Equations are not being displayed properly on some articles. We hope to have this fixed soon. Our apologies.

Sparavigna, A. & Marazzato, R. (2016). The GIMP Retinex Filter Used for Detecting Mispicks in Fabrics. PHILICA.COM Article number 640.

ISSN 1751-3030  
Log in  
Register  
  1092 Articles and Observations available | Content last updated 22 June, 18:28  
Philica entries accessed 3 089 862 times  


NEWS: The SOAP Project, in collaboration with CERN, are conducting a survey on open-access publishing. Please take a moment to give them your views

Submit an Article or Observation

We aim to suit all browsers, but recommend Firefox particularly:

The GIMP Retinex Filter Used for Detecting Mispicks in Fabrics

Amelia Carolina Sparavignaunconfirmed user (Department of Applied Science and Technology, Politecnico di Torino)
Roberto Marazzatounconfirmed user (DAUIN, Politecnico di Torino)

Published in compu.philica.com

Abstract
The paper is proposing the use of a Retinex filter (GIMP Retinex) for detecting the mispicks, that is, the filling yarns that have failed to interlace with the warp of fabrics. Because a Retinex filtering is modelled on the mechanisms of human vision, it seems reasonable that it could be used in processing the images to simulate what the trained staff of textile industry is making in the visual inspection of fabrics on off-line stations. Here some examples are given, showing promising good results.
Keywords: image processing, Retinex filtering, GIMP Retinex, texture analysis, fabric fault detection

Article body


 

The GIMP Retinex Filter Used for Detecting Mispicks in Fabrics


A. C. Sparavigna1 and R. Marazzato

1 Department of Applied Science and Technology, Politecnico di Torino, Torino, Italy

2 Visiting Staff at Department of Mathematical Sciences, Politecnico di Torino, Torino, Italy

 

The paper is proposing the use of a Retinex filter (GIMP Retinex) for detecting the mispicks, that is, the filling yarns that have failed to interlace with the warp of fabrics. Because a Retinex filtering is modelled on the mechanisms of human vision, it seems reasonable that it could be used in processing the images to simulate what the trained staff of textile industry is making in the visual inspection of fabrics on off-line stations. Here some examples are given, showing promising good results. 

Keywords:  image processing, Retinex filtering, GIMP Retinex, texture analysis, fabric fault detection

 

In some previous papers, we have discussed the use of Retinex filtering, applying it to microscopy, radiography and detection of vehicles in foggy images [1-6]. Here we propose it for the detection of faults in fabrics, in particular for the detection of mispicks, which are defects concerning the filling yarns that have failed to interlace with the warp of the fabric. To the authors’ best knowledge, a Retinex filtering for detecting the fabric faults has not yet been proposed and experimented.

Of the Retinex filtering, we discussed in [6], and then let us just remember the following. Retinex filtering methods had been developed to simulate the mechanisms of human vision, which allow an observer seeing details both in the shadows and in the nearby illuminated areas of a given scene, whereas images of the same scene recorded by a digital device, are usually showing either the shadows as too dark or the bright areas as overexposed [7]. Then, the Retinex algorithms have been developed to act on the recorded images for rendering the scene like that viewed by human eye. 

Because a Retinex filtering is modelled on the mechanism of human vision, it seems reasonable that it could be used in processing the digital images to simulate what the trained staff of textile industry is making in the visual inspection of the fabrics on off-line stations.

The visual inspection of woven fabrics, made by people trained for this specific task, is fundamental for textile producers to guarantee the quality of their products as being free from defects. Sometimes, the human inspection is supported by some automatic methods for detecting defects, which are working during the production processes, that is, directly on the looms. As remarked in [8], the automation of visual inspection is  requiring some “complex interaction among various system components”, and then investments for the development of a final system, which could be commercialized. About twenty years ago, such an investment was considered as economically attractive [3], so that some industrial inspection systems had been developed (I-TEX from Elbit Vision Systems, Barco Vision's Cyclops, Zellweger Uster's Fabriscan) [9]. In spite of the presence of such commercial systems, the research for further improvements of textile fault detection continues, as shown by the recent publications on this subject, such as [10-15].

From the first researches for the development of an automatic system based on artificial vision for textile faults detection, it was clear that several difficulties existed for such task. The difficulties were linked to the fact that the fabric faults are often very small and hardly detectable, having a visibility strongly dependent on illumination (front or back lighting) and reduced by the vibrations of the mounting devices [16-20]. It was therefore necessary a suitable illumination for recording good images that could be further analyzed to provide some proper results. For the analyses, approaches based on statistical methods, Fourier analysis of the grey levels of images, Gabor filtering and wavelets with adaptive bases had been used [21-25]. In addition, an approach based on an image processing, developed for the study of liquid crystals [26], had been proposed by one of the authors too [28-29].

