請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/36429完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 貝蘇章(Su-Chang Pei) | |
| dc.contributor.author | Feng-Ju Chang | en |
| dc.contributor.author | 張鳳洳 | zh_TW |
| dc.date.accessioned | 2021-06-13T08:00:32Z | - |
| dc.date.available | 2016-08-02 | |
| dc.date.copyright | 2011-08-02 | |
| dc.date.issued | 2011 | |
| dc.date.submitted | 2011-07-20 | |
| dc.identifier.citation | [1] J. M. Geusebroek, R. V. D. Boomgaard, and A. W. M. Smeulders, “Color Invariance,” in IEEE Trans. on PAMI, 2001, pp. 1338-1349.
[2] J. M. Geusebroek, Th. Gevers, A. W. M. Smeulders, “The Kubelka-Munk Theory for Color Image Invariant Properties,” in CGIV, 2002, pp.463-467. [3] Shafer, S. A., “Using Color to separate reflection components,” in Color Resolution Applications, vol. 10, no.4, pp. 210-218, 1985. [4] Y. C. Chung, S. L. Chang, S. Cherng, and S.W. Chen, “The Invariance Properties of chromatic characteristics,” in PSIVT, 2006, pp.128-137. [5] J. van de Weijer, Th. Gevers, and J. M. Geusebroek, “Edge and Corner Detection by Photometric Quasi-Invariants,” in IEEE Trans. on PAMI, 2005, pp.625-630. [6] J. van de Weijer, Th. Gevers, and J. M. Geusebroek, “Color Edge Detection by Photometric Quasi-Invariants,” in ICCV, 2003. [7] J. van de Weijer, Th. Gevers, and A. W. M. Smeulders, “Robust Photometric Invariant Features From the Color Tensor,” in IEEE Trans. on Image Processing, 2006, pp. 118-127. [8] J. van de Weijer, and Th. Gevers, “Tensor Based Feature Detection for Color Images,” in Color Science and Engineering Systems, Technologies and Applications, 2004, pp. 100-105. [9] Th. Gevers, and A. W. M. Smeulders, “Color Based Object Recognition,” in Pattern Recognition Society, 1999, pp. 453-464. [10] J. M. Geusebroek, R. V. D. Boomgaard, A. W. M. Smeulders, and Anuj Dev, “Color and Scale : The Spatial Structure of Color Images,” in ECCV, 2000. [11] J. van de Weijer, Th. Gevers, and A. D. Bagdanov, “Boosting Color Saliency in Image Feature Detection,” in IEEE Trans. on PAMI, vol. 28, no.1, 2006. [12] S. D. Zenzo, “A Note on the Gradient of a Multi-Image,” in Computer Vision, Graphics, and Image processing, pp. 116-125, 1986. [13] G. Healey, “Segmenting Images Using Normalized Color,” in IEEE Trans. Systems, Man, and Cybernetics, vol. 22, pp. 64-73, 1992. [14] Y. Ohta, T. Kande, and T. Sakai, “Color Information for Region Segmentation,” in Computer Graphics and Image processing, vol. 13, pp. 222-241, 1980. [15] Th. Gevers, and H. M. G. Stokman, “Classification of Color Edges in Video into Shadow-Geometry, Highlight, or Material Transitions,” in IEEE Trans. Multimedia, vol. 5, no. 2, pp. 237-243, 2003. [16] G. D. Finlayson, S. D. Hordley, C. Lu, and M. S. Drew, “On the Removal of Shadows from Images,” in IEEE Trans. on PAMI, 2006, pp. 59-68. [17] G. D. Finlayson, and S. D. Hordley, “Color Constancy at a Pixel,” in J. Optical Soc, 2001, pp.253-264. [18] G. D. Finlayson, M. S. Drew, and C. Lu, “Intrinsic Images by Entropy Minimization,” in ECCV, 2004, pp. 582-595. [19] B. K. Horn, “Determining Lightness from an Image,” Computer Graphics and Image Processing, vol. 3, pp. 277–299, 1974. [20] A. Blake, “On Lightness Computation in the Mondrian World,” in Proceedings of the Wenner-Gren Conference on Central & Peripheral Mechanisms in Colour Vision. MacMillan, New York, 1983, pp. 45–59. [21] M. Bertalmio, G. Sapiro, V. Caselles, and C. Balleste, “Image Inpainintg,” in Proc. ACM