Machine Vision and Applications

, Volume 24, Issue 8, pp 1661–1683 | Cite as

A machine vision system to estimate cotton fiber maturity from longitudinal view using a transfer learning approach

  • Muneem Shahriar
  • Ian Scott-Fleming
  • Hamed Sari-Sarraf
  • Eric Hequet
Original Paper


This paper describes a proposed machine vision system developed to acquire longitudinal images of complete cotton fibers and then estimate their average maturity using image and pattern analysis. Maturity is important to the cotton industry because it relates to fiber’s propensity to break when submitted to mechanical stress and it influences the quality of the goods produced from it (yarns and fabrics). The proposed system is novel because it estimates maturity indirectly from fibers’ longitudinal views using auxiliary training data generated from fibers’ cross-sectional views. It uses the transfer learning framework to reconcile the distribution differences between the two views before traditional machine learning algorithms are applied to learn a suitable model for cotton fiber maturity imaged longitudinally. In addition, the proposed system is more descriptive than commercially available systems currently used in the cotton industry because it estimates not only the average maturity of a complete cotton fiber, but also the maturity variations along the fiber from end to end. Validation studies performed show that the transfer learning approach is a practical and promising way to train our system.


Cotton maturity estimation Transfer learning Feature-based domain adaptation 



This work is supported by a grant from Cotton Incorporated. We also thank the students Devashish Deshpande and Bosco DeSouza for their assistance in imaging cotton fibers using the proposed system.