As previously told, we are here proposing the use of Retinex filtering. Several Retinex approaches exist [30-37], developed after the models created by Edwin Lang, who first studied the mechanisms of human vision and simulated them. We could use single-scale Retinex (SSR), the multiscale Retinex (MSR), or, for colour images, the MultiScale Retinex with Colour Restoration (MSRCR). Among MSRCR we find the GIMP Retinex, a freely available tool developed by Fabien Pelisson [38] (GIMP is the GNU image processing software). Here, we will use this Retinex.

The resulting image of the GIMP Retinex can be adjusted selecting different levels, scales and dynamics. There are three “levels”:  uniform, which tends to treat both low and high intensity areas fairly, low, that “flares up” the lower intensity areas on the image, and high that tends to “bury” the lower intensity areas in favor of a better rendering of the clearer areas of the image. The “scale” determines the depth of the Retinex scale. Minimum value is 16, a value providing gross, unrefined filtering. Maximum value is 250. Optimal and default value is 240. A “scale division” determines the number of iterations in the multiscale Retinex filter. The minimum required, and the recommended value is three. The “dynamic” slider allows adjusting colour saturation contamination around the new average colour (default value is 1,2).

Let us process images of mispicks in fabrics. We choose these defects because, as it will be evident from the discussion, are those which are potentially giving the best results. For them, GIMP Retinex could help improving the score of successful detections.

Mispicks are faults in the structure of woven fabrics, which are deviations from the recurrence of a fundamental unit, and usually appearing as subtle lines, bright or dark, in the image frame. Among these defects, the more frequently encountered are broken or missing picks. Let us consider the Figure 1. The image is showing the defect produced when a yarn is lacking or broken on the loom; it is a defect expanding along the length of the fabric, involving several neighbor yarns.  Mispicks are easy to find by eye inspection with backlighting illumination. This illumination system was used to record the image in the Figure 1.

 

 

Figure 1: A mispick in a textile woven fabric. Image size is 40 mm.

 

We use the GIMP Retinex filter with the following parameters: scale = 150, scale division = 4 and dynamic slider = 0. The result for the image in Fig.1 is given in the Figure 2 for the three levels: uniform, low and high.

 

 

Figure 2: On the left the original image. The other images are those obtained using GIMP Retinex, for Uniform, Low and High levels.

 

It is evident the selective action of the filtering, so the three outputs are enhancing different features of the fabric. In particular, the low level (L) filtering seems suppressing the fault, whereas the high level (H) filtering enhances its visibility. In fact, we have two images to compare, L and H.  L could represent the fabric as it would be “without defect”, and H the “defect”. Using these images, we can try a further analysis comparing them. Let us consider image L in the Figure 2 and invert its colour tones with GIMP, having in this manner the panel L-I in the Figure 3. We can add this image, to image H. The result is an almost homogenous grey image, having the position of the defect evidenced in the bright region. By thresholding the low-right panel of Figure 3, we have the result given in the Figure 4.

 

 

Figure 3: Let us use image L in the Figure 2; we can invert the colour tones with GIMP, having the panel L-I.  We can add this image to image H. The result is the almost homogenous grey image, having the position of the defect evidenced by the bright region (low-right panel). The grey areas are those where the two images are coincident.

 

Figure 4: The image is showing the effect of a suitable thresholding on the result obtained in the Figure 3.

 

After the Figure 4, it is easy to imagine a segmentation of the result given in Fig.3, a segmentation which is able evidencing the position of the defect for any automatic inspection. Let us given another example of missing pick (Figure 5 on the left). In the same image, we can see the result of Retinex filtering. Again, using the same addition of images as in the Figures 3, we can obtain the results given in the Figure 6.

 

 

Figure 5: On the left an image showing a missing pick (image size is of 20mm). The other images are those obtained using GIMP Retinex, for Uniform, Low and High levels. Note that the low level filtering is reducing the effect of the missing pick, whereas the high level filtering is enhancing it.

 

 

Figure 6: Adding the High level filtered image of the Figure 5 to the inverse of the Low level filtered image of Figure 5, we obtain the image here given in the left panel. In the middle panel, we can see the result given with a reduced number of grey tones. On the right, the result after a suitable threshold.

 

In these examples, we have considered an image of a certain fabric. From it, using the Retinex filter, we have obtained two images. One (L), which is obtained after selecting the low level filtering, is that where the lower intensity areas are evidenced. The other image, obtained using the high level (H), has the clearer areas favored. Let us note that, in the given examples, we have used a back lighting illumination system for inspecting the fabric. In them, we have seen a fault as a region that is transmitting more light. Therefore, L is close to the “good” fabric, and H is close to the “bad” fabric, because enhancing the defect, which is transmitting light. Therefore, we can tell that, from a single recorded image of the fabric, we can have at least two filtered images that we can compare to determine the presence of a defect. 

