(3.227.235.183) 您好!臺灣時間:2021/04/14 18:38
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:吳敬群
論文名稱:影像分割之新分水嶺演算法及其場效應可程式邏輯陣列之模擬
論文名稱(外文):Image segmentation with a new watershed algorithm and its FPGA simulation
指導教授:郭鐘榮陳自強陳自強引用關係
學位類別:碩士
校院名稱:國立中正大學
系所名稱:電機工程研究所
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:2004
畢業學年度:92
語文別:中文
論文頁數:47
中文關鍵詞:影像分割分水嶺
相關次數:
  • 被引用被引用:0
  • 點閱點閱:538
  • 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
分水嶺演算法在許多不同的應用,都扮演著重要的角色,其方法是簡單的、直覺的,並可被平行處理且在整張影像可割出一完整的區域。然而在分水嶺演算法裡,有著一個嚴重的缺點,就是過分割的問題。在此我們提出一個改良的演算法用來減少過分割的問題。首先在漲水時,只針對單一的最小值來做獨立漲水的動作,並且記錄漲成後的區域個數,及座標位置。在取得漲成後的區域資訊後,我們可同時將較小的區域合併成較大的區域,進而減少分割出來的區域。
The watershed transform has interesting properties that make it useful for many different image segmentation applications: it is simple and intuitive, can be parallelized, and always produces a complete division of the image. However A severe drawback to the calculation of watershed images is over- segmentation. Here we present an improvement to the watershed transform that reduce over-segmentation. The approach starts with a seed pixel and floods form the seed isolation estimating a region, then calculating the region number. After getting the information of the region and region coordinates, we can merge the small region to become a large region concurrently.
第一章 緒論 .…………………………………………..1
1.1 Vincent之分水嶺演算法…………………………...1
1.2動機 ………………………………………………...2
第二章 Vincent分水嶺演算法 ………………………..4
2.1基本定義…………………………………….………..4
2.2 短線距(Geodesic Distance)……………………….4
2.3 Geodesic Influence Zones…………………………5
2.4蓄水盆之定義…………………………………....….6
2.5 浸泡法(Immersion)的定義………………………….6
2.6分水嶺演算法之流程……………………………….…6
第三章 提出之新分水嶺演算法………………………..10
3.1前處理步驟……………………………………………12
3.2分水嶺處理流程……………………………………..13
第四章 測試結果…………………………………………20
4.1 實際影像之測試…………………………………….20
4.2 梯度臨界值及區域臨界值之定義………………….29
第五章 FPGA模擬…………………………………………37
5.1 決定標籤值………………………………………….37
5.2 記錄座標值及區域大小…………………………….39
第六章 討論…………………………………………….45
參考書目………………………………………………….47
[1] L. Vincent & P. Soille, “Watersheds in digital spaces: An efficient algorithm based on immersion simulations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, pp. 583-597, June 1991.
[2] C.J. Kuo; S.F. Odeh & M.C. Huang, “Image segmentation with improved watershed algorithm and its FPGA implementation,” The 2001 IEEE International Symposium on , Volume: 2 , 6-9 May 2001
Pages:753 - 756 vol. 2
[3] A. Moga, B. Cramariuc & M. Gabbouj, “An efficient watershed segmentation algorithm suitable for parallel implementation,” Proceedings of International Conference on Image Processing, vol. 2, pp. 101-104, Oct. 1995.
[4] J.M. Gauch, “Image segmentation and analysis via multiscale gradient watershed hierarchies,” IEEE Transactions on image processing, vol. 8, Jan. 1999.
[5] D. Hagyard, M. Razaz & P. Atkin, “Analysis of watershed algorithms for grayscale images,” Proceedings of International Conference on Image Processing, vol. 3, pp. 41-44, Oct. 1996.
[6] J.B. Meijster & T.M. Roerdink, “A proposal for the implementation of a parallel watershed algorithm,” Proceedings of CAIP, 1995.
[7] A.N. Moga & M. Gabbouj, “A parallel marker based watershed transformation,” Proceedings of International Conference on Image Processing, vol. 2, pp. 137 —140, 1996.
[8] A.N. Moga & M. gobbouj, “Parallel image component labeling with watershed transformation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, pp. 441-450, May 1997.
[9] M. Fisher & R. Aldrige, “Hierarchical image segmentation using a watershed scale-space tree,” IEE Image Processing and its Applications, conference Publication, No. 456, 1999.
[10] K. Haris, S.N. Efstratiadis, N. Maglaveras & A. K. Katsaggelos, “Watershed-based image segmentation with fast region merging,” Proceedings of International Conference on Image Processing, vol. 3, pp. 338-342, 1998.
[11] K. Haris, S.N. Efstratiadis, N. Maglaveras & A.K. Katsaggelos, “Hybrid image segmentation using watersheds and fast region merging,” IEEE Transactions on Image Processing, vol. 7, Dec. 1998.
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