Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/2617
DC FieldValueLanguage
dc.contributor.advisor李吉群zh_TW
dc.contributor.advisorJ.C. Leeen_US
dc.contributor.author張哲仁zh_TW
dc.date2004zh_TW
dc.date.accessioned2014-06-05T11:43:38Z-
dc.date.available2014-06-05T11:43:38Z-
dc.identifier.urihttp://hdl.handle.net/11455/2617-
dc.description.abstract電腦視覺系統從3D世界中所取得龐大的影像資訊,要如何轉換成有用的資訊。若直接藉由電腦來闡釋原始影像資訊是有困難的,通常最適宜的方式先做影像切割(Image segmentation)的步驟,將影像分割成一件件的低階元件來做後續的處理,所謂低階元件就是指藉由具有相同特性的像素群體組成的。而本論文目的就是建立一套3D形貌影像切割演算法,切割演算法大致分為初略切割與區域成長兩大部分。首先,使用表面曲率符號標記將形貌影像做初略的分割,接著做區域生成,成長方法是採用可變階數表面擬合重新定義表面型態,以不同階數做曲面擬合,直到預設的誤差範圍內。文中之實驗部分所用到的輸入影像是用電腦模擬形貌影像的資料,而影像中元件係以平面、圓柱面及圓錐面等幾何形狀所組成,切割的效果以6張影像來呈現整個演算法的過程及結果。zh_TW
dc.description.abstractIn this paper we present a region based segmentation algorithm for range image . The algorithm can be viewed as a two-stage process: (1)initial segmentation,(2)region growing . First, we segment surface into a set of regions in the range image by Gaussian and mean curvature signs, and then produce a surface type label image . Second , we perform an iterative region growing using variable-order surface fitting . The fitting input is a seed region from surface type label image . In order to determine the seed region , we isolate the largest connected region of any surface type , and then shrink the region until appropriate size is obtained . Using the seed region begins to grow iteratively and then refine the surface definition . Experimental results show the algorithm performance on six range images.en_US
dc.description.tableofcontents摘要 I Abstract II 目錄 III 圖目錄 V 第一章 緒論 1 1-1 前言 1 1.2 研究動機 1 1.3 研究方法 3 1.4 文獻回顧 4 第二章 演算原理 5 2.1形貌影像分割的相關定義 5 2.1.1 曲面定義 5 2.1.2 曲率定義 6 2.1.3 平滑面分解 8 2.2 演算法特性 10 2.3演算法流程 13 第三章 演算法過程詳述 15 3.1影像雜訊評估 15 3-2初略切割 16 3-2-1影像平滑化 18 3-2-2曲率計算 20 3-3區域成長 31 3-3-1 種子區域的選擇 33 3-3-2 可變階數表面擬合 34 3-3-3 種子區域成長 37 第四章 實驗結果與討論 41 第五章 結論與未來展望 61 參考文獻 63zh_TW
dc.language.isoen_USzh_TW
dc.publisher機械工程學系zh_TW
dc.subjectrange imageen_US
dc.subject形貌影像zh_TW
dc.subjectinitial segmentationen_US
dc.subjectregion growingen_US
dc.subjectGaussian curvatureen_US
dc.subjectmean curvatureen_US
dc.subjectvariable-order surface fittingen_US
dc.subject影像切割zh_TW
dc.subject初略切割zh_TW
dc.subject區域成長zh_TW
dc.subject可變階數表面擬合zh_TW
dc.title高斯與平均曲率在形貌影像切割之研究zh_TW
dc.titleStudy of Gaussian and Mean Curvatures in Range Image Segmentationen_US
dc.typeThesis and Dissertationzh_TW
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.openairetypeThesis and Dissertation-
item.cerifentitytypePublications-
item.fulltextno fulltext-
item.languageiso639-1en_US-
item.grantfulltextnone-
Appears in Collections:機械工程學系所
Show simple item record
 
TAIR Related Article

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.