Some other studies are necessary to improve this approach based on Retinex filtering, when we have defects rather difficult to identify, such as the presence of tiny flaws or doublepicks. Unlike mispicks, the doublepicks, which appear when two yarns are very close, produce very narrow lines in the fabric. Some preliminary analyses of Retinex filtering seem quite promising.

Let us conclude the paper with an example of a simple use of GIMP Retinex. In the previous cases, we have proposed this filter for preprocessing the images to be used in an automatic vision system. However, Retinex could be used just to help human vision, for instance, in detecting tiny flaws of the fabric.  A simulation is given in the Figure 7. In the upper panel, we have the fabric as it could be seen during inspection; defects are hardly visible. However, a simple filtering with GIMP Retinex gives us the presence of defects (lower panels). Then, a device providing such filtered images could be used to improve the visual inspection on the off-line stations.

 

 

Figure 7: In the upper panels, the simulation of a good fabric (left) and the same with defects (middle, right). A simple Retinex filtering is evidencing the as given by the lower panels. 

 

References

[1] Sparavigna, A. C. (2015). GIMP Retinex for enhancing images from microscopes. International Journal of Sciences, 4(6), 72-79.

[2] Sparavigna, A. C., & Marazzato, R. (2015). Effects of GIMP Retinex Filtering Evaluated by the Image Entropy. arXiv preprint arXiv:1512.05653.

[3] Marazzato, R., & Sparavigna, A. C. (2015). Retinex filtering of foggy images: generation of a bulk set with selection and ranking. arXiv preprint arXiv:1509.08715.

[4] Sparavigna, A. C., & Marazzato, R. (2016). Evaluation of GIMP Retinex Filtering of Images by Means of the Shen++ Max Shannon Entropy Finder.

[5] Sparavigna, A. C. (2015). An image processing approach based on Gnu Image Manipulation Program GIMP to the panoramic radiography. International Journal of Sciences, 4(5), 57-67.

[6] Sparavigna, A. (2015). Retinex filtering and thresholding of foggy images. PHILICA.COM Article number 511.

[7] Barnard, K., & Funt, B. (1999). Investigations into multi-scale Retinex, in Colour Imaging: Vision and Technology, L. MacDonald, Ed. and M. Ronnier Luo. Ed., John Wiley and Sons, pp. 9-17. ISBN: 978-0-471-98531-0

[8] Kumar, A. (2008). Computer-Vision-Based Fabric Defect Detection: A Survey, IEEE Transactions on Industrial Electronics, 55(1), 348-363. DOI: 10.1109/TIE.1930.896476

[9] Dockery, A. (2001). Automated fabric inspection: assessing the current state of the art. Techexchange. com.

[10] Jing, J.,  Zhang, H. ,  Wang, J.,  Li, P., &  Jia, J. (2013). Fabric defect detection using Gabor filters and defect classification based on LBP and Tamura method. Journal of the Textile Institute, 104(1), 18-27.

[11] Schneider, D., Holtermann, T., & Merhof, D. (2014). A traverse inspection system for high precision visual on-loom fabric defect detection. Machine vision and applications, 25(6), 1585-1599.

[12] Bhangale, R. S., & Zope, C. D. (2014). An Introduction to Textile Defect Identification and Classification Using Wavelet Transform and Neural Networks. International Journal of Advanced Electronics and Communication Systems.

[13] Li, P., Zhao, Z., Zhang, L., Zhang, H., & Jing, J. (2015). The Real-Time Vision System for Fabric Defect Detection with Combined Approach. In International Conference on Image and Graphics (pp. 460-473). Springer International Publishing.

[14] Huang, C. P. (2014). A Study on the Algorithm of Fault Information Automatic Detection for High-Precision Intelligent Instruments. In Advanced Materials Research, 846, 167-171. Trans Tech Publications.

[15] Jinlian Hu (2011). Computer Technology for Textiles and Apparel,  Elsevier.

[16] Sari-Sarraf, H., & Goddard, J. S. (1999). Vision systems for on-loom fabric inspection, IEEE Trans. Industry applications, 35, 1252-1259.

[17] Campbell, J. G., & Murtagh, F. (1998).  Automatic vision inspection of woven textiles using a two-stage defect detector, Opt. Eng. 37, 2536-2542.

[18] Yau, H. F.,  Chen, P. W., Wang, N. C., & Lay, Y. L. (1998). Optimization of the illumination beam size of an optical textile defect inspection system, Meas. Sci. Technol. 9, 960-966.

