請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68597完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 丁建均(Jian-Jiun Ding) | |
| dc.contributor.author | Tzu-Chieh Lin | en |
| dc.contributor.author | 林子傑 | zh_TW |
| dc.date.accessioned | 2021-06-17T02:26:48Z | - |
| dc.date.available | 2018-08-24 | |
| dc.date.copyright | 2017-08-24 | |
| dc.date.issued | 2017 | |
| dc.date.submitted | 2017-08-17 | |
| dc.identifier.citation | REFERENCE
A. Superpixel and Image Segmentation [1] 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. [2] 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. [3] 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. [4] T. Kim and K. Lee, “Learning full pairwise affinities for spectral segmentation,” in CVPR, pp. 2101-2108, 2010. [5] Z. Li, X. M. Wu, and S. F. Chang, “Segmentation using superpixels: A bipartite graph partitioning approach,” in CVPR, pp. 789-796, 2012. [6] S. R. Rao, H. Mobahi, A. Y. Yang, S. S. Sastry, and Y. Ma, “Natural image segmentation with adaptive texture and boundary encoding,” in ACCV, pp. 135-146, 2009. [7] C. Y. Hsu and J. J. Ding, “Efficient image segmentation algorithm using SLIC superpixels and boundary-focused region merging,” in ICICS, pp. 1-5, 2013. [8] Y. Deng and B. S. Manjunath, “Unsupervised segmentation of color-texture regions in images and video,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 8, pp. 800-810, 2001. [9] T. Cour, F. Benezit, and J. Shi, “Spectral segmentation with multiscale graph decomposition,” in CVPR, vol. 2, pp. 1124-1131, 2005 [10] J. Wang, Y. Jia, X. S. Hua, C. Zhang, and L. Quan, “Normalized tree partitioning for image segmentation,” in CVPR, pp. 1-8, 2008. [11] M. Donoser, M. Urschler, M. Hirzer and H. Bischof, 'Saliency driven total variation segmentation,' 2009 IEEE 12th International Conference on Computer Vision, Kyoto, pp. 817-824, 2009. [12] 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. [13] X. Gu, J. D. Deng, and M. K. Purvis, “Improving superpixel-based image segmentation by incorporating color covariance matrix manifolds,” in ICIP, pp. 4403-4406, Oct. 2014. [14] X. Wang, Y. Tang, S. Masnou, and L. Chen, “A Global/Local Affinity Graph for Image Segmentation,” IEEE Trans. Image Processing, vol. 24, no. 4, pp. 1399-1411, 2015. [15] Y. Yang, Y. Wang, and X. Xue, “A novel spectral clustering method with superpixels for image segmentation,” Optik-International Journal for Light and Electron Optics, vol. 127, no. 1, pp. 161-167, 2016. B. Edge Detection [16] P. Dollar and C. L. Zitnick, “Structured forests for fast edge detection,” in ICCV, pp. 1841–1848, 2013. [17] J. J. Lim, C. L. Zitnick and P. Dollár, 'Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection,' 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, pp. 3158-3165, 2013. C. Saliency Detection [18] W. Zhu, S. Liang, Y. Wei and J. Sun, “Saliency optimization from robust background detection,” in CVPR, pp. 2814-2821, 2014. [19] J. Kim, D. Han, Y. W. Tai and J. Kim, 'Salient Region Detection via High-Dimensional Color Transform,' 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, pp. 883-890, 2014. D. Computer Vision [20] 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. [21] G. Sharma, W. Wu and E. Dalal, “The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations,” Color Research & Application, vol. 30, no. 1, pp. 21-30, 2005. E. Theorems and Mathematics [22] Field, David J. “Relations between the statistics of natural images and the response properties of cortical cells,” JOSA A, vol. 4, no.12, pp. 2379-2394, 1987. F. Database and Evaluation Metrics [23] D. Martin, C. Fowlkes, D. Tal, and J. Malik. “A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics,” in ICCV, pp. 416–423, 2001. [24] R. Unnikrishnan, C. Pantofaru, and M. Hebert, “Toward objective evaluation of image segmentation algorithms,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 6, pp. 929-944, 2007. [25] M. Meilǎ, “Comparing clusterings: an axiomatic view,” in ICML, pp. 577-584, 2005. [26] D. Martin, C. Fowlkes, D. Tal, and J. Malik. “A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics,” in ICCV, pp. 416–423, 2001. [27] J. Freixenet, X. Muñoz, D. Raba, J. Martí, X. Cufí, 'Yet another survey in image segmentation: Region and boundary information integration.' in ECCV, pp.408-422, 2002. G. Adopted Image Segmentation Method [28] H. Y. Ko and J. J. Ding, “Adaptive Growing and Merging Algorithm for Image Segmentation” 2016. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68597 | - |
| dc.description.abstract | 影像切割在電腦視覺和影像處理的領域中，扮演著相當重要的基礎處理角色，也有許多的相關應用如物件追蹤與影像壓縮等。現今已經有許多不同類型的影像切割演算法被提出，我們所提出的演算法是基於超像素(superpixel)、色彩、邊緣、質地、顯著值等特徵，進行分階段的超像素生長及適應性合併，用以將原始影像切割為使用者所希望的區域數。使用超像素生成局部區域資訊可以提升演算法整體運算效率，個別超像素的色彩及質地資訊是我們做為初步超像素生長的依據，超像素相接區域的邊緣梯度資訊則做為抑制超像素生長的因素，透過衡量原始影像的景物區隔性和計算顯著值，可以避免超像素被過度合併破壞物體資訊。在最後的適應性合併階段中，達到使用者輸入的原始影像切割區域數之前，合併過程會適應剩餘區域數。
若衡量原始影像的景物區隔性質方法應用在醫學影像上，可以估測出不同的細胞影像拍攝亮度，以調整套用在細胞切割演算法的亮度門檻值，可以改善經由影像亮度門檻值選取細胞區域的結果表現。 | zh_TW |
| dc.description.abstract | As a basic preprocessing procedure, image segmentation plays an important role in computer vision and image processing. There are many applications for image segmentation, such as object recognition and image compression. Recently, different kinds of image segmentation algorithms have been proposed.
