跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.82) 您好!臺灣時間:2025/02/07 04:15
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

: 
twitterline
研究生:林國偉
研究生(外文):Guo-Wei Lin
論文名稱:結合形狀資訊之正規化分割影像切割法
論文名稱(外文):Image Segmentation by Normalized Cut with Shape Information
指導教授:張欽圳
指導教授(外文):Chin-Chun Chang
學位類別:碩士
校院名稱:國立臺灣海洋大學
系所名稱:資訊工程學系
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:2005
畢業學年度:93
語文別:英文
論文頁數:38
中文關鍵詞:影像切割圖形分割廣義霍夫轉換
外文關鍵詞:image segmentationgraph partitioninggeneralized Hough transform
相關次數:
  • 被引用被引用:0
  • 點閱點閱:250
  • 評分評分:
  • 下載下載:42
  • 收藏至我的研究室書目清單書目收藏:1
在電腦視覺領域中,影像切割是一個典型的問題。近幾年,有些研究嘗試將影像切割轉換成圖論的切割問題求解。這些研究有一些共通的特性:將像素視作圖形的節點,用邊線連結某些節點,並用加權函數計算每一邊的權重,如此會形成一個圖;接著建立成本的度量法,並嘗試找出一種共通的解法,使分割結果具有最低的成本。其中一種成本度量法–正規化分割度量法及其解法,具有以下特性:能連結任意二個像素;分割出來的群,具有較強的內部連結,和較弱的外部連結。基於像素間連結的彈性,或許能針對特定的切割標的,微調加權函數,以獲致理想的結果。
所有先前提出之成本度量法,僅使用低階特徵作為權重。本研究利用部份廣義霍夫轉換法的概念,定義出能表示高階特徵–形狀資訊的加權函數。廣義霍夫轉換法是一個能有效偵測剛體的方法,但使用上有其限制:物體不能有太大的變形;除了目標物之外,亦會獲得不必要的雜邊。本研究首先在未知樣本作邊緣偵測,以輪廓線上的像素作為圖的節點,參考廣義霍夫轉換法的資訊定義出加權函數,用以指定節點之間的權重,最後,利用正規化分割度量法將像素分群,以獲得目標物體之輪廓點。實驗證實,本研究所提出的方法和廣義霍夫轉換法相較,能獲得較連續的輪廓線,能容許較大的物體變形,並且能排除多餘的雜邊。
Image segmentation is a classical problem in compute vision. In the recent years, some researches regard the image segmentation problem as a graph-partitioning problem. Among various graph-partitioning algorithms for image segmentation, of particular interest in this thesis is the normalized cut because the normalized cut is capable of establishing the relationship between each pair of pixels. However, to our knowledge, all of the graph-partitioning approaches only utilize low-level information about the image. In this thesis, in order to find the contour of the target shape with shape deformations, we propose a new scheme to incorporate high-level information about the target shapes, which is collected by the generalized Hough transform (GHT), into the normalized cut. The experimental results show that our approach can segment out the target shape. In addition, in comparison with the GHT, the proposed approach has better edge continuation, could tolerate larger shape variation, and cover less erroneous contours.
List of Figures II
List of Tables III
1 Introduction 1
1.1 Motivation 1
1.2 Survey of Related Research 2
1.3 An Overview of the Proposed Approach 6
1.4 Thesis Organization 7
2 Normalized Cut with Shape Information 8
2.1 Review of Image Segmentation by Normalized Cut 8
2.1.1 The Minimization of Normalized Cut 8
2.1.2 The Weight Function of the Normalized Cut 10
2.2 Incorporation of Shape Information with the Normalized Cut 11
2.3 Proposed Algorithm 13
2.3.1 Learning Stage 14
2.3.2 Segmentation Stage 16
3 Experimental Results 21
3.1 Platform 21
3.2 Parameters 21
3.3 Results 22
3.4 Discussion 35
4 Conclusion 36
Reference 37
[1] Z. Wu and R. Leahy, “An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(11), pp. 1101–1113, 1993.
[2] J. Shi and J. Malik, “Normalized Cuts and Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence,” Vol. 22, No. 8, 2000.
[3] D. H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognit., vol. 13, pp. 111–122, 1981.
[4] W. Skarbek , A. Koschan, “Color Image Segmentation- A Survey,” Technisher Bericht 94-32, Technical University of Berlin, Oct.
[5] L. Lucchese and S. K. Mitra, “Color image segmentation: A state-of-the-art survey,” in Proc. Indian National Science Academy (INSA-A), vol. 67, A, New Delhi, India, Mar. 2001, pp. 207–221.
[6] S. Wang, J. M. Siskind, “Image Segmentation with Minimum Mean Cut,” ICCV 2001: pp. 517-524.
[7] S. Sarkar and P. Soundararajan, “Supervised Learning of Large Perceptual Organization: Graph Spectral Partitioning and Learning Automata,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 5, pp. 504-525, May 2000.
[8] J. McQueen, “Some Methods for Classification and Analysis of Multivariate Observations,” Proc. of the 5th Berkeley Symp. on Math. Stat. and Prob., Vol. 1, pp. 281-296, 1967.
[9] N.R. Pal and S.K. Pal, “A Review on Image Segmentation Techniques,” Pattern Recognition, Vol. 26, No. 9, pp. 1277-1294, 1993.
[10] P. Chen and T. Pavlidis, “Image segmentation as an estimation problem,” Computer Graphics and Image Processing 12, 153–172, 1980.
[11] S. W. Zucker, “Region growing: Childhood and adolescence,” Computer Graphics and Image Processing 5, pp. 382–399, 1976.
[12] S.A. Shafer, “Using Color to Separate Reflection Components,” Color Research and Application, Vol. 10, No. 4, pp. 210-218, 1985.
[13] J. H. Elder, A. Krupnik, and L. A. Johnston, “Contour Grouping with Prior Models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 6, 2003.
[14] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models,” International Journal of Computer Vision, 1:321–331, 1988.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
1. 林麗娟(1996)。多媒體電腦圖像設計與視覺記憶的關係。教學科技與媒體,28,3-12。
2. 李秀娟、張永達、黃達三(1998)。概念圖應用於國中生物教材之分析與評論─以神經系統為例。科學教育,213,14-26。
3. 吳美蓉(2000)。自然科教科書之評鑑研究。教師之友。41(2),49-56。
4. 王淑琴、郭重吉(1994):利用DOE晤談研究大學生電學方面的另有架構。科學教育,第五期,PP.117-140。
5. 許良榮(1994)。科學課文的特性與學習。科學教育月刊,170,23-36。
6. 郭重吉(1988)。從認知的觀點探討自然科學的學習。教育學院學報,13,352-378。
7. 陳文典(2000)。由國民中小學課程目標看「自然與生活科技」學習領域之教學與教材。科學教育月刊,231,40-42。
8. 陳嘉成(1998)。合作學習是概念構圖在國小自然科教學之成效研究。國立政治大學教育與心理研究, 21, 107-128。
9. 陳瓊森(1993)。高一學生直流電路概念結構之研究。彰化師範大學學報,4,511-542。
10. 葉俊豪、陳瓊森(1995)。利用定性與定量測驗來探究高二學生對直流電路的知識結構。科學教育,6,156-178。
11. 劉昭宏、郭重吉(1995)。教科書在國中理化教學的應用之個案研究。科學教育,6,89-112。
12. 鄭世仁(1992)。揭開「教科書」的面紗。國立教育資料館館訊,18,1-7。