[19]  Ribolzi, S., Merckle, J., & Gresser, J. (1993).  Real time fault detection on textiles using opto-electronic processing, Textile Res. J. 63, 61-71.

[20] Kasdan, H. L. (1979). Industrial application of diffraction pattern sampling, Opt. Eng. 18, 496-503.

[21] Abouelela, A., Abbas, I., El Deeb, I., & Nassar, S. (2000). A statistical approach for textile fault detection, IEEE International Conference on Systems, Man, and Cybernetics, 8-11 Oct. 2000,  4, 2857-2862.

[22] Chan, C. H., & Pang,  G. (2002). Fabric defect detection by Fourier analysis, IEEE Transactions on Industry Applications, 36, 1267-1276 (2002).

[23] Arivazhagan, S., Ganesan, L., & Bama, S. (2006). Fault segmentation in fabric images using Gabor wavelet transform. Machine Vision and Applications, 16(6), 356-363.

[24] Kumar, A., & Pang, G. K. H. (2002). Defect detection in textured materials using Gabor filters, Industry Applications, IEEE Transactions on Industry Applications, 38, 425-440.

[25] Jasper, J. W., Garnier, S. J. & Potlapalli, H. (1996). Texture characterization and defect detection using adaptive wavelets,  Opt. Eng., 35, 3140-3149.

[26] Montrucchio, B., Sparavigna, A., & Strigazzi, A. (1998). A new image processing method for enhancing the detection sensitivity of smooth transitions in liquid crystals, Liq. Cryst., 24, 841-852.

[27] Sparavigna, A. C., & Montrucchio, B. (2006). Performing Textile Fault Detection by Means of Texture Analysis. WSEAS TRANSACTIONS ON SIGNAL PROCESSING, 2, 541-548.

[28] Sparavigna, A., & Montrucchio, B. (2006, April). Texture analysis for textile fault detection. In Proceedings of the 5th WSEAS international conference on Applied computer science (pp. 861-866). World Scientific and Engineering Academy and Society (WSEAS).

[29] Sparavigna A., Dorma, G. &  Montrucchio, B. (2006). Diffractive optics for fabric fault detection,          pp. 82-88, Vol. 5, SCI2006 - X World Multi-Conference on Systemics, Cybernetics and Informatics, Orlando, Florida, July 16-19.

[30] Zhixi Bian, & Yan Zhang (2002). Retinex image enhancement techniques: Algorithm, application and advantages, EE264 final project report for Image Processing and Reconstruction.

[31] Jobson, D.J., Rahman, Z., & Woodell, G.A. (1997). A Multi-Scale Retinex for bridging the gap between colour images and the human observation of scenes, IEEE Transactions on Image Processing 6(7):965-976. DOI: 10.1109/83.597272

[32] Land, E.H. (1986). An alternative technique for the computation of the designator in the Retinex theory of color vision, Proc. Nat. Acad, Sci. 83:3078-3080. PMCID: PMC323455

[33] Land, E.H. (1983). Recent advances in Retinex theory and some implications for cortical computations, Proc. Nat. Acad. Sci. 80:5163-5169. PMCID: PMC384211

[34] Land, E. H. (1986). Recent advances in Retinex theory, Vis. Res. 26:7-21. DOI: 10.1016/0042-6989(86)90067-2

[35] Land, E. H. (1959). Experiments in color vision, Scientific American, May Issue, 285-298.

[36] Land, E. H. (1959). Color vision and the natural image, Proc. of the National Academy of Sciences 45(1):115–129. PMCID: PMC222521

[37] Jobson, J., Rahman, Z., & Woodell, G.A. (1997). Properties and performance of a center/surround Retinex, Image Processing IEEE Transactions on 6(3):451-462. DOI: 10.1109/83.557356

[38] Fabien Pelisson, GIMP Retinex,  http://www-prima.inrialpes.fr/pelisson/MSRCR.php




Information about this Article
This Article has not yet been peer-reviewed
This Article was published on 22nd July, 2016 at 11:28:13 and has been viewed 842 times.

Creative Commons License
This work is licensed under a Creative Commons Attribution 2.5 License.
The full citation for this Article is:
Sparavigna, A. & Marazzato, R. (2016). The GIMP Retinex Filter Used for Detecting Mispicks in Fabrics. PHILICA.COM Article number 640.


<< Go back Review this ArticlePrinter-friendlyReport this Article



Website copyright © 2006-07 Philica; authors retain the rights to their work under this Creative Commons License and reviews are copyleft under the GNU free documentation license.
Using this site indicates acceptance of our Terms and Conditions.

This page was generated in 0.2349 seconds.