請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65477
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 丁建均 | |
dc.contributor.author | Chien-Chi Chen | en |
dc.contributor.author | 陳建齊 | zh_TW |
dc.date.accessioned | 2021-06-16T23:45:26Z | - |
dc.date.available | 2015-07-27 | |
dc.date.copyright | 2012-07-27 | |
dc.date.issued | 2012 | |
dc.date.submitted | 2012-07-24 | |
dc.identifier.citation | A. Human visual system
[1] J. M.Wolfe and T. S. Horowitz, “What attributes guide the deployment of visual attention and how do they do it,” Nat. Rev. Neurosci., vol. 5, no. 6, pp. 495–501, Jun 2004. B. Button-up approach. [2] L. Itti, C. Koch, and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1254-1259, Nov 1998. [3] Y. F. Ma and H. J. Zhang, “Contrast-based image attention analysis by using fuzzy growing,” in ACM International Conference on Multimedia, pp. 374–381, 2003. [4] J. Harel, C. Koch, and P. Perona, “Graph-based visual saliency,” Advances in Neural Information Processing Systems, pp. 545–552, MIT Press, 2006. [5] L. Itti and P. F. Baldi, “Bayesian surprise attracts human attention,” Advances in Neural Information Processing Systems, pp. 547–554, MIT Press, 2005. [6] L. Itti, and P. Baldi, “A principled approach to detecting surprising events in video,” in Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 631-637, June 2005. [7] C. Koch, S. Ullman, “Shifts in selection in visual attention: toward the underlying neural circuitry,” Human Neurobiology, vol. 4, pp. 219-227, 1985. [8] F. Liu, M. Gleicher, “Region enhanced scale-invariant saliency detection,” In Proceedings of IEEE ICME, pp.1477-1480, July 2006. [9] O.L.Meur, O.L.Callet, D.Barba, and D.Thoreau, “A coherent computational approach to model bottom-up visual attention,” IEEE Trans. on PAMI, vol.28, no.5, pp.802-817, May 2006. [10] J.K. Tsotsos, S.M. Culhane, W.Y.K. Wai, Y.H. Lai, N. Davis, and F. Nuflo, “Modelling visual attention via selective tuning,” Artificial Intelligence, vol. 78, no. 1-2, pp. 507–545, Oct. 1995. [11] T. Liu, J. Sun, N. Zheng, X. Tang, and H. Shum, “Learning to detect a salient object,” IEEE Trans. on PAMI, vol. 33, no. 2, pp. 353-367, Feb 2011. [12] M. M. Cheng, G. X. Zhang, N. J. Mitra, X. Huang, and S. M. Hu, “Global contrast based salient region detection,” CVPR, pp. 409-416, June 2011. [13] X. Hou, L. Zang, “Saliency detection: a spectral residual approach,” CVPR, pp. 1-8, June 2007. [14] R. Achanta, S. Hemami, F. Estrada, and S. Susstrunk, “Frequency-tuned salient region detection,” CVPR, pp. 1597-1604, June 2009. [15] R. Achanta, S. Susstrunk, “Saliency detection using maximum symmetric surround,” ICIP. IEEE CS, pp 2653–2656. [16] R. Achanta, F. Estrada, P. Wils, and S. Süsstrunk, “Salient region detection and segmentation,” ICVS, pp. 66–75, 2008. [17] Y. Xue, Z.Liu, and R. Shi, “Saliency detection using multiple region-based feature,” In Optical Engineering, vol. 50, issue 5, pp. 057008-057008-9, 2011. [18] Z. Han, Z. Liu, Z. Zhang, Y. Lu, W.Li, and H. Yan, “Salient object extraction based on region saliency ratio,” IEEE/ACIS ICIS, pp.611-615, June 2009. [19] Z. Liu, Y. Xue, H.Yan, and Z. Zhang, “Efficient saliency detection based on Gaussian models,” IET Image Processing, pp. 122-131, 2011 [20] A. Elgammal, R. Duraiswami, D. Harwood, and L. s. Davis, “Background and Foreground Modeling Using Non-Parametric Kernel Density Estimation for Visual Surverillance,” Proceeding of the IEEE, 90, pp. 1151-1163, (2002). [21] Y. Zhai, M. Shah, “Visual attention detection in video sequences using spatiotemporal cues,” In ACM Multimedia, pp. 815–824, 2006. 410, 411, 412, 413, 414, 415. [22] H. Huang, L. Zhang, and T.-N. Fu, “Video painting via motion layer manipulation,” Comput. Graph. Forum, 29(7):2055–2064, 2010. [23] Y.-S. Wang, C.-L. Tai, O. Sorkine, and T.