(54.236.58.220) 您好!臺灣時間:2021/03/05 00:24
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:許俊陽
研究生(外文):HSU, CHUN-YANG
論文名稱:利用深度學習網路於布料毛球分類之應用
論文名稱(外文):Fabric Pilling Classification Using a Deep Learning Network
指導教授:林學儀林學儀引用關係林正堅林正堅引用關係
指導教授(外文):LIN, HSUEH-YILIN, CHENG-JIAN
口試委員:陳政宏洪士程
口試委員(外文):CHEN, CHENG-HUNGHUNG, SHIH-CHENG
口試日期:2020-07-16
學位類別:碩士
校院名稱:國立勤益科技大學
系所名稱:資訊工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:36
中文關鍵詞:織物圖像毛球等級分類深度學習網路圖像處理
外文關鍵詞:Fabric imagepilling level classificationdeep learning networkimage processing
相關次數:
  • 被引用被引用:0
  • 點閱點閱:37
  • 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:6
  • 收藏至我的研究室書目清單書目收藏:0
台灣的紡織業一直以來在台灣整體產業中佔有很重要的地位,從上游的纖維廠、中游的紡紗、織布、染整、到下游的成衣、服飾業,形成非常完整的上、中、下游製造體系與群聚效益,也建立跨國性產銷網路,因此具備高度之競爭力。在廠商出貨前,會依據SGS國際標準檢測,將對織物進行摩擦性測試,並以人工檢查方式分類,以確保沒有破損。由於利用人工目視檢查織物需要花費大量之人力資源,且檢測員長期集中肉眼在觀察的情況下,往往會造成職業上的傷害,而導致整個運作的效率降低。
本研究以獲得的布匹圖像建立資料庫,並透過快速傅立葉轉換和高斯濾波器用於圖像處理,來增強織物圖像中毛球之特性,使用深度學習網路進行毛球分類。實驗結果可以發現本研究所提出的方法在毛球分類中的平均準確度為100%。證實本研究所提出的深度學習網路於織物毛球分類結果均優於其他方法。
Taiwan ’s textile industry has always occupied a very important position in Taiwan ’s overall industry. From the upstream fiber factory, the midstream spinning, weaving, dyeing and finishing, to the downstream garment and apparel industry, it forms a very complete the downstream manufacturing system and the benefits of clustering also establish a multinational production and marketing network, and therefore have a high degree of competitiveness. Before the manufacturer ships, it will be tested according to SGS international standards, and the fabric will be friction tested and classified by manual visual inspection to ensure that there are no defects. Because the use of manual visual inspection of fabrics requires a lot of human resources, and the inspectors focus on the naked eye for a long period of time, it will often cause occupational injuries and reduce the efficiency of the entire operation.
The database of clothing images obtained in this study is established, and is used for image processing through fast Fourier transform and Gaussian filter to enhance the characteristics of hair balls in fabric images, and the deep learning network is used to classify hair balls. The experimental results show that the method proposed in this study has an average accuracy of 100% in the classification of hair bulb levels. It proves that the deep learning network hair ball level classification method proposed by this research can be realized.
摘要 I
ABSTRACT II
致謝 III
目錄 IV
圖目錄 V
表目錄 VI
第一章 緒論 1
1.1 研究背景與動機 1
1.2 論文架構 4
第二章 文獻探討 5
2.1 織物之介紹及相關研究 5
2.2 卷積神經網路之介紹及相關研究 8
第三章 研究方法 12
3.1 快速傅立葉轉換 13
3.2 高斯濾波器 13
3.3 利用卷積神經網路進行毛球等級分類 17
第四章 實驗結果 26
4.1 快速傅立葉結合高斯濾波器結果 27
4.2 使用深度學習網路的分類結果 28
第五章 結論與未來工作 32
5.1 結論 32
5.2 未來工作 32
參考文獻 33
[1]紡拓會全球資訊網Taiwan Textile Federation,http: //www.textiles.org.tw/。
[2]J. Hessels, S. C. Parker, “Internationalization and Growth: A cross-country analysis of European SMEs,” Journal of World Business, Vol. 48, No. 1, pp. 137-148, 2013.
[3]紡織百科,http://fangzhi.baike.com/。
[4]Z. Deng, L. Wang, & X. Wang, “An integrated method of feature extraction and objective evaluation of fabric pilling,” The Journal of The Textile Institute, Vol. 102, No. 1, pp. 1-13, 2011.