In this thesis, we propose an image segmentation algorithm based on superpixel, color, edge, texture and saliency information. The algorithm is designed to segment image into a certain number of regions assigned by the user. By using the superpixel information, one can improve the computation efficiency. The color and texture information of superpixels are mainly used in the superpixel growing process. On the contrast, the edge information on the boundary of two adjacent superpixels is used for determining whether the two superpixels should be prevented from merging. Saliency information is also a factor to suppress the merging process in order to keep the object integrity. In addition, we adjust the weight of edge, texture, and saliency information by measuring the foreground significance. In the adaptive region merging process, the merging criterion will be adaptive to the current region number. When the foreground significance is applied to medical cell image, we can estimate the imaging characteristic such that a better threshold can be chosen and further improve the cell image segmentation and tracing result. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T02:26:48Z (GMT). No. of bitstreams: 1 ntu-106-R04942101-1.pdf: 5528433 bytes, checksum: b57384e6b863305ca215374665a0d3c6 (MD5) Previous issue date: 2017 | en |
| dc.description.tableofcontents | CONTENTS
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 x Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Main Contribution 2 1.3 Organization 2 Chapter 2 Reviews of Superpixel and Resent Image Segmentation Algorithms 3 2.1 Mean Shift Superpixel 3 2.1.1 About Mean Shift Superpixel 3 2.1.2 The Algorithm 5 2.1.3 Simulation Results 6 2.2 Simple Linear Iterative Clustering Superpixels (SLIC) 7 2.2.1 About SLIC 7 2.2.2 The Algorithm 10 2.2.3 Simulation Results 11 2.3 Normalized Cut (Ncut) 12 2.3.1 About Normalized Cut 12 2.3.2 The Algorithm 14 2.3.3 Simulation Results 16 2.4 Multi-Layer Spectral Segmentation (MLSS) 17 2.4.1 About MLSS 17 2.4.2 The Algorithm 19 2.4.3 Simulation Results 20 2.5 Segmentation by Aggregating Superpixels (SAS) 21 2.5.1 About SAS 21 2.5.2 The Algorithm 22 2.5.3 Simulations 24 Chapter 3 Proposed Segmentation Algorithms 25 3.1 Introduction 25 3.2 Superpixel Algorithm and Saliency Detection 28 3.2.1 Mean Shift superpixel 28 3.2.2 Saliency Detection 29 3.3 Edge Information and Texture Features 30 3.3.1 Edge Detection 30 3.3.2 Texture Features 31 3.4 Two Stages Superpixel Growing and Merging 31 3.4.1 Superpixel Growing 31 3.4.2 Adaptive Region Merging 32 3.5 Foreground Significance Estimation and Superpixel Post-process 33 3.5.1 Foreground Significance Estimation 33 3.5.2 Superpixel Post-processing 34 3.6 Edge Information Enhancement 36 3.7 Texture Information Enhancement 38 3.7.1 Additional Texture from DCT 38 3.7.2 Additional Texture from Gradient Histogram 40 3.8 Proposed Algorithm 40 3.9 The Analysis of Our algorithm 43 Chapter 4 Simulations 45 4.1 Parameter Setting 45 4.2 Database and Evaluation Metrics 46 4.3 Comparison to the State-of-the-art Methods 47 4.3.1 Comparison of Performance Evaluation 47 4.3.2 Visual Comparison 48 Chapter 5 Cell Segmentation and Adjustment 56 5.1 Introduction 56 5.2 Adjustment and Results 57 5.3 3D Visualization 60 Chapter 6 Conclusion and Future Work 63 6.1 Conclusion 63 6.2 Future Work 64 REFERENCE 65 | |
| dc.language.iso | en | |
| dc.subject | 影像切割 | zh_TW |
| dc.subject | 超像素 | zh_TW |
| dc.subject | 邊緣偵測 | zh_TW |
| dc.subject | 顯著偵測 | zh_TW |
| dc.subject | 電腦視覺 | zh_TW |
| dc.subject | superpixel | en |
| dc.subject | edge detection | en |
| dc.subject | saliency detection | en |
| dc.subject | computer vision | en |
| dc.subject | Image segmentation | en |
| dc.title | 使用於模糊前景影像與細胞影像之進階影像切割 | zh_TW |
| dc.title | Advanced Image Segmentation Techniques for Ambiguous Foreground and Cell Images | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 105-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 夏至賢(CHIH-HSIEN HSIA),王鵬華(PENG-HUA WANG),郭景明(CHING-MING KUO) | |
| dc.subject.keyword | 影像切割,超像素,邊緣偵測,顯著偵測,電腦視覺, | zh_TW |
| dc.subject.keyword | Image segmentation,superpixel,edge detection,saliency detection,computer vision, | en |
| dc.relation.page | 68 | |
| dc.identifier.doi | 10.6342/NTU201703888 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2017-08-19 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-106-1.pdf 未授權公開取用 | 5.4 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。