跳到主要內容

臺灣博碩士論文加值系統

(44.210.99.209) 您好!臺灣時間:2024/04/14 16:27
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:林雅婷
研究生(外文):Ya-Ting Lin
論文名稱:植基於適性門檻之紋理影像切割
論文名稱(外文):Texture Image Segmentation Using Adaptive Thresholding
指導教授:廖士寬
指導教授(外文):Shih-Kuan Liao
學位類別:碩士
校院名稱:臺中技術學院
系所名稱:資訊科技與應用研究所
學門:電算機學門
學類:電算機應用學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:62
中文關鍵詞:影像切割紋理特徵適性門檻
外文關鍵詞:Image segmentationTexture featureAdaptive threshold
相關次數:
  • 被引用被引用:0
  • 點閱點閱:191
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
紋理在影像處理中是一門重要課題,延伸了許多應用如影像切割、影像查詢、物件辨識等。影像切割在系統應用中屬於前處理步驟,切割的好壞往往佔有很大的影響。本研究貢獻在利用適性門檻有效的進行紋理影像切割,其適性門檻值可隨著訓練影像的特性調門檻值,當作評估相似紋理區域的依據。

本研究提出適性門檻(adaptive threshold)作為相似紋理評估,改良Huang[24]的切割演算法,切割影像中不同紋理的區域。在紋理特徵方面,採用Color Co-Occurrence Matrix(CCM)及Difference between Pixels of Scan Patter(DBPSP),CCM描述著影像中鄰近像素之間的像素變化的關係產生共生矩陣,DBPSP則是描述鄰近像素之間的像素值變化的程度。在紋理影像切割的研究中,傳統的分裂合併法受到固定門檻值影響,隨著影像中紋理特性的改變,將導致固定門檻值無法根據影像特性切割出不同紋理區域,而本研究根據紋理影像特性訓練出適性門檻,當作評估相似紋理區域的依據。本方法的紋理影像切割流程為影像分裂(image splitting)、聚合合併(agglomerative merging)以及邊界重新調整(boundary refinement),而適性門檻使用在聚合合併步驟。在實驗方面,除了針對不同的紋理影像資料庫,進行適性門檻的影像切割實驗,說明適性門檻可隨著影像的特性進行調整,並與其他方法比較切割結果,驗證本研究能夠成功的切割影像中不同紋理的區域。
Texture is one of the important issues in image processing. It was used in many applications such as image segmentation, image retrieval, pattern recognition, and so on. Image segmentation is the pre-processing in many applications; where the segment results affect the following processing. This thesis proposes an adaptive threshold in texture image segmentation. The adaptive threshold can be determined according training images and is used to assess the distance between two similar texture regions.
In an image, regions containing different texture features are recognized as different objects. The directionality relationships of each pixel and its neighbors are described as patterns and the probabilities of the pattern correlations are used as texture features. The conventional split-and-merge procedure method used fixed thresholds in the splitting and the merging processes. However, an adequate threshold is difficult to be determined. We proposed to compute an adaptive threshold according to the texture features in the training images. Our method includes splitting, agglomerative merging, and boundary refinement. The adaptive threshold is used in the agglomerative merging process. The experimental results demonstrated that our method can segment texture objects successfully.
摘要 ii
Abstract iii
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究背景 1
1.2 動機目的 2
1.3 研究架構 3
第二章 文獻探討 4
2.1 影像切割技術 4
2.1.1 以分裂合併法的影像切割 6
2.2紋理特徵描述 9
2.2.1 Color Co-Occurrence Matrix 10
2.2.2 Difference between Pixels of Scan Pattern 17
第三章 研究方法 20
3.1 特徵有效性 20
3.2 切割演算法 25
3.2.1 影像分裂 25
3.2.2 聚合合併 29
3.2.3 邊界調整 34
3.3 適性門檻值 38
第四章 實驗結果與分析 42
4.1 適性門檻分析 42
4.1.1測試影像資料庫 43
4.1.2紋理影像分析 43
4.2 實驗結果 47
4.2.1實驗一 48
4.2.2實驗二 50
4.2.2實驗三 52
4.3 實驗比較與討論 54
4.3.1實驗比較 54
4.3.2討論 57
第五章 結論與展望 59
參考文獻 60
[1]A. K. Jain, F. Farrokhnia, “Unsupervised texture segmentation using Gabor filters”, Pattern Recognition, vol. 24, no. 12, pp.1167-1186, 1991.
[2]A. Hanbury, B. Marcotegui,“Morphological segmentation on learned boundaries”, Image and Vision Computing, vol.27(4), pp.480-488, 2009.
[3]B. M. Mehtre, M. Kankanhalli, W. F. Lee, “Shape Measures for Content-Based Image Retrieval: A Comparison Info,” Processing & Management, Vol. 33, pp. 319–337, 1997.
[4]Brodatz Textures, http://www.ux.uis.no/~tranden/brodatz.html
[5]C. H. Lin, R. T. Chen, Y. K. Chan, “A Smart Content-based Image Retrieval System Based on Color and Texture Feature”, Image and Vision Computing, Vol.27, pp. 658-665, 2009.