Conf. Comp. Graphics (SIGGRAPH), 2000, pp. 417-424. [22] A. Criminisi, P. Perez, and K. Toyama, “Region Filling and Object Removal be Exemplar-Based Image Inpainting,” in IEEE Trans. on Image Processing, 2004, pp. 1-13. [23] J. van de Weijer, and Th. Gevers, and A. Gijsenij, “Edge-Based Color Constancy,” in IEEE Trans. on Image Processing, 2007, pp. 2207-2214. [24] K. Barnard, V. Cardei, and B. Funt, “A comparison of computational color constancy algorithms- Part I : Methodology and experiments with synthesized data,” in IEEE Trans. on Image Processing, Vol. 11, No. 9, Sept., 2002. [25] K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms- Part II : Experiments with image data,” in IEEE Trans. on Image Processing, 2002, pp. 985-996. [26] D. Forsth, “A novel algorithm for color constancy,” in Int. J. Comput. Vis., vol. 5, no. 1, pp.5-36, 1990. [27] D. Brainard, and W. Freeman, “Bayesian color constancy,” in J. Opt. Soc. Amer. A, vol. 12, no.7, p.1393. [28] G. D. Finlayson, S. Hordley, and P. Hubel, “Color by correlation : A simple, unifying framework for color constancy,” in IEEE Trans. on PAMI, vol. 23, no. 11, pp. 1209-1221, 2001. [29] G. D. Finlayson, and S. Hordley, “Gamut constrained illumination estimation,” in Int. J. Comput. Vis., vol. 67, no.1, pp. 93-109, 2006. [30] G. D. Finlayson, and E. Trezzi, “Shades of gray and color constancy,” in Proc. IS&T/SID 12 th Color Imaging Conf., 2004, pp.37-41. [31] E. H. Land, “ The retinex theory of color vision, ” in Sci. Amer., vol. 237, no.6, pp. 108-120, 122, 123, 126, 128, 1977. [32] G. Buchsbaum, “A spatial processor model for object color perception,” in J. Frank. Inst., vol. 310, 1980. [33] Marc Ebner, “Color constancy base on local space average color,” in Machine Vision and Applications, vol. 11, no. 5, 2009. [34] E. H. Land and J. J. McCann, “Lightness and Retinex Theory,” in Journal of the optical society of America, 1970. [35] J. van de Weijer, C. Schmid, J. Verbeek, “Using High-Level Visual Information for color constancy,” in ICCV, 2007. [36] A. Torralba, and A. Oliva, “Statistics of natural image categories,” in Network: Comput. Neural Syst., pp. 391-412, 2003. [37] A. Gijsenij and T. Gevers, “Color constancy using natural image statistics,” in IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8, 2007. [38] A. Gijsenij and T. Gevers, “Color constancy using natural image statistics and scene semantics,” in IEEE Trans. Pattern Anal. Mach. Intell, 2010. [39] V. C. Cardei and B. Funt, “Committee-based colour constancy,” in Seventh Color Imaging Conference: Color Science and Engineering Systems, Technology and Applications, 1999. [40] P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8. [41] D. L. Ruderman, T. W. Cronin, and C. C. Chiao, “Statistics of Cone Responses to Natural Images: Implications for Visual Coding,” in J. Opt. Soc. Am. A 15, pp. 2036-2045, 1998. [42] B. Li, D. Xu, and C. Y. Lang, “Color constancy based on texture similarity for natural images,” in Color. Technol. 