[5]S. Saharkhiz, & M. Abdorazaghi, “The performance of different clustering methods in the objective assessment of fabric pilling,” Journal of Engineered Fibers and Fabrics, Vol. 7, No. 4, 155892501200700413, 2012.
[6]S. Y. Yun, S. Kim, & C. K. Park, “Development of an objective fabric pilling evaluation method. I. Characterization of pilling using image analysis,” Fibers and Polymers, Vol. 14, No. 5, pp. 832-837, 2013.
[7]R. Furferi, M. Carfagni, L. Governi, Y. Volpe, & P. Bogani, “Towards automated and objective assessment of fabric pilling,” International Journal of Advanced Robotic Systems, Vol. 11, No. 10, pp. 171, 2014.
[8]M. Eldessouki, H. A. Bukhari, M. Hassan, & K. Qashqary, “Integrated computer vision and soft computing system for classifying the pilling resistance of knitted fabrics,” Fibres & Textiles in Eastern Europe, Vol. 6, No. 108, pp. 106-112, 2014.
[9]L. Technikova, M. Tunak, & J. Janacek, “Pilling evaluation of patterned fabrics based on a gradient field method,” Indian Journal of Fibre & Textile Research (IJFTR) , Vol. 41, No. 1, pp. 97-101, 2016.
[10]M. L. Huang, & C. C. Fu, “Applying image processing to the textile grading of fleece based on pilling assessment,”Fibers, Vol. 6, No. 4, pp. 73, 2018.
[11]C. L. Lee, & C. J. Lin, “Integrated Computer Vision and Type-2 Fuzzy CMAC Model for Classifying Pilling of Knitted Fabric,”Electronics, Vol. 7, No. 12, pp. 367, 2018.
[12]D. H. Hubel, & T. N. Wiesel, “Receptive fields of single neurones in the cat's striate cortex,” The Journal of physiology, Vol. 148, No. 3, pp. 574-591, 1959.
[13]K. Simonyan, & A. Zisserman, “Very deep convolutional networks for large-scale image recognition,”arXiv preprint arXiv, pp. 1409.1556, 2014.
[14]J. L. McClelland, D. E. Rumelhart, & PDP Research Group, “Parallel distributed processing,” Explorations in the Microstructure of Cognition, Vol. 2, pp. 216-271, 1986.
[15]C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, & A. Rabinovich, “Going deeper with convolutions,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015.
[16]S. Wu, S. Zhong, & Y. Liu, “Deep residual learning for image steganalysis,” Multimedia Tools and Applications, Vol. 77, No. 9, pp. 10437-10453, 2018.
[17]H. Y. Lin, & C. J. Lin, “Using a hybrid of fuzzy theory and neural network filter for single image dehazing,” Applied Intelligence, Vol. 47, No. 4, pp. 1099-1114, 2017.
[18]K. He, X. Zhang, S. Ren, & J. Sun, “Deep residual learning for image steganalysis,” Multimed Tools and Applications, pp. 1-17, 2017.
[19]李國豪,應用卷積類神經網路進行布料品檢瑕疵因之分類。國立成功大學工業與資訊管理學系,台南市,2019。
[20]梁啟納,以卷積神經網路進行颱風路徑分類。淡江大學土木工程學系,新北市,2019。
[21]楊敞翔,使用卷積神經網路分類龍舌蘭品種。慈濟大學醫學資訊學系,花蓮縣,2019。
[22]J. W. Cooley, & J. W. Tukey, “An algorithm for the machine calculation of complex Fourier series,” Mathematics of Computation, Vol. 19, No. 90, pp. 297-301, 1965.
[23]C. S. Yang, C. J. Lin, & W. J. Chen, “Using deep principal components analysis-based neural networks for fabric pilling classification,” Electronics, Vol. 8, No. 5, pp. 474, 2019.
[24]J. Jing, Z. Zhang, X. Kang, & J. Jia, “Objective evaluation of fabric pilling based on wavelet transform and the local binary pattern,” Textile Research Journal, Vol. 82, No. 18, pp. 1880-1887, 2012.
[25]M. Eldessouki, M. Hassan, K. Qashqary, & E. Shady, “Application of principal component analysis to boost the performance of an automated fabric fault detector and classifier,” Fibres & Textiles in Eastern Europe, pp. 51-57, 2017.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