跳到主要內容

臺灣博碩士論文加值系統

(35.175.191.36) 您好!臺灣時間:2021/08/01 00:52
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:李妍歆
研究生(外文):Lee, Yen-Hsin
論文名稱:紋理辨識演算法之研究
論文名稱(外文):A Study on Texture Recognition Algorithms
指導教授:郝樹聲郝樹聲引用關係
指導教授(外文):Hao, Shu-Sheng
口試委員:劉正瑜張耀鴻瞿忠正郝樹聲
口試委員(外文):Liu, Cheng-YuZhang, Yao-HongChiu, Chung-ChengHao, Shu-Sheng
口試日期:2012-05-15
學位類別:碩士
校院名稱:國防大學理工學院
系所名稱:電子工程碩士班
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:2012
畢業學年度:100
語文別:中文
論文頁數:57
中文關鍵詞:紋理辨識樣式共生矩陣區域樣式共生矩陣
外文關鍵詞:Texture RecognitionMotif Co-occurrence MatrixROI MCM
相關次數:
  • 被引用被引用:0
  • 點閱點閱:282
  • 評分評分:
  • 下載下載:10
  • 收藏至我的研究室書目清單書目收藏:0
由於科技的日新月異,電腦、相機、照像型手機以及平板電腦的普及化,現在數位影像已成為人們生活中隨手可得的資訊,也因為數位影像的資訊量日益龐大,如何有效的而快速的影像檢索變成一門重要的課題。本論文首先對影像進行色彩空間轉換,將彩色影像轉成灰階影像,經由邊緣偵測後,再進行型態濾波處理,接著對影像做區域填補和連通元件的抽取,再尋找垂直投影量和水平投影量的最大值以及平均值,完成特徵區域中心定位,接著使用區域(Region of Interest﹐ROI)樣式共生矩陣(Motif Co-occurrence Matrix﹐MCM)稱為RMCM來計算影像各點像素與鄰近像素之關係,每一個2 x 2的像素轉換成一個圖形樣式(motif),統計鄰近的motif次數與計算motif與motif之間的距離關係得到特徵值。接著使用歐幾里德距離作為影像特徵相似性比對之計算。本論文之研究主要探討針對特徵區域中心進行特徵擷取的方法,此方法可以濾掉過多的雜訊以及不重要的背景,提高原本利用整張影像去做特徵擷取的辨識率。本研究使用部分影像結合區域樣式共生矩陣與特徵區域中心定位兩種演算法,單張平均處理時間為0.82秒,比MCM方法快2.57倍,所獲得的辨識率分別是,車輛的正確性為95%,花朵的正確性為90%,建築物的正確性為88%,本研究方法的準確度與辨識率的表現較其他方法更為優異,處理時間也更短,顯示本論文研究的實用性與可行性。
As the fast developing of new technologies of the multimedia devices, we are possibly receiving huge amount of images from daily life. Once these images have been stored, how to retrieve the desired pictures quickly and accurately from database is becoming a main issue. In this thesis, we intend to develop an efficient texture recognition algorithm. Using this algorithm, we can retrieve the desired images similar to the input sample images. Our research images include vehicles, buildings, flowers and other natural scenes.
First, we make the color space transformation to separate the luminance and chrominance planes. Second, we apply the edge and the morphological filter on the grey scale images to refill and extract the interesting objects from the image. Third, the vertical and horizontal projection method is applied to find the maximum and mean projection values to locate the center of the interesting objects. Fourth, we develop a texture recognition algorithm called Region of Interest (ROI) Motif Co-occurrence Matrix (RMCM) to find the relation of the neighboring pixels on the image. In this algorithm, we need to generate a 2 x 2 pattern called motif. The main idea of this algorithm is how to fast and accurate to find the characteristic values of motif. Finally, we can compare the Euclidean distance of these characteristic values form motif to locate the most similar image from database.
In our develop algorithm we combine the partly area motif and characteristic area center location methods to raise the accuracy of recognition and speed the recognition. Using our proposed RMCM, the mean processing time is about 0.82 seconds per image. This value is about 2.57 times faster than using Motif Co-occurrence Matrix (MCM). The accuracies are about 95%、90% and 88% related to vehicles, flowers and buildings.
誌謝 ii
摘要 iv
ABSTRACT v
目錄 vi
表目錄 viii
圖目錄 ix
1. 緒論 1
1.1 研究動機與目的 1
1.2 文獻探討 2
1.3 研究系統流程 3
1.4 論文架構 4
2. 背景知識 5
2.1 色彩空間 5
2.1.1 YIQ色彩空間 6
2.1.2 HSI色彩空間 6
2.2 邊緣偵測 8
2.2.1 LoG邊緣偵測法 10
2.2.2 Sobel邊緣偵測法 10
2.3 形態學處理 11
2.3.1 膨脹 11
2.3.2 侵蝕 12
2.3.3 斷開 12
2.3.4 閉合 12
2.4 區域填補 14
2.5 連通元件抽取 16
3. 影像特徵擷取與方法 18
3.1 樣式共生矩陣 18
3.2 區域樣式共生矩陣與特徵區域中心定位 22
4. 實驗流程與結果 31
4.1 實驗流程 31
4.2 影像距離比對 49
4.3 實驗辨識結果 49
4.3.1區域樣式共生矩陣(RMCM)實驗結果 50
5. 結論 54
參考文獻 55
自傳 57

