影像自動分群應用於工具機路徑規劃之研究｜國立中央大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	林柔廷 Jou-Ting Lin
論文名稱：	影像自動分群應用於工具機路徑規劃之研究
指導教授：	黃衍任
口試委員:
學位類別：	碩士 Master
系所名稱：	工學院 - 機械工程學系 Department of Mechanical Engineering
論文出版年：	2020
畢業學年度：	108
語文別：	中文
論文頁數：	63
中文關鍵詞：	影像處理、模糊理論、路徑規劃
相關次數：	點閱：11 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

近年來，機器視覺在工業界應用的地方越來越多，尤其在材料切割與雕刻上，其輸入多為圖像，為了使輸入影像符合使用者需求，常需使用者事先對圖像進行前處理，再輸入至機台進行加工，增加使用上的困難，且一般工具機加工多為 X-Y 方向，若圖像較複雜，其加工路徑可能並未是最佳路徑，造成時間成本，因此本研究希望融合影像處理與路徑規劃，提出新的路徑規劃法。
本研究使用 C#作為開發語言，搭配機器學習與模糊理論，使影像可自動分群並進行切割，以符合使用者需求，並配合輪廓跟蹤產生有別於一般 X-Y 方向的路徑規劃，並探討如分群演算法之利弊、影像處理之效果和路徑規劃之優劣等問題。
關鍵字：影像處理、模糊理論、路徑規劃

In recent years, there are more and more applications of machine vision in the industrial world, especially in material cutting and engraving, the input is mostly images. In order to make the input image meet the needs of users, users often need to pre-image Processing, and then input to the machine for processing, increasing the difficulty of use, and the general tool machining is mostly in the XY direction. If the image is more complicated, the processing path may not be the best path, resulting in time cost, so this study Hope to combine image processing and path planning, and propose a new path planning method.
This research uses C# as the development language, combined with machine learning and fuzzy theory, so that the images can be automatically grouped and cut to meet the needs of users, and the contour tracking generates a path plan that is different from the general XY direction, and discusses such as the pros and cons of Cluster Analysis, the effect of image processing and the advantages and disadvantages of path planning.
Keyword：Image processing、Fuzzy Theory、Route Plan

摘要 .................................................................... vi
Abstract ............................................................... vii
致謝 .................................................................. viii
目錄 .................................................................... ix
圖目錄 .................................................................. xi
表目錄 ................................................................ xiii
第一章 緒論 .............................................................. 1
1-1前言 ................................................................ 1
1-2研究動機與目的 ...................................................... 1
1-3文獻回顧 ............................................................ 2
1-4內容架構 ............................................................ 3
第二章 基礎理論 .......................................................... 4
2-1 Canopy聚類演算法 ................................................... 4
2-2 K-means演算法 ...................................................... 6
2-3 顏色模型 ........................................................... 7
2-3-1 RGB顏色模型 .................................................... 7
2-3-2 HSL顏色模型 .................................................... 7
2-4 影像前處理 ......................................................... 8
2-4-1 圖像灰階化 ..................................................... 8
2-4-2 高斯濾波 ....................................................... 8
2-4-3 Otsu二值化 ..................................................... 9
2-5 連通分量標記 ...................................................... 10
2-6 Boundary Tracing .................................................. 11
2-7 模糊理論 .......................................................... 12
2-7-1 模糊推論工廠 .................................................. 12
2-7-2 模糊決策 ...................................................... 12
第三章 影像分群研究方法與討論 ........................................... 14
3-1 顏色分群 .......................................................... 15
3-1-1 Canopy聚類演算法之影響 ........................................ 16
3-1-2 Canopy演算法閾值之影響 ........................................ 18
3-1-3 顏色模型之影響 ................................................ 21
3-2 形狀分群 .......................................................... 23
3-3交叉計算顏色分群與形狀分群 ......................................... 25
第四章 背景移除研究方法與討論 ........................................... 28
4-1背景移除演算法 ..................................................... 28
4-1-1 重要度之影響 .................................................. 31
4-2 手動修正 .......................................................... 33
4-3 背景移除效果討論 .................................................. 35
第五章 影像輪廓之路徑規劃研究方法與討論 ................................. 39
5-1 影像輪廓演算法 .................................................... 39
5-2 操作介面 .......................................................... 42
5-3 路徑規劃之比較 .................................................... 44
5-3-1 圖形模式 ...................................................... 44
5-3-2 輪廓模式 ...................................................... 46
第六章 結論與未來展望 ................................................... 48
5-1結論 ............................................................... 48
5-2未來展望 ........................................................... 48
參考文獻 ................................................................ 49
                                

[1] MacQueen, J. B. “Some Methods for classification and Analysis of
Multivariate Observations”, Proceedings of 5th Berkeley Symposium on
Mathematical Statistics and Probability, 1967, pp. 281–297
[2] Sobel I. and Feldman G., “A 3x3 isotropic gradient operator for image
processing ”,a talk at the Stanford Artificial Project in, pp. 271-
272,1968
[3] Canny, J. "A Computational Approach To Edge Detection", IEEE Trans.
Pattern Analysis and Machine Intelligence, pp.679-714,1986
[4] Luc Vincent and Pierre Soille,“Watersheds in digital spaces: an
efficient algorithm based on immersion simulations”, IEEE Transactions on
Pattern Analysis and Machine Intelligence, Vol. 13, pp. 583–598,1991
[5] Andrew Mccallum , Kamal Nigam , Lyle Ungar, “Efficient Clustering of
High-Dimensional Data Sets with Application to Reference Matching”, The
International Conference on Knowledge Discovery and Data
Mining(SIGKDD),2000
[6] MacQueen, J. B. “Some Methods for classification and Analysis of
Multivariate Observations”, Proceedings of 5th Berkeley Symposium on
Mathematical Statistics and Probability, pp. 281–297, 1967
[7] Weisstein, Eric W,” Moore Neighborhood From Math World-A Wolfram Web
Resource”, http://mathworld.wolfram.com/MooreNeighborhood.hml.
[8] Mirante, Weingarten.” The Radial Sweep Algorithm for Constructing
Triangulated Irregular Networks”, IEEE Computer Graphics and Applications,
Vol. II, May 1982
[9] Jonghoon Seo, Seungho Chae, Jinwook Shim2, Dongchul Kim, Cheolho Cheong and Tack-Don Han,” Fast Contour-Tracing Algorithm Based on a PixelFollowing Method for Image Sensors”, Vol. 9, March 2016
[10] Zadeh L.A.,” Fuzzy sets”, Vol. 8, June 1965
[11] https://www.remove.bg/
[12] Rother C. , Kolmogorov V., and A. Blake, “GrabCut: Interactive
foreground extraction using iterated graph cuts”, ACM Trans. Graph., vol.
23, pp. 309–314, 2004.
[13] 王文俊：《認識 Fuzzy 理論與應用》，第四版，新北市：全華圖書，2017
[14] 張家樵 : <三軸機械手臂雷射加工控制之研究>。碩士論文，國立中央大
學，民國 108 年 6 月

簡易檢索 / 詳目顯示

相關論文