-Y. Lee, “Optimized scale-and-stretch for image resizing,” ACM Trans. Graph., 27(5):118:1–8, 2008. C. Depth of field. [24] L. Cong, R. F. Tong, and D. Y. Bao, “Detect saliency to understand a photo,” ICMT, pp.286-289, 26-28, 2011. [25] C. T. Vu, T. D. Phan, and D. M. Chandler, “S3: A spectral and spatial measure of local perceived sharpness in natural images,” Image Processing, IEEE Transation, pp 934- 945, 2012. D. Middle high level approach [26] N. Bruce, J. Tsotsos, “Saliency based on information maximization,” NIPS, pp. 155–162, 2005. [27] W. Wang, Y. Wang, Q. Huang, and W. Gao, “Measuring visual saliency by site entropy rate,” CVPR, pp. 2368-2375, 2010. 418 [28] S. Goferman, Z. M. Lihi, and A. Tal, “Context-aware saliency detection,” CVPR, pp.1633-1640, 2010. [29] T. Deselaers, V. Ferrari, “Global and efficient self-similarity for object classification and detection,” CVPR, pp.1633-1640, 2010. [30] J. Hateren and A. van der Schaaf, “Independent component filters of natural images compared with simple cells in primary visual cortex,” Proc. R. Soc. Lond. B, 1998. E. Image segmentation approach. [31] J. Shi, J. Malik, “Normalized cuts and image segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, Aug. 2000. [32] P. F. Felzenszwalb, “Efficient graph-based image segmentation,” Int'l J. Computer Vision, vol. 59, no. 2, pp. 167-181, 2004. [33] Y. Y. Boykov, M. P. Jolly, “Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images,” Proc. Int'l Conf. Computer Vision, pp. 105-112, 2001. [34] Y. Boykov, V. Kolmogorov, “An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision,” PAMI, Vol. 26, No. 9, pp. 1124-1137, 2004. F. Relative algorithm of proposed approach 1. [35] L. Xu, C. Lu, Y. Xu and J. Jia, “Image smoothing via L0 gradient minimization,” ACM Transactions on Graphics, Vol. 30, No. 6 Proc. ACM SIGGRAPH ASIA 2011, Dec. 2011. [36] J. J. Ding, C. J. Kuo, and W. C. Hong, “An efficient image segmentation technique by fast scanning and adaptive merging,” Computer Vision, Graphics, and Image Processing, Sitou, Taiwan, Aug. 2009. [37] S. L. Horowitz and T. Pavlidis, “Picture segmentation by a tree traversal algorithm,” JACM, vol. 23, pp. 368-388, April, 1976. [38] Y. Deng, and B.S. Manjunath, “Unsupervised segmentation of color-texture regions in images and video,” IEEE Trans. Pattern Anal. Machine Intell., vol. 23, no. 8, pp. 800-810, Aug. 2001. G. Relative algorithm of proposed approach 2. [39] M. E. Tipping and C. M. Bishop, “Probabilistic principal component analysis,” Journal of the Royal Statistical Society, B, vol. 6, no. 3, pp. 611–622, 1999. [40] E. Alpaydin, Introduction to machine learning, 2nd ed., The MIT Press, 2010. [41] B. Alexe, T. Deselaers, and V. Ferrari, “What is an object,” CVPR, IEEE, vol., no., pp.73-80, 13-18, 2010. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65477 | - |
dc.description.abstract | 在這十年內,因應大量影像處理對於預先定義出影像中顯著區域的需求,像是影像切割、影像壓縮和影響大小調整等等。定義顯著區域為自動判斷出影像中較重要區域,並且產生出以顯著程度為權重的影像, 這個研究已經成為影像處理中不可或缺的前處理方法。
在這過去十年內,顯著區域偵測已經發展出主要的四個方向,像是基於區域法、基於方塊法、中心與周圍差異法和物體分類法。而不同於中心與周圍差異法,基於區域法在這幾年發展出較為可靠的演算法,這是因為此法可以利用不同的影像切割方式在不同的影像中互相擬補各個方法的缺點。 根據這個理論,我們將精力聚焦於基於區域法和基於方塊法來做改良的基石。基於區域法是採用不同的切割方式做為定義顯著區域的前處理,此法可以結合不同影像切割的優點來達到較好的結果。再另一方面,基於方塊法計算出每一個八乘八方塊的差值,並且使較少出現的方塊給予較高的顯著權重,即為越少在影像中出線的方塊即為顯著區域。在本篇論文當中,我們提出了兩個新定義顯著區域方法。第一,區域對筆法為現在領域中最佳的方法,我們結合此法並且結合我們提出的背景定義概念的不同基於區域法而成為一個完整的系統。第二,我們提出一個新方法為結合基於區域法以及基於方塊法,此法巧妙的運用兩個方法的優點達到比現在最好的方法更好的結果。 依據實驗結果顯示出我們提出的方法有效的並且成功的超越現在顯著區域研究領域中大部分的方法,此項結果可以支持我們的研究結果是卓越的並且有理論根據的。 | zh_TW |
dc.description.abstract | Research of saliency map detection has fast development in the last ten years because of the great demand of image processing application, for instance image segmentation, image compression and image resizing etc. Saliency map, defining salient region of image automatically, has been indispensible part of preprocessing method in several image processes.