[1]Huang, P. W. and Dai, S. K., “Image Retrieval by Texture Similarity,” Pattern Recognition, Vol. 36, pp. 665-679, 2003.
[2]Jhanwar, N., Chaudhuri, S., Seetharaman, G., and Zavidovique, B., “Content Based Image Retrieval using Motif Co-occurrence Matrix,” Image and Vision Computing, Vol. 22, pp. 1211-1220, 2004.
[3]蔡育忠,“影像紋理辨識之研究”,碩士論文,國防大學,桃園,2010。
[4]Seetharaman, G. S. and Zavidovique, B., “Image Processing in a Tree of Peano Coded Images,” Computer Architecture for Machine Perception. CAMP '97. Proceedings Fourth IEEE International Workshop on, pp. 229-234, 1997.
[5]Seetharaman, G., Zavidovique, B., and Shivayogimath, S., “Z-trees: Adaptive Pyramid-Algorithms for Image Segmentation,” in Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on, Vol. 3, pp. 294-298, 1998.
[6]Peano, G., “Sur Une Courbe Qui Remplit Toute Une Aire Plaine,” Mathematische Annalen-MATH ANN , Vol. 36, no. 1, pp. 157-160, 1890.
[7]Lin, C. H., Chen, R. T., and Chan, Y. K., “A Smart Content-Based Image Retrieval System Based on Color and Texture Feature,” Image and Vision Computing, Vol. 27, pp. 658-665, 2009.
[8]Su, M. C. and Chou, C. H., “A Modified Version of the K-means Algorithm with a Distance Based on Cluster Symmetry,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 23, pp. 674-680, 2001.
[9]Liu, D. and Yu, J., “Otsu Method and K-means”, Ninth International Conference on Hybrid Intelligent Systems, 2009. HIS '09, Vol. 1, pp. 344-349, 2009.
[10]Dehariya, V. K., Shrivastava, S. K., and Jain, R. C., “Clustering of Image Data Set Using K-Means and Fuzzy K-Means Algorithms”, 2010 International Conference on Computational Intelligence and Communication Networks (CICN), pp. 386-391, 2010.
[11]http://ccckmit.wikidot.com/ai:kmeans
[12]張智菁,“衛星影像目標辨識之研究”,碩士論文,國防大學,桃園,2011。
[13]Michael, W. S., William, B. C., and John, C. B., “An Experimental Comparison of RGB, YIQ, LAB, HSV, and Opponent Color Models,” ACM Transactions on Graphics, Vol. 6, no. 2, pp. 123-158, 1987.
[14]繆紹綱,數位影像處理,普林斯頓國際有限公司,第364-392頁,2007。
[15]Marr, D. and Hildreth, E., “Theory of Edge Detection,” Proceedings of the Royal Society of London, Vol. B207, pp. 187-217, 1980.
[16]Basart, J. P. and Gonzalez, R. C., “Binary Morphology,” in Advances in Image Analysis, Y. Mahdavieh and R. C. Gonzalez (eds.), SPIE Press, Bellingham, Wash., pp.277-305, 1992.
[17]Basart, J. P., Chacklackal, M. S., and Gonzalez, R. C., “Introduction to Gray-Scale Morphology,” in Advances in Image Analysis, Y. Mahdavieh and R. C. Gonzalez (eds.), SPIE Press, Bellingham, Wash., pp. 306-354, 1992.
[18]Haralick, R. M. and Shapiro, L. G., Computer and Robot Vision, Addison Wesley, Vol. 1, 1992.
[19]Nathan, K. and Henry, W., Euclidean Distance Matrices and Applications, Springer Science Business Media, LLC, Canada, pp. 879-914, 2012.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top