跳到主要內容

臺灣博碩士論文加值系統

(3.236.124.56) 您好!臺灣時間:2021/07/31 07:21
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:盧奕帆
研究生(外文):I-Fan Lu
論文名稱:無參數需求之高精準度與高強健性影像切割演算法
論文名稱(外文):High Accuracy and High Robust Natural Image Segmentation Algorithm without Parameter Adjusting
指導教授:丁建均丁建均引用關係
口試委員:郭景明葉敏宏簡鳳村
口試日期:2015-06-10
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電信工程學研究所
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:2015
畢業學年度:103
語文別:英文
論文頁數:90
中文關鍵詞:影像分割基於熵率的超像素邊緣偵測顯著影像偵測電腦視覺
外文關鍵詞:Image segmentationERS superpixelsedge detectionsaliency detectioncomputer vision
相關次數:
  • 被引用被引用:0
  • 點閱點閱:205
  • 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
在電腦視覺和影像處理的領域中,影像分割一直是重要的基礎工作。雖然本主題已經被研究了許多年,然而,要如何在全自動、無需調整參數的前提下,仍然可以將大部分的自然影像精準的分割,仍然是一項具有挑戰性的任務。此外,近年來關於超像素(superpixel) 的研究有很大的進展,這種新技術使傳統的影像分割演算法具有更高的效率和更好的性能。在這篇論文中,我們將提出一種運用超像素等多項技術的「全自動」影像分割方法,使用者無需輸入參數或是調整參數即可得到高精確度的影像分割結果。
我們的演算法採用了基於熵率的超像素(ERSs)、邊緣偵測、顯著影像偵測以及計算紋理特徵等技術。將原始影像轉為基於熵率的超像素表示,使得演算法效率大幅提高。透過計算超像素周邊以及內部的梯度資訊,傳統的邊緣偵測得以修正,進一步防止超像素過度合併。利用顯著影像偵測與計算紋理特徵,超像素合併的門檻值可根據影像作自適應調整,避免影像過度分割。模擬結果顯示,對於任意自然影像的分割處理,我們方法表現的分割結果相當符合人類感知,且不需要額外的參數調整,而這也超越了其他現有已知最先進的方法的模擬結果。

In computer vision and image processing, image segmentation is always an important fundamental work. Though this topic has been researched for many years, it is still a challenging task to well segment most of the natural images automatically without adjusting any parameter. Recently, the researches of superpixels have great improvement. This new technique makes the traditional segmentation algorithms more efficient and has better performances. In this thesis, an automatic image segmentation algorithm based on superpixels and many other techniques is proposed. It can accurately segment almost all of the natural images without parameter adjustment.
In our algorithm, the techniques of entropy rate superpixels (ERSs), edge detection, saliency detection, and computing texture feature are adopted. With the aid of ERSs, the proposed algorithm can be implemented very efficiently. To prevent over-merge of superpixels, modified edge detection which computes the gradient information of the contours and the interiors of superpixels is used. Saliency detection and the texture features of an image are also used to prevent over-segmentation. Moreover, an adaptive threshold is also used for superpixel merging. These techniques make the segmentation result more consistent with human perception without adjusting any parameter. Simulations show that our proposed method can well segment most of natural images and outperform state-of-the-art methods.

口試委員會審定書 #
誌謝 i
中文摘要 ii
ABSTRACT iii
CONTENTS iv
LIST OF FIGURES vii
LIST OF TABLES ix
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Main Contribution 2
1.3 Organization 2
Chapter 2 Reviews of Segmentation Algorithms 4
2.1 Mean Shift 4
2.1.1 About Mean Shift 4
2.1.2 The Algorithm 5
2.1.3 Simulation Results 5
2.2 Watershed Approach 6
2.2.1 About Watershed Approach 6
2.2.2 The Algorithm 7
2.2.3 Simulation Results 8
2.3 Normalized Cut 9
2.3.1 About Normalized Cut 9
2.3.2 The Grouping Algorithm 11
2.3.3 Simulation Results 13
2.3.4 Multiscale Normalized Cut (MNCut) 14
2.4 Efficient Graph-based Segmentation 15
2.4.1 About Efficient Graph-based Segmentation 15
2.4.2 The Algorithm 17
2.4.3 Simulation Results 19
Chapter 3 Reviews of Superpixels and Superpixel-based Segmentation Algorithms 20
3.1 Introduction of Superpixel 20
3.2 Simple Linear Iterative Clustering Superpixels 21
3.2.1 About Simple Linear Iterative Clustering Superpixels 21
3.2.2 The Algorithm 24
3.2.3 Simulation Results and Discussion 25
3.3 Entropy Rate Superpixel Segmentation 26
3.3.1 About Entropy Rate Superpixel Segmentation 26
3.3.2 Preliminaries of this Method 27
3.3.3 Problem Formulation and Algorithm 28
3.3.4 Conclusion and Simulation Results 30
3.4 Segmentation by Aggregating Superpixels (SAS) 32
3.4.1 About Segmentation by Aggregating Superpixels 32
3.4.2 The Algorithm 36
3.4.3 Simulation Results and Discussion 38
3.5 Learning Full Pairwise Affinities for Spectral Segmentation (MLSS) 39
3.5.1 About MLSS (Multi-Layer Spectral Segmentation) 39
3.5.2 The Algorithm 39
3.5.3 Simulation Results 40
Chapter 4 Proposed Algorithm 42
4.1 Introduction 42
4.2 Superpixel Generation and Saliency Detection 45
4.2.1 Superpixel Generation 45
4.2.2 Saliency Detection 46
4.3 Modified Edge Detection and Texture Features 48
4.3.1 Modified Edge Detection 48
4.3.2 Texture Features 51
4.4 Proposed Segmentation Algorithm 53
4.5 Analysis of Our Algorithm 58
Chapter 5 Simulations 65
5.1 Compared with the state-of-the-art methods 65
5.1.1 Database 65
5.1.2 Visual Comparison 68
5.2 Compared with the MLSS method and the SAS method 77
Chapter 6 Conclusion and Future Work 84
6.1 Conclusion 84
6.2 Future Work 85
REFERENCE 86
PUBLICATION 90

