(3.238.7.202) 您好!臺灣時間:2021/03/04 21:06
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:傅建璋
研究生(外文):Chien-Chang Fu
論文名稱:應用影像處理方法於布匹客觀分級
論文名稱(外文):Apply image processing methods in fabrics objective grading
指導教授:黃美玲黃美玲引用關係
指導教授(外文):Mei-Ling Huang
學位類別:碩士
校院名稱:國立勤益科技大學
系所名稱:工業工程與管理系
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2017
畢業學年度:105
語文別:中文
論文頁數:56
中文關鍵詞:布匹毛球影像處理機器學習
外文關鍵詞:fabricpillsimage processingmachine learning
相關次數:
  • 被引用被引用:0
  • 點閱點閱:61
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
臺灣作為一個海島國家,土地狹小、人口密集度大,多是仰賴進口能源與原料,這種模式是臺灣的經濟來源,一直扮演著世界的代工廠。臺灣紡織為傳統產業較為現代年輕人不想投入的產業,因此造成紡織業人力資源的匱乏的危機,另外加上中國經濟逐漸崛起人工薪資上漲,使在中國設廠的台灣紡織廠商加工成本提高,迫使台灣的紡織業轉往其他東南亞國家,所以紡織業要從這些困境之中找出生存點。
本研究探討布匹的等級分級,在傳統的布匹等級標準檢驗方式,都以耐磨次數作為依據,再以人工目視的方式進行檢測判定等級,這樣人工檢測方式可能會造成一些判定的誤差,故提出客觀分級方法去取代傳統的主觀分級方法,運用客觀分級方式可以使布匹檢測上會有所依據。本研究分級方法分為影像處理、機器學習兩個部分,在影像處理方面,濾波影像處理方法使用了快速傅立葉結合高斯濾波、多貝西小波方法,也使用二值化以及形態學、拓樸學影像處理方法運用於T/C單毛刷布匹,擷取布匹影像資訊進一步建立布匹特徵參數資料庫,再最後運用機器學習方法進行分類處理,找出布匹分級最佳的處理分析方法。
Taiwan is a small island state, which is densely populated. Because of lacking natural resources, Taiwan depends on imports for most energy and raw materials. Taiwan plays an important role in foundry, which is the country's economy. Textile industry is one of the traditional industries in Taiwan, which mostly young people do not want to join, it results in the shortage of human resources. In addition, because of the economic growth in China, the labor cost has gradually increased. The Taiwan's textile manufacturers in China face the increasing of processing costs, which forces Taiwan's textile manufacturers to relocate to other Southeast Asian countries. The textile industry in Taiwan needs to find the ways out of the worst environment.
This study focuses on the grading of fabrics. The traditional examining standard methods of fabrics grading are based on the number of wear-resistant, and then determining the grading by eye-estimation. The manual detection method may cause the deviation, so this study proposes the objective grading method to replace the traditional subjective classification method, which makes the objective grading in fabric detection on scientific basis. The classification method in this study has two parts: image processing and machine learning. In terms of image processing, filter image processing method utilizes Fast Fourier Transform with Gaussian filtering, Daubechies Wavelet method. The binary threshold and morphology, topology image processing methods are also applied in T/C terry fleece fabrics. The fabric images information extraction is utilized to further establish the fabric feature parameter database, and then use the machine learning method for classification to find the optimized classification of fabric grading methods.