125, pp. 328–333, 2009. [43] M. Wu, J. Sun, J. Zhou, and G. Xue, “Color constancy based on texture pyramids matching and regularized local regression,” in JOSA A, vol.27, issue 10, pp. 2097-2105, 2010. [44] A. Gijsenij, T. Gevers, and J. van de Weijer, “Generalized Gamut Mapping using Image Derivative Structures for color constancy,” in Int. J. Comput. Vis., 2008. [45] F. Gasparini, and R. Schettini, “Color balancing of digital photos using simple image statistics,” in Pattern Recognition Society, 2003. [46] V. C. Cardei, B. Funt, and K. Brnard, “Estimating the scene illumination chromaticity by using a neural network,” in J. Opt. Soc. Am. A, vol. 19, no.12, 2002. [47] J. M. Geusebroek, “Compact Object Descriptors from local color invariant histograms,” in BMCV, pp. 1029-1038, 2006. [48] J. M. Geusebroek, and A. W. M. Smeulders, “A six-stimulus theory for stochastic texture,” in International Journal of Computer Vision, pp. 7-16, 2005. [49] J. B. De Paula, “Converting RGB Images to LMS Cone Activations,” Department of Computer Science, The University of Texas at Austin, Tech. Rep. TR-06-49, 2006. [50] Marc Ebner, Color Constancy. Wiley-IS&T Series in Imaging Science and Technology, 2007. [51] William K. Paratt, Digital Image Processing. Published by John Wiley & Sons, Inc., 2007. [52] “Color for Image Retrieval,” class notes for Multimedia Analysis and Indexing (MMAI), Communication and Multimedia lab, Department of Computer Science, National Taiwan University, Oct. 5, 2010. [53] “Texture and Shape for Image Retrieval,” class notes for Multimedia Analysis and Indexing (MMAI), Communication and Multimedia lab, Department of Computer Science, National Taiwan University, Oct. 12, 2010. [54] Th. Gevers, and J. van de Weijer, “Color in Image/Video Processing Applications,” Tutorial of ICIP, Cairo, Egypt, 2009. [55] F. Ciurea and B. V. Funt, “A large image database for color constancy research,” in Eleventh Color Imaging Conference: Color Science and Engineering Systems, Technology and Applications, pp. 160–164, 2003. [56] J. M. Geusebroek, G. J. Burghouts, and A. W. M. Smeulders, The Amsterdam library of object images, Int. J. Comput. Vision, 61(1), 103-112, January, 2005. [57] “A Tutorial on Clustering Algorithms,” http://home.dei.polimi.it/matteucc/Clustering/tutorial_html/cmeans.html. [58] G.J. Klinker and S.A. Shafer, “A Physical Approach to Color Image Understanding,” in Int’l J. Computer Vision, vol. 4, pp. 7-38, 1990. [59] B.A. Maxwell and S.A. Shafer, “Physics-Based Segmentation of Complex Objects Using Multiple Hypothesis of Image Formation,” in Computer Vision and Image Understanding, vol. 65, pp. 265-295, 1997. [60] “ Spherical Coordinates, ” http://mathworld.wolfram.com/SphericalCoordinates.html [61] O. Chapelle, P. Haffner, and V. Vapnik, “Support Vector Machines for Histogram-Based Image Classification,” in IEEE Trans. Neural Networks, vol. 10, no. 5, pp. 1055-1064, 1999. [62] D. Koubaroulis, J. Matas, and J. Kittler, “Evaluating Color-Based Object Recognition Algorithms Using the Soil-47 Database,” in Proc. Asian Conf. Computer Vision, 2002. [63] D. Comaniciu and P. Meer, “Mean shift analysis and applications,” in Proceedings of the 7th International Conference on Computer Vision, 1999, pp. 1197–1203. [64] J. Canny, “A computational approach to edge detection,” in IEEE Trans. Patt. Anal. Mach. Intell., vol. 8, pp. 679–698, 1986. [65] R. Frankot and R. Chellappa, “A method for enforcing integrability in shape from shading algorithms,” in IEEE Trans. Patt. Anal. and Mach. Intell., vol. 10, pp. 439–451, 1988. [66] “Majority filter,” http://webhelp.esri.com/arcgisdesktop/9.3/index.cfm?TopicName=majority_filter [67] “Gamma value, delta E and Color Space,” http://www.digital.idv.tw/digital/classroom/mroh-class/oh109/index-oh109.htm [68] “Syntactic Analysis for videos,” class notes for Multimedia Analysis and Indexing (MMAI), Communication and Multimedia lab, Department of Computer Science, National Taiwan University, Sep. 21, 2010. [69] S. Bianco, G. Ciocca, C. Cusano, and R. Schettini, “Improving color constancy using indoor-outdoor image classification,” in IEEE Trans. Image Process. 