segments outside the image and the ones with an area greater or smaller than a minimum (50 pixels) and maximum area (3500 pixels), correspondingly.

F. Feature extraction: When the input data to an algorithm is too large to be processed and it is suspected to be notoriously redundant then the input data will be transformed into a reduced representation set of features (also named features vector). Transforming the input data into the set of features is called feature extraction. Feature extraction has two major point for extraction:

  • Feature Selection
  • Feature Definition

Feature Definition: Several types of features are used , the simplest are the geometric features ,intensity features & moment based feature. The users use both geometrical and intensity based attributes to evaluate a segment in fabric images. Geometric features, like form factor, rectangularity factor, location and orientation are used. Intensity features, that are commonly used to find average and the standard deviation of the intensity values. Moment-based features, which provide information about shape and intensity at the same time.

Feature selection: Feature requires a lot of computational power especially the texture based ones.   Feature provide the useful information and reject the rest. Feature section refers to a method that selects a subset of original feature based on a evaluation orientation. Feature extraction is general term for method of constructing get combination of the variable to around this problem while still describing the data with sufficient accuracy.



The fabric defect detection in the normal fabrics defines the faults by this feature extraction method. Fabrics using both geometric and texture features to capture the visual properties. One of the most important advantage of the methods that, it is multipurpose without requiring any adjustment. For given method allows finding the better accuracy and consuming the time in Industry. Here, it has been demonstrated that Textile Defect Recognition System is capable of  detecting  fabrics’ defects with  more  accuracy and  efficiency Thereby  applying  Matlab 7.3  version  to  the  color  faulty  fabrics  it  is  processed and finally the histogram is obtained for the same image and thresholding is done to obtain the intensity of the image. In future this can be exteded to any number of fault identifications on fabrics and processed


In future this work may be extended such that the output is given to neural network and the Microcontrollers of any type can be utilized and programmed such that it can detect the faulty fabric part. If the microcontroller is connected with motors of any type then it will be operated under normal fabric condition and can stop the motor if there is any fault on fabrics


  1. R. C. Gonzalez, R. E. Woods, S. L. Eddins, “Digital Image Processing using MATLAB”, ISBN 81-297-0515-X, 2005, pp. 76-104,142-166
  2. http:// en.wikipedia.org/wiki/Tirupur
  3. Kenneth R. Castelman, Digital image processing, Tsinghua Univ Press, 2003.
  4. I.Pitas, Digital Image Processing Algorithm and Applications. John Wiley &Sons, Inc.2002.
  5. Navneet Kaur, Mandeep Dalal “Application of Machine Vision Techniques in Textile (Fabric) Quality Analysis” IOSR Journal of Engineering Apr. 2012, Vol. 2(4) pp: 582-584.
  6. S. Priya, T. Ashok Kumar, Dr. Paul Varghese “A Novel Approach to Fabric Defect Detection Using Digital Image Processing” Proceedings of International Conference onSignal Processing, Communication, Computing and Networking Technologies (ICSCCN 2011),2011.
  7. C.Chan and G. K. H Pang., “Fabric defect detection by Fourier analysis”, IEEE Trans. on Ind. Appl, vol 36, no.5, ppI267-1276 Oct 2000.
  8. Wood E. J., “Applying Fourier and associated transforms to patterncharacterization in textiles,” Textile Res. J., vol. 60, pp. 212-220, 1990

Related posts

Implementation Of a Softcore Reconfigurable Embedded Processor For Performance Monitoring


Agricultural Marketing and Economic Development in India


Location Aware Personalized Assistance


Leave a Comment