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:2025/02/19 11:05
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:王禎澤
研究生(外文):Chen-Tse Wang
論文名稱:利用霍夫反演轉換達成圓與弧的影像偵測
論文名稱(外文):Detection of Arcs and Circles in Images Using Hough and Inversion Transforms
指導教授:黃博惠黃博惠引用關係
指導教授(外文):Po-Whei Huang
口試委員:林芬蘭李朱慧
口試日期:2017-07-25
學位類別:碩士
校院名稱:國立中興大學
系所名稱:資訊工程學系所
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:2017
畢業學年度:105
語文別:中文
論文頁數:22
中文關鍵詞:圓與弧偵測圓霍夫轉換霍夫反演轉換物件識別
外文關鍵詞:Circle and arc detectionCircular Hough TransformHough Inversion TransformObject Recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:166
  • 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
本論文提出了一種嶄新的方法,利用霍夫反演變換來達到圓與弧的偵測,此方法首先使用反演變換將圓轉換為直線,其次使用霍夫轉換來偵測經轉換得來的直線,最後使用隨機抽樣一致算法抽取資訊並排除雜訊來達成偵測。
為了降低空間複雜度以及誤差,霍夫反演變換使用二維的累加器而非傳統霍夫變換所使用的三維累加器。本論文以人造影像及實拍照片做實驗,驗證結果:即便輸入資料受到強烈的缺損,本方法亦能提供精準的回傳值。
A novel detection method for arcs and circles in images using Hough and Inversion Transforms (HIT) is proposed in this thesis. In this method, circles in the image are converted into lines first by Hough Inverse transform. Then, Hough transform is used to detect those lines. Finally, Random Sample Consensus is used to extract desired information and remove irrelevant data. To reduce space complexity and deviation, the HIT uses a two-dimensional rather than a three-dimensional accumulator usually used by the traditional Circular Hough Transform. Experimental results show that the proposed method can detect circles and arcs accurately in both of synthetic and real images even though the target objects may have defects.
摘要 i
Abstract ii
目錄 iii
表目錄 iv
圖目錄 iv
第一章. 導論 1
第二章. 相關研究 2
2.1. Circular Hough Transform (CHT) 2
2.2. 取邊緣任意三點圓進行迭代 2
第三章. 霍夫反演變換 3
3.1. 反演變換 3
3.2. 霍夫變換 5
3.3. 隨機抽樣一致算法(RANSAC) 7
3.4. 匹配 9
第四章. 實驗結果 10
4.1. 精準度測試 10
4.2. 缺損測試 14
4.3. 耗費時間 16
4.4. 真實相片 17
第五章. 結論 20
References 21
[1]SHAPIRO, Linda G.; STOCKMAN, G. C. Computer Vision: Theory and Applications. 2001.
[2]DUDA, Richard O.; HART, Peter E. Use of the Hough transformation to detect lines and curves in pictures. Communications of the ACM, 1972, 15.1: 11-15.
[3]CANNY, John. A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence, 1986, 6: 679-698.
[4]FISCHLER, Martin A.; BOLLES, Robert C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 1981, 24.6: 381-395.
[5]FITZGIBBON, Andrew W., et al. A buyer's guide to conic fitting. DAI Research paper, 1996.
[6]GANDER, Walter; GOLUB, Gene H.; STREBEL, Rolf. Least-squares fitting of circles and ellipses. BIT Numerical Mathematics, 1994, 34.4: 558-578.
[7]XU, Lei; OJA, Erkki; KULTANEN, Pekka. A new curve detection method: randomized Hough transform (RHT). Pattern recognition letters, 1990, 11.5: 331-338.
[8]D'ORAZIO, Tiziana, et al. A new algorithm for ball recognition using circle Hough transform and neural classifier. Pattern recognition, 2004, 37.3: 393-408.
[9]BASAK, Jayanta; PAL, Sankar K. Theoretical quantification of shape distortion in fuzzy Hough transform. Fuzzy sets and systems, 2005, 154.2: 227-250.
[10]GOULERMAS, John Yannis; LIATSIS, Panos. Genetically fine-tuning the hough transform feature space, for the detection of circular objects. Image and Vision Computing, 1998, 16.9: 615-625.
[11]GUO, Si-yu; ZHANG, Xu-fang; ZHANG, Fan. Adaptive randomized Hough transform for circle detection using moving window. In: Machine Learning and Cybernetics, 2006 International Conference on. IEEE, 2006. p. 3880-3885.
[12]ILLINGWORTH, John; KITTLER, Josef. The adaptive Hough transform. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 5: 690-698.
[13]IRWANSYAH, Arif, et al. FPGA-based circular hough transform with graph clustering for vision-based multi-robot tracking. In: ReConFigurable Computing and FPGAs (ReConFig), 2015 International Conference on. IEEE, 2015. p. 1-8.
[14]NI, Jianjun, et al. Automatic detection and counting of circular shaped overlapped objects using circular hough transform and contour detection. In: Intelligent Control and Automation (WCICA), 2016 12th World Congress on. IEEE, 2016. p. 2902-2906.
[15]LESTRIANDOKO, Nova Hadi; SADIKIN, Rifki. Circle detection based on hough transform and Mexican Hat filter. In: Computer, Control, Informatics and its Applications (IC3INA), 2016 International Conference on. IEEE, 2016. p. 153-157.
[16]RIZON, Mohamed, et al. Object detection using circular Hough transform. 2005.
[17]ZHU, Gui-ying; ZHANG, Rui-lin. Circle detection using Hough transform [J]. Computer Engineering and Design, 2008, 6: 045.
[18]DJEKOUNE, A. Oualid; MESSAOUDI, Khadija; BELHOCINE, Mahmoud. A New Modified Hough Transform Method for Circle Detection. In: IJCCI. 2013. p. 5-12.
[19]AYALA-RAMIREZ, Victor, et al. Circle detection on images using genetic algorithms. Pattern Recognition Letters, 2006, 27.6: 652-657.
[20]CUEVAS, Erik, et al. Circle detection using electro-magnetism optimization. Information Sciences, 2012, 182.1: 40-55.
[21]YIN, Peng-Yeng. A new circle/ellipse detector using genetic algorithms. Pattern Recognition Letters, 1999, 20.7: 731-740.
[22]LUTTON, Evelyne; MARTINEZ, Patrice. A genetic algorithm for the detection of 2D geometric primitives in images. In: Pattern Recognition, 1994. Vol. 1-Conference A: Computer Vision & Image Processing., Proceedings of the 12th IAPR International Conference on. IEEE, 1994. p. 526-528.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top