17, pp. 2381–2392, 2008. [70] V. Yanulevskaya, and J. M. Geusebroek, “Significance of the Weibull Distribution and Its Sub-Models in Natural Image Statistics,” in International Conference on Computer Vision Theory and Applications, pp. 355-362, 2009. [71] “ Computational Visual Cognition Laboratory, ” http://cvcl.mit.edu/database.htm [72] A. Gijsenij, T. Gevers, J. van de Weijer, “Physics-based Edge Evaluation for Improved Color Constancy,” in Proc. CVPR, Miami, USA , 2009. [73] K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” in CRA, 27(3), pp. 147–151, 2002. [74] H. S. Scholte, S. Ghebreab, A. Smeulders, and V. Lamme, “ The parvo and magno-cellular systems encode natural image statistics parameters,” in J. Vision 8, 686&686a, 2008. [75] S. Lazebnik, C. Schmid, and J. Poncek, “Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,” in IEEE Conference on Computer Vision and Pattern Recognition, pp. 2169–2178, 2006. [76] B. S. Manjunath and W.Y. Ma, “Texture features for browsing and retrieval of image data,” , in IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol.18, no.8, pp.837-42,1996. [77] A. Oliva, and A. Torralba, “Modeling the Shape of the Scene: a Holisitic Representation of the Spatial Envelope,” in International Journal of Computer Vision, vol.42 (3), pp. 145-175, 2001. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/36429 | - |
| dc.description.abstract | 對於影像處理的很多運用中像是影像檢索, 影像切割, 影像分類, 物體或是景像辨識,我們都希望在擷取或是偵測影像的特徵時能夠不受到光源變化的影響。經由了解影像生成模型，並且在特定光源和物體表面假設下，我們可以得到各式各樣不受光源影響亦或是只跟物體反射率有關的全色彩特徵。另外一種色彩特徵，我們稱為半色彩特徵，它是透過色彩一次微分減去其在光影變化例如陰影或是強光變化方向的投影而得到的，它比全色彩特徵更加穩定，所以比較適合拿來偵測影像特徵，但很不幸地，根據影像生成模型的推導，我們可以發現半色彩特徵還是跟光源會有關係，因此並不適合在不同的光源變化下擷取和比較影像特徵。想要擷取影像特徵還是必須動用到全色彩特徵，我們可以利用測量到的不確定性去給予權重，之後再結合顏色張量以改善全色彩特徵的不穩定性。
假如我們可以投影一個像素至與光源垂直即不受光源影響的方向，那麼我們就可以得到一維無陰影的影像。藉由乘上一個投影矩陣，我們可以進一步顯示二維無陰影影像，至於三維無陰影影像的還原，我們提出利用比較有彈性的分類方法(Fuzzy C means)來做更有效率及精確的陰影切割並偵測陰影的邊緣,透過所切割的結果，我們提出利用非陰影區域來調整陰影區域的亮度和質地，此舉是為了使還原結果更好，接著利用離散餘弦轉換來解帕松方程式藉以得到三維無陰影影像，最後我們還提出利用彌補影像缺失的技術讓靠近陰影邊緣的還原像素看起來更自然。 光源恆定性除了找出不受光源影響的色彩特徵外，光源偵測及色彩校正也是另外一個很重要且更具挑戰性的分枝。在此論文，我們會複習一些根據影像像素或是像素差假設的光源偵測法並且提出一個新的偵測光源方法:透過對人眼均勻的色彩空間進行色偏差分析以便找出掃描累加的RGB分布時所需的影像像素比例，接著將大於此比例所對應像素值的所有像素去做一個權重平均以得到一個更具代表且比較不受脈衝雜訊影響的光源顏色。此外，不同於純粹取像素平均值以估計光源顏色的Gray World方法，我們提出利用色彩張量特徵值的和來給予較大像素變化區域更多的權重並且壓低一大塊區域都是類似顏色的影響。至於Gray Edge的方法，我們提出利用顏色張量加上陰影變量和強光變量來對不同的邊緣做權重的分配並且更進一步利用奇異值分解使得此方法可以推廣到真實世界的影像上。 既然沒有任何一個光源偵測法可以適用於所有影像，一個最新的光源偵測趨勢就是想辦法結合不同光源偵測法的結果，最常見的有資料驅動的類型例如最小平方法，另外就是根據現有的知識例如在一堆訓練用的影像中去計算最好方法出現次數的比例來給予各個估計的光源不同的權重。我們覺得只考慮最好的光源偵測法過於主觀，於是我們提出改成考慮所有要結合的光源偵測法，並且根據它們所偵測出來的光源和真實光源的角度差來給予不同的權重。此外，一個最新的光源結合技術就是整合最小平方法和最好方法出現次數的比例。 我們進一步地將最好方法出現次數的比例換成新提出來的光源結合方法，藉以用來給定調節項的初始權重值，從我們的實驗結果發現到我們所提出的光源結合法確實可以得到更精準的光源估測。 | zh_TW |
| dc.description.abstract | Photometric invariance or we say color invariance is important for many applications such as image retrieval, image segmentation, image classification, object and scene recognition, etc. Since both color based feature extraction and detection are susceptive to the varying imaging conditions including light source as well as the surface geometry, our aim is to obtain the color descriptor or feature which is invariant with respect to the photometric variation and only depends on the object reflectance.