  1. 1.
    Wang, H., Mao, C., Sari-Sarraf, H., Hequet, E.F.: Accurate length measurement of multiple cotton fibers. J. Electron. Imaging 17(3), 031110 (2008)Google Scholar
  2. 2.
    Shahriar, M.: Machine Vision System for Quantification of Cotton Fiber Length and Maturity. Texas Tech University, Lubbock (2008)Google Scholar
  3. 3.
    Hequet, E., Wyatt, B., Abidi, N., Thibodeaux, D.P.: Creation of a set of reference material for cotton fiber maturity measurements. Text. Res. J. 76(7), 576–586 (2006)CrossRefGoogle Scholar
  4. 4.
    AATCC-20A-Section-14: AATCC 20A-2008 Fiber Analysis: Quantitative. American Association of Textile Chemists and Colorists Research, Triangle Park (2008)Google Scholar
  5. 5.
    Xu, B., Huang, Y.: Image analysis for cotton fibers, part II: cross sectional measurements. Text. Res. J. 74, 409–416 (2004)CrossRefGoogle Scholar
  6. 6.
    Frydrych, I., Raczynska, M., Cekus, Z.: Measurement of cotton fineness and maturity by different methods. Fibres Text. East. Eur. 18(6), 54–59 (2010)Google Scholar
  7. 7.
    Long, R.L., Bange, M.P., Gordon, S.G., Constable, G.A.: Measuring the maturity of developing cotton fibers using an automated polarized light microscopy technique. Text. Res. J. 80(5), 463–471 (2010)CrossRefGoogle Scholar
  8. 8.
    Schwarz, E.R., Hotte, G.H.: Micro-determination of cotton fiber maturity in polarized light. Text. Res. J. 5(8), 370–376 (1935)CrossRefGoogle Scholar
  9. 9.
    ASTM-D1442: D1442–00 (2000): Standard test method for maturity of cotton fibers (sodium hydroxide swelling and polarized light procedures). In: American Society for Testing and Materials Designation, pp. 354–359 (2000)Google Scholar
  10. 10.
    Rodgers, J., Delhom, C., Fortier, C., Thibodeaux, D.: Rapid measurement of cotton fiber maturity and fineness by image analysis-microscopy using the Cottonscope\(^{\textregistered }\) . Text. Res. J. 82(3), 259–271 (2012)Google Scholar
  11. 11.
    Abbot, A.M., Hequet, E., Higgerson, G., Lucas, S., Naylor, G., Purmalis, M., Thibodeaux, D.: Performance of the CottonscanTM instrument for measuring the average fiber linear density (fineness) of cotton lint samples. Text. Res. J. 81(1), 94–100 (2010)CrossRefGoogle Scholar
  12. 12.
    Abbot, A.M., Higgerson, G., Lucas, S., Naylor, G.: An upgraded CottonscanTM instrument for measuring the average fiber linear density (fineness) of cotton lint samples. Text. Res. J. 81(7), 683–689 (2011)CrossRefGoogle Scholar
  13. 13.
    Lord, E.: Airflow through plugs of textile fibers. Part 2—the micronaire test. J. Text. Inst. 47, T16–T30 (1956)Google Scholar
  14. 14.
    Zhang, Z., Su, Y., Lu, C.: A novel method to assess cotton fiber qualities based on Fraunhofer diffraction. Paper presented at the 2nd International Asia Conference on Informatics in Control, Automation and RoboticsGoogle Scholar
  15. 15.
    Adedoyin, A.A., Li, C., Toews, M.D.: Characterization of single cotton fibers using a laser diffraction system. Text. Res. J. 81(4), 355–367 (2010)CrossRefGoogle Scholar
  16. 16.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  17. 17.
    Zhong, E., Fan, W., Peng, J., Zhang, K., Ren, J., Turaga, D., Verscheure, O.: Cross domain distribution adaptation via kernel mapping. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1027–1036. ACM, New York (2009)Google Scholar
  18. 18.
    Shahriar, M., Scott-Fleming, I., Sari-Sarraf, H., Hequet, E.F.: Training a new cotton imaging system via a transfer learning approach. Paper Presented at the The International Conference on Image Processing, Computer Vision, and Pattern Recognition, Las VegasGoogle Scholar
  19. 19.
    Shahriar, M., Sari-Sarraf, H., Hequet, E.: Feature-based transfer learning to train a novel cotton imaging system. Paper Presented at the IEEE SSIAI, Sante Fe, New MexicoGoogle Scholar
  20. 20.
    Huang, Y., Xu, B.: Image analysis for cotton fibers, part I: longitudinal measurements. Text. Res. J. 72, 713–720 (2002)CrossRefGoogle Scholar
  21. 21.
    Thibodeaux, D., Evans, J.: Cotton fiber maturity by image analysis. Text. Res. J. 56, 130–139 (1986)CrossRefGoogle Scholar
  22. 22.
    Duckett, K., Cheng, C.C.: The detection of cotton fiber convolutions by the reflections of light. Text. Res. J. 42, 263–268 (1972)CrossRefGoogle Scholar
  23. 23.
    Han, Y., Cho, Y.J., Lambert, W., Bragg, C.: Identification and measurement of convolutions in cotton fibers using image analysis. Artif. Intell. Rev. 12, 201–211 (1998)CrossRefGoogle Scholar
  24. 24.
    Morlier, O.W., Orr, R.S., Grant, J.N.: The relation of length to other physical properties of cotton fibers. Text. Res. J. 21, 6–13 (1951)CrossRefGoogle Scholar
  25. 25.
    Pillay, K.P.R., Shankaranarayana, K.S.: Variation in the properties of cotton fibers with length. Text. Res. J. 31, 515–524 (1961)CrossRefGoogle Scholar
  26. 26.
    Fiori, L.A., Louis, G.L., Sands, J.E.: Blending cottons differing widely in maturity: part I: effect on properties of single yarns. Text. Res. J. 29, 706–716 (1959)Google Scholar
  27. 27.
    Sands, J.E., Louis, G.L., Tallant, J.D.: Linear densities of fibers in selected length groups of 42 domestic and foreign cottons. Text. Res. J. 30, 619–620 (1960)CrossRefGoogle Scholar
  28. 28.
    Haralick, R.M.: Statistical and structural approaches to texture. Proc. IEEE 67(5), 786–804 (1979)CrossRefGoogle Scholar
  29. 29.
    Otsu, N.: A threshold selection method from gray-level histograms. Paper presented at the IEEE transactions on systems, man, and cyberneticsGoogle Scholar
  30. 30.
    Gonzalez, R.C., Woods, R.E., Eddins, S.L.: Digital Image Processing Using MATLAB. Pearson Prentice Hall, New Jersey (2004)Google Scholar
  31. 31.
    Breunig, M.M., Kriegel, H.-P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. SIGMOD Rec. 29(2), 93–104 (2000). doi: 10.1145/335191.335388 CrossRefGoogle Scholar
  32. 32.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, New York (2001)zbMATHGoogle Scholar
  33. 33.
    Baudat, G., Anouar, F.: Generalized discriminant analysis using a kernel approach. Neural Comput. 12(10), 2385–2404 (2000)CrossRefGoogle Scholar
  34. 34.
    Mika, S., Ratsch, G., Weston, J., Scholkopf, B., Muller, K.-R.: Fisher discriminant analysis with kernels. Neural Netw. Signal Process. IX, 41–48 (1999)Google Scholar
  35. 35.
    Perez-Cruz, F.: Kullback–Leibler divergence estimation of continuous distributions. In: IEEE International Symposium on Information Theory, pp. 1666–1670. ISIT 2008, 6–11 July 2008 (2008)Google Scholar
  36. 36.
    Kirkpatrick, S., Jr., C.D.G., Vecchi, M.P.: Optimization by Simulated Annealing. Science 220, 671–680 (1983)Google Scholar
  37. 37.
    Yang, X.S.: Engineering Optimization: An Introduction with Metaheuristic Applications. Wiley, New York (2010)Google Scholar
  38. 38.
    Fox, J.: Multiple and generalized nonparametric regression. In: Sage University Papers Series on Quantitative Applications in the Social Sciences, Thousand Oaks (2000)Google Scholar
  39. 39.
    Kutner, M.H.: Applied Linear Statistical Models, 5th edn. McGraw-Hill, Irwin (2004)Google Scholar
  40. 40.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981). doi: 10.1145/358669.358692

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Muneem Shahriar
    • 1
  • Ian Scott-Fleming
    • 2
  • Hamed Sari-Sarraf
    • 3
  • Eric Hequet
    • 4
  1. 1.Department of Electrical and Computer EngineeringTexas Tech UniversityLubbockUSA
  2. 2.Department of Computer ScienceTexas Tech UniversityLubbockUSA
  3. 3.Department of Electrical and Computer EngineeringTexas Tech UniversityLubbockUSA
  4. 4.Fiber and Biopolymer Research InstituteLubbockUSA

Personalised recommendations