A.Image Segmentation
[1] J. Shi and J. Malik, “Normalized Cuts and Image Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, Aug. 2000.
[2]P. Felzenszwalb and D. Huttenlocher, “Efficient Graph-Based Image Segmentation,” Int’l J. Computer Vision, vol. 59, no. 2, pp. 167-181, Sept. 2004.
[3]V. Kwatra, A. Schodl, I. Essa, G. Turk, and A. Bobick, “Graphcut Textures: Image and Video Synthesis Using Graph Cuts,” ACM Trans. Graphics,vol. 22, no. 3, pp. 277-286, July 2003.
[4]D. Comaniciu and P. Meer, “Mean Shift: A Robust Approach toward Feature Space Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619, May 2002.
[5]A. Vedaldi and S. Soatto, “Quick Shift and Kernel Methods for Mode Seeking,” Proc. European Conf. Computer Vision, 2008.
[6]L. Vincent and P. Soille, “Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-598, June 1991.
[7]Y. Weiss, “Segmentation Using Eigenvectors: A Unifying View,”Proc. IEEE Int’l Conf. Computer Vision, 1999.
[8]P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik, “Contour Detection and Hierarchical Image Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 898-916, May 2011.
[9]T. Cour, F. Benezit, J. Shi, “Spectral segmentation with multiscale graph decomposition,” in CVPR, pp. 1124-1131, 2005.
[10]L. Najman and M. Schmitt, “Geodesic Saliency of Watershed Contours and Hierarchical Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 12, pp. 1163-1173, Dec. 1996.
[11] Z. Lin, J. Jin and H. Talbot, “Unseeded region growing for 3D image segmentation,” ACM International Conference Proceeding Series, vol. 9, pp. 31-37, 2000.

B.Superpixel
[12]A. Moore, S. Prince, J. Warrell, U. Mohammed, and G. Jones, “Superpixel Lattices,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[13]S. Avidan and A. Shamir, “Seam Carving for Content-Aware Image Resizing,” ACM Trans. Graphics, vol. 26, no. 3, Article 10, 2007.
[14]O. Veksler, Y. Boykov, and P. Mehrani, “Superpixels and Supervoxels in an Energy Optimization Framework,” Proc. European Conf. Computer Vision, 2010.
[15]R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Süsstrunk, “SLIC superpixels compared to state-of-the-art superpixel methods,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274 - 2282, May 2012.
[16]Y. M. Liu, O. Tuzel, S. Ramalingam, and R. Chellappa, “Entropy rate superpixel segmentation,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097-2104, 2011.

C.Superpixel-Based Segmentation
[17]Z. Li, X. M. Wu, and S. F. Chang, “Segmentation Using Superpixels: A Bipartite Graph Partitioning Approach,” in CVPR, pp. 789-796, 2012.
[18]T. Kim and K. Lee, “Learning full pairwise affinities for spectral segmentation,” in CVPR, pp. 2101-2108, 2010.


D.Clustering Techniques
[19]S.X. Yu and J. Shi, “Multiclass Spectral Clustering,” Proc. IEEE Int’l Conf. Computer Vision, 2003.
[20] A. Y. Ng, M. I. Jordan, and Y. Weiss, “On spectral clustering: Analysis and an algorithm,” Advances in neural information processing systems, vol. 2, pp. 849–856, 2002.
[21] I. Dhillon, “Co-clustering documents and words using bipartite spectral graph partitioning,” In ACM SIGKDD, pp. 269-274, 2001

E.Computer Vision
[22]D. Zhou, O. Bousquet, T.N. Lal, J. Weston, and B. Scho‥lkopf, “Learning with Local and Global Consistency,” Proc. Neural Information Processing Systems, 2003.
[23]P. Arbelaez, “Boundary Extraction in Natural Images Using Ultrametric Contour Maps,” Proc. IEEE Workshop Perceptual Organization in Computer Vision, 2006.

F.Saliency Detection
[24]C. Yang, L. Zhang, H. Lu, X. Ruan, and M.-H. Yang, “Saliency detection via graph-based manifold ranking,” in CVPR, 2013.
[25]L. Grady, M. Jolly, and A. Seitz, “Segmenation from a box,” in ICCV, 2011.

G.Edge Detection
[26]P. Acharjya, R. Das, and D. Ghoshal, “A Study on Image Edge Detection Using the Gradients,” International Journal of Scientific and Research Publications, vol. 2, Issue 12, Dec. 2012.
[27]LS. Davis, “A survey of edge detection techniques,” Computer Graphics and Image Processing, vol 4, no. 3, pp 248-260, 1975.

H.Theorems and Mathematics
[28]Field, David J. “Relations between the statistics of natural images and the response properties of cortical cells,” JOSA A 4.12 (1987): 2379-2394.
[29] G. Golub and C. Van Loan. Matrix computations. Johns Hopkins University Press, 1996.

I.Specular-Free Image
[30] R. T. Tan, K. Ikeuchi, “Separating reflection components of textured surfaces using a single image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 2, 2005.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top