| 研究生: |
林松柏 Lin, Sung-Po |
|---|---|
| 論文名稱: |
傳統、小波理論與動態輪廓模式之波浪影像邊緣偵測處理 Traditional , Wavelet and Active ontour Model in Edge Detection Analysis of Wave Image |
| 指導教授: |
黃明志
Huang, Min-Chih |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 系統及船舶機電工程學系 Department of Systems and Naval Mechatronic Engineering |
| 論文出版年: | 2005 |
| 畢業學年度: | 93 |
| 語文別: | 中文 |
| 論文頁數: | 76 |
| 中文關鍵詞: | 邊緣偵測 、動態輪廓模式 、小波 |
| 外文關鍵詞: | edge detection, Snakes, Active contour model, wavelet |
| 相關次數: | 點閱:98 下載:4 |
| 分享至: |
| 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 |
傳統的影像邊緣偵測採用二維差分運算子以偵測影像邊緣,乃假設影像邊緣上和邊緣旁之影像灰階值必然不同,當取微分時,在邊緣上會呈現非常大梯度值。本文以 Prewitt與 Sobel二維差分運算子作影像邊緣偵測。藉由調整影像灰階值的臨界值參數可強化邊緣,亦可更進一步的以骨架法細線化影像邊緣。
二維小波轉換則是一種比較新的影像邊緣偵測方法,當取小波轉換時,在影像邊緣上亦會呈現非常大的梯度值。本文以墨西哥小波作影像邊緣偵測。
在電腦視覺或影像處理上經常使用動態輪廓或蛇行模式來偵測物體的邊界或邊緣。本文採用一個改良的動態輪廓模式,即廣義梯度向量流場蛇形法,來追蹤一高速攝影機在斷面水漕所拍攝之波浪影像序列。本文驗證此方法可準確地追蹤一孤立波在直立壁上造成捲入型碎波時,波形在時間與空間之變化。
本文針對波浪影像邊緣偵測提供三種截然不同的系統處理及分析比較。
NONE
1.Berger, M.O.,Mohr, R.“ Towards autonomy in active contour models,” In Tenth International Conference on Pattern Recognition, Atlantic City, NJ, 847– 851.1990.
2.Cohen,L.D., “On Active Contour Models and Balloons,”Computer Vision and Image Processing: Image Understanding 53(2),pp. 211–218,1991
3.Courant, R., Hilbert, D., Methods of Mathematical Physics, Wiley, New York,Volume l,pp.190,1989
4.Gonzalez, R. C., Woods, R. E., Digital Image Processing 2/e,
Prentice Hall,pp.75-146,pp.519-596,2002
5.Holland, K.T., Holman, R.A., Lippmann, T.C.,Stanley,J., Plant, N., “Practical Use of Video Imagery in Nearshore Oceangraphic Field Studies,”IEEE Journal of Oceanic Engineering 22(1), pp.81-91,1997
6.Hull,P.,Mu¨ller,G.,“Aninvestigation of breaker heights,shapes and pressures,”Ocean Engineering 29(1),pp.59-79,2002
7.Kass, M., Witkin, A., Terzopoulos, D., “Snakes: active contour models,”International Journal of Computer 1(4),pp.321–331, 1988
8.Lee,H.S.,Kwon,S.H.,“Wave profile measuerment by wavelet transform,”Ocean Engineering 30(18),pp. 2313-2328 2003
9.Liu, A. K.,Peng C.Y.,Chang, S. Y.-S.,“Wavelet analysis of satellite images for coastal watch, ”IEEE Journal of Oceanic Engineering 22(1),pp.7-17,1997
10.Lobregt, S., Viergever, M.A. “A discrete dynamic contour model,”IEEE Transactions on Medical Imaging 14(1),pp.12- 24,1995
11.Mallat, S. G.,A wavelet tour of signal processing, Academic Press,pp.1-126,1998
12.Myler, H. R.,Computer imaging recipes in C, PTR Prentice Hall, pp.53-135,1993
13.Neuenschwander, W.M., Fua, P., Ivenson,L., Sze´kely, G., Ku¨bler, O., “Ziplock snakes,”International Journal of Computer Vision 25(3),pp.191–201,1997
14.Russ, J. C. ,The Image Processing Handbook, CRC Press,pp.212- 480,1994
15.Williams,D.J., Shah, M. “A fast algorithm for active contours and curvature estimation, ” Computer Vision and Image Processing:Image Understanding 55(1), pp.14-26,1992
16.Xu,C.,Prince,J.L.,“Snakes, shapes, and gradient vector flow,”IEEE Transactions on Image Processing 7(3),pp.359– 369,1998
17.Xu,C.,Prince,J.L.,“Generalized gradient vector flow external forces for active contours,” Signal Processing — An International Journal, 71 (2), pp. 131-139,1998
18.Yao, A. ,Wu, C.H.,“An automated image-based technique for tracking sequential surface wave profiles,” Ocean Engineering 32(2),pp.157-173,2004
19.劉岳豪“利用影像特徵進行水下檢測影像拼嵌之研究,”國立成功大學碩士論文,2004