Please use this identifier to cite or link to this item:
Feature-Based Disconnected Object Contour Linker Based on Canny Edge detector and Genetic Algorithm
|關鍵字:||錯誤邊緣切割;false edge segment;canny 邊緣偵測;梯度;梯度方向;基因演算法;canny edge detector;gradient;gradient direction;genetic algorithm||出版社:||資訊管理學系所||引用:|| P. Bao, L. Zhang, and X. Wu, “Canny Edge Detection Enhancement by Scale Multiplication,” September 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 9, pp. 1485–1490  F. Benmansour, L. D. Cohen, “Fast Object Segmentation by Growing Minimal Paths from a Single Point on 2D or 3D Images,” 2009, Journal of Mathematical Imaging and Vision, pp. 209-221.  J. Canny, “A Computational Approach to Edge Detection,” November 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8, No. 6, pp. 679–698.  R. C. Gonzalez, R. E. Woods, “Digital Image Processing,” Englewood Cliffs, NJ: Prentice-Hall, 2002.  M. Kass, A. Witkin, and D. Terzopoulos, “Snakes - Active Contour Models,” 1987, International Journal of Computer Vision, Vol. 1, No. 4, pp. 321-331.  K. F. Man, K. S. Tang, and S. Kwong, “Genetic Algorithms: Concepts and Designs, Springer-Verlag,” 1999, New York.  U. Maulik, “Medical Image Segmentation Using Genetic Algorithms,” 2009, IEEE Transactions on Information Technology in Biomedicine, Vol. 13, No. 2, pp. 166-173.  S. Osher, R. Fedkiw, “Level Set Methods and Dynamic Implicit Surfaces”, Springer-Verlag, 2003, New York.  C. L. Phillips, “The Level-Set Method,” June 1999, MIT Undergraduate Journal of Mathematics, No. 1, pp. 155-164.  S. Ravishankar, A. Jain, and A. Mittal, “Multi-Stage Contour Based Detection of Deformable Objects,” 2008, ECCV 2008, Part I, LNCS 5302, pp. 483–496.  J.A. Sethian, “Level Set Methods and Fast Marching Methods”, Cambridge: Cambridge, University Press, 1999, New York.  M. Sezgin, B. Sankur, “Survey over Image Thresholding Techniques and Quantitative Performance Evaluation,” January 2004, Journal of Electronic Imaging, Vol. 13, No. 1, pp. 146–165  C. Xu, J. L. Prince “Gradident Vector Flow: A New External Force for Snakes,” 1997, IEEE Computer Society Conference on Pattern Recognition, pp. 66-71.  Y. S. Yun, “Hybrid Genetic Algorithm with Adaptive Local Search Scheme,” 2006, Computers and Industrial Engineering, Vol. 51, No. 1, pp. 128-141.  H. Zhao, G. Qin, and X. Wang, “Improvement of canny algorithm based on pavement edge detection,” 16-18 October 2010, 2010 3rd International Congress on Image and Signal Processing (CISP), Vol. 2, pp. 964-967||摘要:||
Object contour detection is very important in image processing. There are many edge and object contour detectors that have been proposed, such as, Canny edge detector, ACM, and level set methods. However, those detection methods have some drawbacks which lead to the incomplete edge and object contours. More precisely, in the ACM and level set methods, the initial contour of object has to be specified by a user in advance, and the segmentation results highly depend on the given initial contour. Besides, the ACM and level set methods are significantly sensitive to noise. Although Canny edge detector does not need to give any initial contour of object, it may bring about “broken edge problem.” To solve the broken edge problem and to generate the most suitable parameters, a feature-based disconnected object contour segments (FBDOC) linker based on Canny edge detector and genetic algorithm is provided in this thesis.
To extract objects from an image, in this thesis Canny edge detector is first used to detect the object contour, and then the FBDOC linker is employed to link the disconnected edge segments based on the features of the gray-level difference at vicinity of, the gradient and gradient direction on, and the length of the line segment which connects two disconnected edge segments. Finally, the genetic-based parameter detector (GBPD) is used to find the most suitable parameters continuously until the fitness function is convergent.
The experimental results show that the FBDOC linker can get the suitable parameters to use, and give more impressive object segmentation results.
|Appears in Collections:||資訊管理學系|
Show full item record
TAIR Related Article
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.