In past decade, saliency map has developed four primary concepts in the field such as the following: region-based, block-based, center-surround and object classification methods. Region-based method shows the robust performance during the recent year which is contrary to center-surround method. This is due to different image segmentation method, it can complement each methods. According to the theorem, we focus on the region-based and block-based method for saliency detection. Region-based method is adopted image segmentation for preprocessing determining the salient regions, which can combine different segmentation methods with several concepts for enhancing diverse image. On the other hand, block-based method which calculates difference of each 8x8 block in image determining seldom appearing patches in high score to be a salient patch. In this thesis, we provide two novel methods below: First, a mixed region-based method which improves the state-of-the-art RC method into a region-based system with background determination concept. Second, the combination of region-based and block-based methods uses both advantages of two leading to a novel region-based method in our system. The simulation results show that our two novel methods have better performance compared to different methods in saliency detection field. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T23:45:26Z (GMT). No. of bitstreams: 1 ntu-101-R99942128-1.pdf: 5090469 bytes, checksum: 893ca61cc436825a6392f2136d32501d (MD5) Previous issue date: 2012 | en |
dc.description.tableofcontents | 誌謝 i
中文摘要 iii ABSTRACT v CONTENTS vii LIST OF FIGURES x LIST OF TABLES xv Chapter 1 Introduction 1 Chapter 2 Button-Up Approach 5 2.1 Itti Approach 6 2.1.1 Center-Surround Differences and Normalization 7 2.1.2 Across-Scale Combinations and Winner-Take-All 9 2.1.3 Simulation Results and Discussion 10 2.2 Spectral Residual Approach 12 2.2.1 Spectral Residual (SR) to Saliency Map 12 2.2.2 Simulation Results and Discussion 13 2.3 Frequency-Tuned (FT) Approach 15 2.3.1 Spatial Frequency Analysis 15 2.3.2 Maximum Symmetric Surround 16 2.3.3 Simulation Results and Discussion 18 2.4 Global Regional Approach 19 2.4.1 Multi-Scales Contrast 21 2.4.2 Center-Surround Histogram 22 2.4.3 Color Spatial-Distribution 23 2.4.4 Simulation Results and Discussion 24 2.5 Global Histogram Approach 25 2.5.1 Histogram Based Contrast (HC) 25 2.5.2 Region Based Contrast 27 2.5.3 Simulation Results and Discussion 28 2.6 Segmentation-Based Approach 29 2.6.1 Region Saliency Ratio 30 2.6.2 Multiple Region-Based Feature 31 2.6.3 Simulation Results and Discussion 33 Chapter 3 Depth of Field 35 3.1 Classification Approach 36 3.1.1 Focal Point 37 3.1.2 Region Contrast 38 3.2 Sharpness Measure 38 3.2.1 Spectral Measure of Sharpness (S1) 38 3.2.2 Spatial Measure of Sharpness (S2) 40 3.2.3 Simulation Results and Discussion 41 Chapter 4 Middle High level approach 43 4.1 Context-Aware Approach 44 4.2 Information Maximum 46 4.2.1 Sparse Coding Bases 48 4.2.2 Graph Representation 49 4.2.3 SER 49 4.2.4 Simulation Results and Discussion 51 Chapter 5 Adaptive Region Merging and Border Measuring for Saliency Detection 53 5.1 Improved Color Spatial Algorithm 57 5.2 Image Segmentation and Proposed Region Merging Algorithm 59 5.2.1 Fast Scanning Algorithm 60 5.2.2 Proposed Adaptive Region Merging Algorithm 64 5.3 Border Measuring 66 5.4 Complete Algorithm of Full Structure 68 5.5 Simulation Results and Discussion 70 Chapter 6 Boundary Scoring Approach 77 6.1 Applied Technique 1: Principal Component Analysis (PCA) 79 6.2 Applied Technique 2: Improved Block-Based Method 84 6.3 Applied Technique 3: Region Boundary Saliency Ratio 89 6.4 Complete Algorithm of Full Structure 91 6.5 Simulation Results and Discussion 92 6.5.1 Discussion 94 6.5.2 Drawback of Proposed Algorithm 97 Chapter 7 Conclusion and Future Work 103 REFERENCE 105 | |
dc.language.iso | en | |
dc.title | 根據主成分分析及邊緣資訊的先進顯著區域擷取技術 | zh_TW |
dc.title | Advanced Saliency Extraction Techniques Based on Principal Component Analysis and Boundary Information | en |
dc.type | Thesis | |
dc.date.schoolyear | 100-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 葉敏宏,郭景明,許文良 | |
dc.subject.keyword | 顯著圖,顯著區域偵測,物體偵測, | zh_TW |
dc.subject.keyword | Saliency map,Saliency detection,Object detection, | en |
dc.relation.page | 109 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2012-07-24 | |
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-101-1.pdf 目前未授權公開取用 | 4.97 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。