摘要 I
Abstract II
目錄 III
圖目錄 VI
表目錄 VII
第一章 緒論 1
1.1研究背景與動機 1
1.2研究目的 2
1.3研究對象與範圍 3
1.4研究流程與架構 3
1.5架構流程圖 4
第二章 文獻探討 5
2.1紡織介紹 5
2.1.2國內紡織概況與結構 5
2.2數位影像處理 7
2.2.1機器視覺概論 7
2.2.2直方圖(灰階值分布圖) 7
2.2.3影像評估方法 8
2.3傅立葉轉換 9
2.3.1離散傅立葉轉換 9
2.3.2快速傅立葉轉換 10
2.3.3高斯濾波器 11
2.4小波轉換 12
2.4.1多貝西小波 13
2.5 二值化 15
2.6形態學 15
2.7影像拓樸學 17
2.8機器學習 20
2.8.1類神經網路 20
2.8.2倒傳遞類神經網路 21
2.8.3 K近鄰算法 22
2.8.4支撐向量機 23
2.9織物研究相關文獻 24
第三章 研究方法 29
3.1研究流程 29
3.2資料蒐集 31
3.2.2光源探討 32
3.3影像處理 33
3.3.1快速傅立葉結合高斯濾波 33
3.3.2多貝西小波濾波 35
3.3.3二值化 36
3.4特徵參數提取 37
3.4.1形態學 37
3.4.2拓撲學 38
3.4.3建立資料庫 38
3.5模型建立 40
3.5.1類神經網路分析 40
3.5.2 K近鄰算法分析 40
3.5.3支撐向量機分析 40
第四章 實驗結果與討論 41
4.1資料蒐集結果 42
4.2影像處理結果 42
4.2.1快速傅立葉高斯濾波結果 42
4.2.2多貝西小波結果 43
4.2.3影像二值化結果 45
4.3影像形態學結果 46
4.4機器學習分類結果 47
第五章 結論與建議 50
5.1結論 50
5.2建議 52
參考文獻 53
1. 天下雜誌,http://www.cw.com.tw/article/article.action?id=5078926。
2. 紡拓會全球資訊網Taiwan Textile Federation,http://www.textiles.org.tw/。
3. 紡織百科,http://fangzhi.baike.com/。
4. 產業價值鏈平台,http://ic.tpex.org.tw/。
5. 連國珍,1990,數位影像處理,儒林圖書有限公司。
6. 國家發展委員會檔案管理局,www.archives.gov.tw/。
7. 中央大學影像處理暨虛擬實境實驗,http://ip.csie.ncu.edu.tw/course/IP/IP1405cp.pdf
8. 謬紹綱,2003,數位影像處理,台灣培生教育,台北。
9. 劉震昌,2010,數位影像處理,高立圖書有限公司,台北。
10. 葉怡成,1997,應用類神經網路,儒林圖書有限公司。
11. 蘇木春、張孝德,2007,機器學習:類神經網路、模糊系統以及基因演算法則,全華圖書有限公司。
12. 吳成柯、程湘君、戴善榮,2001,數位影像處理,儒林圖書,臺北。
13. Albert Cohen, 2003, “Numerical Analysis of Wavelet Methods”, eBook ISBN: 9780080537856, PP.354.
14. Ankit Vidyarthi, Namita Mittal, 2016, “AVNM: A Voting based Novel Mathematical Rule for Image Classification”, Computer Methods and Programs in Biomedicine, Vol.137, pp.195-201.
15. Chung-Feng Jeffrey Kuo, Chung-Yang Shih, Chang-Chiun Huang, Yao-Ming Wen, 2016, “Image inspection of knitted fabric defects using wavelet packets”, Textile Research Journal, Vol.86, pp.553-560.
16. Deng Z, Wang L, Wang X, 2011, “An integrated method of feature extraction and objective evaluation of fabric pilling”, Journal of the Textile Institute, Vol.102, pp.1-13.
17. Dejun Zheng, Yu Han, Jin Lian Hu, 2014, “A new method for classification of woven structure for yarn-dyed fabric”, Textile Research Journal, Vol.84, pp.78-95.
18. Gonca Ozcelik Kayseri, Erhan Kirtay, 2015, “Part 1. Predicting the Pilling Tendency of the Cotton Interlock Knitted Fabrics by Regression Analysis”, Journal of Engineered Fibers and Fabric, Vol.10, pp.110-120.
19. Gonca Ozcelik Kayseri, Erhan Kirtay, 2015, “Part II. Predicting the Pilling Tendency of the Cotton Interlock Knitted Fabrics by Artificial Neural Network”, Journal of Engineered Fibers and Fabric, Vol.10, pp.62-71.