[6]D. Martin, C. Fowlkes, D. Tal, J. Malik, “A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics”, Proc. 8th Int''l Conf. Computer Vision, vol. 2, pp.416-423, 2001.
[7]G. Wiselin Jiji, L. Ganesan, “A new approach for unsupervised segmentation”, Applied Soft Computing, 2008.
[8]G.P. Babu, B.M. Mehtre, M.S. Kankanhalli, “Color indexing for efficient image retrieval”, Multimedia Tools and Applications, vol. 1, no. 4(1), pp.327-48, 1995.
[9]H. Fu, Z. Chi, D. Feng, ”Attention-driven image interpretation with application to image retrieval”, Pattern Recognition, vol.39, pp.1604-1621, 2006.
[10]H. Zhou, R. Wang, C. Wang, “A novel extended local-binary-pattern operator for texture analysis”, Information Sciences, vol.178(22), pp.4314-4325, 2008.
[11]J. Sklansky, “Image Segmentation and Feature Extraction”, IEEE Transaction on Systems, Man, and Cybernetic, Vol. 8, pp.238-247, 1978.
[12]J. S. Kim, K. S. Hong, ”Color-texture segmentation using unsupervised graph cuts”, Pattern Recognition, vol.42, pp.735-750, 2009.
[13]K. Muneeswaran, L. Ganesan, S. Arumugam, K. Ruba Soundar, ”Texture image segmentation using combined features from spatial and spectral distribution”, Pattern Recognition Letters, vol.27, pp.755-764, 2006.
[14]K. Hammouche, M. Diaf, P. Siarry, “A multilevel automatic thresholding method based on a genetic algorithm for a fast image segmentation”, Computer Vision and Image Understanding, vol.109, pp.163–175, 2008.
[15]K. M. Chen, S. Y. Chen, “Color texture segmentation using feature distributions”, Pattern Recognition Letters, vol.23,pp.755–771, 2002.
[16]L. Gupta, U. G. Mangai, S. Das, ”Integrating region and edge information for texture segmentation using a modified constraint satisfaction neural network”, Image and Vision Computing, vol.26, pp.1106-1117, 2008.
[17]L. Lin, L. Zhu, F. Yang, T. Jiang, ”A novel pixon-representation for image segmentation based on Markov random field”, Image and Vision Computing, vol.26, pp.1507-1514, 2008.
[18]L. Cao, P. Bao, Z. Shi, ”The strongest schema learning GA and its application to multilevel thresholding”, Image and Vision Computing, vol.26, pp.716-724, 2008.
[19]L. Maa, R.C. Stauntonb, “A modified fuzzy C-means image segmentation algorithm for use with uneven illumination patterns”, Pattern Recognition, vol.40, pp.3005–3011, 2007.
[20]M. F. A. Fauzi, P. H. Lewis, ”Automatic texture segmentation for content-based image retrieval application”, Pattern Analysis & Applications, vol.9, pp.307-323, 2006.
[21]N. Jhanwara, S. Chaudhuri, G. Seetharaman, B. Zavidovique, “Content based image retrieval using motif cooccurrence matrix”, Image and Vision Computing, vol.22, pp.1211–1220, 2004.
[22]P. Schroeter and J. Bigun,” Hierarchical image segmentation by multi-dimensional clustering and orientation-adaptive boundary refinement”, Pattern Recognition, Vol.28, PP.695-709, 1995.
[23]P.W. Huang , S.K. Dai, “Image retrieval by texture similarity”, Pattern Recognition, vol.36, pp.665- 679, 2003.
[24]P.W. Huang, S.K. Dai, P.L. Lin, “Texture image retrieval and image segmentation using composite sub-band gradient vectors”, Journal of Visual Communication and Image Representation, vol.17, No. 5, pp. 947-957, 2006.
[25]S. Arivazhagan, L. Ganesan, ”Texture segmentation using wavelet transform”, Pattern Recognition Letters, vol.24, pp.3197-3203, 2003.
[26]T. Ojala, M. Pietikainen, “Unsupervised texture segmentation using feature distributions”, Pattern Recognition, vol.32, pp.477-486, 1999.
[27]X. Qing, Y. Jie, D. Siyi, ”Texture Segmentation using LBP Embedded Region Competition”, Electronic Letters on Computer Vision and Image Analysis, vol.5(1), pp.41-47, 2005.
[28]吳俊霖、曾振益,”改良式自動種子區塊成長之彩色影像分割法”, 南臺灣資訊科技與應用研討會,2007年,台灣,頁59-74。
[29]陳普中,”紋理分析於瑕疪定位及影像檢索之研究”,台灣科技大學電機工程系碩士論文,2003年。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top