本研究旨在開發一客製化應用程式，以數位影像處理技術達到減少分析八種不同形狀之Nylon 6,6異形纖維橫截面之光學顯微鏡影像做數量及形狀因子分析時的人為介入。我們使用了數學形態學、二值化、空間域遮罩運算、邊緣偵測、霍夫轉換與簽名法等影像處理方法，將影像中的纖維分離並以數值分析方法計算纖維的幾何性質。最後成功為紡織工業的品質管理量測客觀的數據、減少人力並提升效率使得製造流程更為自動化，最後本研究之量測結果透過與人工量測之數值進行比較來做驗證。

The aim of this study is the development of a custom-made application with the aid of digital image processing techniques to reduce human intervention on measuring 8 different types of Nylon 6,6 profiled fiber’s cross-section optical microscopic image, in order to get its amount and its shape factor. Several image processing techniques such as mathematical morphology, binarization, spatial masks, edge detection, Hough transformation, shape signature, and etc. were deployed to isolate fibers and compute their geometry property with the aid of numerical analysis methods. We successfully provide objective result, reduce human effort and improve efficiency on quality control of textile industry which makes the manufacture process become more automated, and the result was validated through human inspection.

[1]Graeber, R.C. 1986. “Crew Factors in Flight Operations: IV. Sleep and Wakefulness in International Aircrews.” NASA.
[2]Rosekind, M.R., Gander, P.H., Connell, L.J., and Co, E.L. 2001. “Crew Factors in Flight Operations X: Alertness Management in Flight Operations Education Manual.” NASA.
[3]李俊輝，1997，「影像處理應用於混紡紗斷面纖維之辨識及分佈分析」，碩士論文，國立台灣科技大學，台北市。
[4]Thibodeaux, D.P., and Evans J.P. 1986. “Cotton Fiber Maturity by Image Analysis.” Textile Research Journal 56 (2): 130-139.
[5]Huang, Y., and Xu, B. 2002. “Image Analysis for Cotton Fibers Part I: Longitudinal Measurements.” Textile Research Journal 72 (8): 713-720.
[6]Xu, B., and Huang, Y. 2004. “Image Analysis for Cotton Fibers Part II: Cross-Sectional Measurements.” Textile Research Journal 74 (5): 409-416.
[7]Wang, Q., and Xu, B. 2016. “A Coupled-Contour Model for Effective Segmentation of Cotton Cross-Sections in Wide-Field Microscopic Images.” Textile Research Journal 0 (0): 1-13. doi: 10.1177/0040517516654113.
[8]Drobina, R., and Machino M.S. 2006. “Application of the Image Analysis Technique for Textile Identification.” AUTEX Research Journal 6 (1): 40-48.
[9]Nateri, A.S., Ebrahimi, F., and Sadeghzade N. 2014. “Evaluation of Yarn Defects by Image Processing Technique.” International Journal for Light and Electron Optics 125 (20): 5998-6002. doi: 10.1016/j.ijleo.2014.06.095.
[10]Eldessouki, M., Ibrahim, S., and Militky, J. 2014. “A Dynamic and Robust Image Processing Based Method for Measuring the Yarn Diameter and its Variation.” Textile Research Journal 84 (18): 1948-1960. doi: 10.1177/0040517514530032.
[11]Gonçalves, N., Carvalho, V., Belsley, M., Vasconcelos. R.M., Soares, F.O., and Machado J. 2014. “Yarn Features Extraction Using Image Processing and Computer Vision-A Study with Cotton and Polyester Yarns” Measurement 68: 1-15. doi: 10.1016/j.measurement.2015.02.010.
[12]Shady, E., Qashqary, K., Hassan, M., and Militky, J. 2012. “Image Processing Based Method Evaluating Fabric Structure Characteristics.” FIBER & TEXTILES in Eastern Europe 20 6A(95): 86-90.
[13]Schneider, D. 2013. “Tracking Yarns in High Resolution Fabric Images: A Real-Time Approach for Online Fabric Faw Detection.” Real-Time Image and Video Processing 8656(865603): 1-12. dio: 10.1117/12.2001114.
[14]Meskuotiene, A., Dargiene, J., and Domskiene, J. 2014. “Metrological Performance of the Digital Image Analysis Method Applied for Investigation of Textile Deformation.” Textile Research Journal 85 (1): 71-79. dio: 10.1177/0040517514538696
[15]Swery, E.E., Allen, T., and Kelly, P. 2015. “Automated Tool to Determine Geometric Measurements of Woven Textiles Using Digital Image Analysis Techniques.” Textile Research Journal 86 (6): 618-635. dio: 10.1177/0040517515595031.
[16]Xu, B. 1993. “Fiber Cross-Sectional Shape Analysis Using Image Processing Techniques.” Textile Research Journal 63 (12): 717-730.
[17]Wang, Z., Zhong, Y., and Wang, S. 2011. “Profiled Fiber Cross-Sectional Shape Characterization for Identification.” International Journal of Clothing Science and Technology 23(2/3): 131-141. dio: 10.1108/09556221111107324
[18]Wang, Z., Zhong, Y., and Wang, S. 2012. “A new shape factor measure for characterizing the cross-section of profiled fiber.” Textile Research Journal 82 (5): 454-462. dio: 10.1177/0040517511426614.
[19]黃議賜，2007，「應用輪廓簽名特徵於鞋印圖形檢索」，碩士論文，國立台灣科技大學，台北市。
[20]陳建廷，2010，「背光源模組擴散板之自動化瑕疵檢測」，碩士論文，國立台灣科技大學，台北市。
[21]官聲嚴，2014，「曲面物體表面之光學瑕疵檢測」，碩士論文，國立台灣科技大學，台北市。
[22]Gonzalez, Woods. 2008. 「數位影像處理 Digital Image Processing 3/e」，新北市，普林斯頓國際有限公司。
[23]鍾國亮，2012，「影像處理與電腦視覺」，台北市，東華書局。
[24]Sobel I. 2014. “An Isotropic 3 3 Image Gradient Operator.” ResearchGate.
[25]Canny, J. 1986. “A Computational Approach to Edge Detection.” IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-8(6): 679-698.
[26]Hough P.V.C. 1962. Method and Means for Recognizing Complex Patterns. US Patent 3,069,654.
[27]O’Gorman, F. 1976. “Finding Picture Edges Through Collinearity of Feature Points.” IEEE Transactions on Computers C-25(4): 449-456. doi: 10.1109/TC.1976.1674627.
[28]Ballard, D.H. 1981. “Generalizing the Hough Transform to Detect Arbitrary Shapes.” Pattern Recognition 13(2): 111-122.
[29]Duda, R.O., and Hart, P.E. 1971 “Use of the Hough Transformation to Detect Lines and Curves in Pictures.” Technical note, Artificial Intelligence Center.
[30]Kimme, C., Ballard, D., and Sklansky, J. 1975. “Finding Circle by an Array of Accumulators.” Short Communications Graphics and Image Processing 18(2): 120-122.
[31]Yuen, H.K., Princen, J., Illingworth, J., and Kittler J. 1989. “A Comparative Study of Hough Transform Methods for Circle Finding.” AVC, doi:10.5244/C.3.29
[32]Davies, E.R. 1988. “A Modified Hough Scheme for General Circle Location.” Pattern Recognition Letters 7(1): 37-43.
[33]El-ghazal, A., Basir, O., Belkasim, S. 2009. “Farthest Point Distance: A New Shape Signature for Fourier Descriptors.” Signal Processing: Image Communication 24(7): 572-286. doi: 10.1016/j.image.2009.04.001