20. Guoqiang Zhang, B. Eddy Patuwo, Michael Y. Hu, 1998, “Forecasting with artificial neural networks: The state of the art.” International Journal of Forecasting, Vol.14, Page 35–62.
21. Junfeng Jing, Zhang, Zanzan, Xuejuan Kang, Jianyuan Jia, 2012, “Objective evaluation of fabric pilling based on wavelet transform and the local binary pattern”, Textile Research Journal, Vol.82, pp.1880-1887.
22. Junmin Zhang, Xungai Wang, Stuart Palmer, 2009, “Performance of an Objective Fabric Pilling Evaluation Method”, Textile Research Journal, Vol.80, pp.1648-1657.
23. Junmin Zhang, Xungai Wang, Stuart Palmer, 2010, “Objective Pilling Evaluation of Nonwoven Fabrics”, Fibers and Polymers, Vol.11, pp.115-120.
24. Lenka Technikova, Maros Tunak, Jiri Janacek, 2016, “Pilling evaluation of patterned fabrics based on a gradient field method”, Indlan Journal OF FIBRE & Textile Research, Vol.41, pp.97-101.
25. Lenka Technikova, Maros Tunak, Jiri Janacek, 2017, “New objective system of pilling evaluation for various types of fabrics”, Journal of The Textile Institute, Vol.108, pp.123-131.
26. Lucia Bissi, Giuseppe Baruffa, Pisana Placidi, Elisa Ricci, Andrea Scorzoni, Paolo Valigi, 2013, “Automated defect detection in uniform and structured fabrics using Gabor filters and PCA”, Journal of Visual Communication and Image Representation, Vol.24, pp.838-845.
27. Mohamed Edessouki, Hanan A Bukhari, Mounir Hassan, Khadijah Qashqari, 2014, “Integrated Computer Vision and Soft Computing System for Classifying the Pilling Resistance of Knitted Fabrics”, Fibres & Textiles in Eastern Europe, Vol.22, pp.106-112.
28. Paul Heckbert, 1998, “Fourier Transforms and the Fast Fourier Transform (FFT) Algorithm”, Notes 3, Computer Graphics 2, 15-463.
29. Rocco Furferi, Monica Carfagni, Lapo Governi, Yary Volpe, Patrizia Bogani, 2014, “Towards Automated and Objective Assessment of Fabric Pilling”, International Journal of Advanced Robotic Systems, Vol.11, pp.11-24.
30. Robert Hecht-Nielsen, 1992, “Theory of the backpropagation neural network”, ISBN: 0-12-741252-2, PP.65-93.
31. Raghuveer M. Rao, Ajit S. Bopardikar, 1998, “Wavelet Transforms: Introduction to theory and Application”, Prentice Hall PTR.
32. Stephane Mallat, Gabriel Peyre, 2009, “A Wavelet Tour of Signal Processing The Sparse Way Preface to the Sparse Edition.”
33. Siamak Saharkhiz, Mohammad Abdorazaghi, 2012, “The Performance of Different Clustering Methods in the Objective Assessment of Fabric Pilling”, Journal of Engineered Fibers and Fabric, Vol.7, pp.35-41.
34. Scott E. Umbaugh, 1998, “Computer Vision and Image Processing: A Practical Approach Using CVIPTools.”, Prentice Hall.
35. Soon Young Yun, Sungmin Kim, Chang Kyu Park, 2013, “Development of an objective fabric pilling evaluation method. I. Characterization of pilling using image analysis”, Fibers and Polymers, Vol.14, pp.832-837.
36. Soon Young Yun, Sungmin Kim, Chang Kyu Park, 2013, “Development of an Objective Fabric Pilling Evaluation Method. II. Fabric Pilling Grading Using Artificial Neural Network”, Fibers and Polymers, Vol.14, pp.2157-2162.
37. Zhou feng Liu, Chunlei Li, Quanjun Zhao, Liang Liao, Yan Dong, 2015, “A fabric defect detection algorithm via context-based local texture saliency analysis”, International Journal of Clothing Science and Technology, Vol.27, pp.738-750.
電子全文 電子全文(網際網路公開日期:20220719)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