SavedAdd your journal

Journals / Tekstil ve Konfeksiyon / 2026 / Volume: 27 Issue: 2

YARN LOCATION DETECTION IN WOVEN FABRIC IMAGE USING AUTOMATIC MULTISCALE-BASED PEAK DETECTION

OTOMATİK ÇOKLU-ÖLÇEK TEMELLİ TEPE NOKTASI TESPİTİ KULLANARAK DOKUMA KUMAŞ GÖRÜNTÜLERİNDE İPLİK KONUM TESPİTİ

Bekir Yıldırım
Pages
—
Publication Date
2017-06-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The method is tested with real woven fabric images and  experimental results show that AMPD algorithm performs well for detecting yarn locations.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, an approach based on Automatic Multiscale-Based Peak Detection (AMPD) is proposed for detecting yarn locations  in a woven fabric image with skew and noise.
📊
Key Findings & Data:Finding yarn locations in a digital image of woven fabric can be defined as a problem of  local maxima detection in a noisy signal of a periodic or a quasi-periodic signal.
💡
Conclusion & Impact:The method is tested with real woven fabric images and  experimental results show that AMPD algorithm performs well for detecting yarn locations.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Image processing · woven fabric · automatic multiscale-based peak detection (AMPD)

Abstract

In this study, an approach based on Automatic Multiscale-Based Peak Detection (AMPD) is proposed for detecting yarn locations  in a woven fabric image with skew and noise. Finding yarn locations in a digital image of woven fabric can be defined as a problem of  local maxima detection in a noisy signal of a periodic or a quasi-periodic signal. In this approach, projection profiles of woven fabric  images in vertical and horizontal directions are calculated and local peaks are detected by using the AMPD algorithm where local  maxima indicate yarn center positions along the woven fabric width or length. The method is tested with real woven fabric images and  experimental results show that AMPD algorithm performs well for detecting yarn locations. Although the proposed method performs  well on noisy images; detection accuracy is highly affected by the skewness. Therefore, woven fabric images are needed to be enhanced  before obtaining signals.

Özet

Bu çalışmada, iplik konumlarının eğiklik ve gürültü içeren dokuma kumaş görüntülerinde tespiti için otomatik çoklu-ölçek temelli  tepe noktası tespitine dayalı bir yaklaşım önerilmektedir. Dokuma kumaşların sayısal görüntülerinde iplik konumlarının bulunması  gürültü içeren periyodik veya yarı-periyodik sinyallerde yerel maksimum noktaların tespiti problemi olarak tanımlanabilir. Bu  yaklaşımda dokuma kumaş görüntülerinin yatay ve düşey projeksiyon profilleri hesaplanır ve dokuma kumaş eni veya boyunca uzanan  ipliklerin orta konumlarını ifade eden yerel tepeler otomatik çoklu-ölçek temelli tepe noktası tespiti algoritması ile tespit edilir. Metot  gerçek dokuma kumaş görüntüleri ile test edilmiş ve deneysel sonuçlar algoritmanın iplik konumlarının tespiti için iyi sonuçlar verdiğini  göstermiştir. Gürültü içeren görüntülerde iyi sonuçlar vermesine karşın eğikliğin varlığı tespitlerin doğruluğunu oldukça etkilemektedir.  Bundan dolayı dokuma kumaş görüntüleri sinyallerin eldesinden önce düzeltilmelidir.

🔖

Cite This Article

Yıldırım, B. (2017). YARN LOCATION DETECTION IN WOVEN FABRIC IMAGE USING AUTOMATIC MULTISCALE-BASED PEAK DETECTION. Tekstil ve Konfeksiyon, Volume: 27 Issue: 2. https://ajindex.com/articles/1111403

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (16)

  1. Lin, J.J, 2002, “Applying a co-occurrence matrix to automatic inspection of weaving density for woven fabrics", Textile Research Journal, 72(6), p. 486- 490.
  2. Wood, E.J, 1990,“Applying Fourier and associated transforms to pattern characterization in textiles”, Textile Research Journal, 60(4), p. 212-220.
  3. Ravandi, S.A.H, and Toriumi, K, 1995,“Fourier-Transform Analysis of Plain Weave Fabric Appearance”, Textile Research Journal, 65(11), p. 676-683.
  4. Xu, B.G, 1996,”Identifying fabric structures with Fast Fourier Transform techniques”, Textile Research Journal, 66(8), p. 496-506.
  5. Tunak, M, Linka, A, and Volf,P, 2009,“Automatic Assessing and Monitoring of Weaving Density”, Fibers and Polymers, 10(6), p. 830-836.
  6. Jeong, Y.J and Jang J.H, 2005, “Applying image analysis to automatic inspection of fabric density for woven fabrics”, Fibers and Polymers, 6(2), p. 156-161.
  7. Haralick, R.M, Shanmugam, K, and Dinstein, I.H, 1973, “Textural features for image classification”, Systems, Man and Cybernetics, IEEE Transactions,(6), p. 610-621.
  8. Technikova, L, and Tunak, M, 2013, “Weaving Density Evaluation with the Aid of Image Analysis”, Fibres & Textiles in Eastern Europe, 21(2), p. 74-79.
  9. Yildirim, B, 2013, “Determination of Optimum Filter Size for Detecting Yarn Boundaries”, Fibers and Polymers, 14(10), p. 1739-1747.
  10. Scholkmann, F, Boss, J, and Wolf,M, 2012,“An efficient algorithm for automatic peak detection in noisy periodic and quasi-periodic signals”, Algorithms,5(4), p. 588-603.
  11. Release, M, TheMathWorks. Inc., Natick, Massachusetts, United States, 2012.
  12. Pan, R.R, Gao, W, Liu, J, Wang, H, 2010,“Automatic Inspection of Woven Fabric Density of Solid Colour Fabric Density by the Hough Transform”, Fibres& Textiles in Eastern Europe, 18(4), p. 46-51.
  13. Pan, R, Gao, W, and Liu, J, 2009,“Color clustering analysis of yarn-dyed fabric in HSL color space”, IEEE World Congress on Software Engineering, 481.
  14. Jeong, Y, 2008, “Novel Technique to Align Fabric in Image Analysis”. Textile Research Journal, 78(4): p. 304-310.
  15. Yildirim, B, 2014, “Projection profile analysis for skew angle estimation of woven fabric images”, Journal of the Textile Institute, 105(6), p. 654-660.
  16. Bovik, A.C, Handbook of image and video processing, 2010, Academic press.