According to the color image formation model, we can acquire numerous full color invariant descriptors under a certain illuminant as well as the surface assumption. The quasi-invariants, derived by subtracted the projected variants from the color derivative are more stable than full invariants to remove shadow-shading and highlight edges and therefore suitable for feature detection. As to the feature extraction, the full invariants are still needed since the quasi-invariants are in fact related to the illuminant from the mathematical deduction. With the weights by measured uncertainties as well as the structure (color) tensor, the full invariants become more robust in feature extraction. If we can represent a pixel in the illuminant invariant direction, the 1D shadow free image can be obtained. The 2D illuminant invariant image can be further acquired by multiplied with the projection matrix. As to the 3D shadow free image, we propose to use a soft classification based method, fuzzy C means, to effectively and accurately segment the shadow area and then detect the shadow edges. According to the segmentation map, we can further adjust the brightness as well as the texture of the shadow area in order to get better recovered result. Finally, we utilize the modified intensity values as well as the gradients to solve the Poisson equation by discrete sine transform to obtain a 3D shadow-free image. Moreover, we propose to use the exemplar-based inpainting technique to make the reconstructed pixels which are near shadow edges look more natural. In addition to the representation of the color invariant descriptors for reaching color constancy, illuminant estimation and color correction is another essential branch for color constancy. Considering the bad impulse noise resistance of the White Patch Retinex (WPR), susceptibility to large uniformly colored regions of the Gray world (GW), non-generality of the weighted Gray Edge (WGE) method, we propose an illuminant estimation method by adaptive scanning of accumulative color histograms based on the color cast analysis in color space for improving WPR. Also, we use the color tensor to assign more weight to regions with larger color variation for improving GW. As to WGE, the initial guess of the illuminant from original Gray Edge hypothesis, eigen-value sum of the structure tensors with shadow-shading as well as specular variants, and singular value decomposition are considered to make it more generalized. After improving all above single algorithms, we further propose an illuminant fusion scheme which is called fuzzy frequency ratio (FFR) in that it is not reasonable for best frequency ratio (BFR) to only consider the best illuminant (hard decision). That is, we take all above improved illuminant estimation measures into account and assign distinct weights to them. Finally, FFR is integrated to the regularized local regression (RLR-FFR). From our experiments, the improved single algorithms are all indeed better than original methods and the proposed combination scheme (FFR) is better than BFR and also more proper to be used for setting the initial weights in the regularized local regression. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-13T08:00:32Z (GMT). No. of bitstreams: 1 ntu-100-R98942063-1.pdf: 12539762 bytes, checksum: 882ba1c4fb6e3293f7faf145675e26bd (MD5) Previous issue date: 2011 | en |
| dc.description.tableofcontents | 誌謝 i
中文摘要 iii ABSTRACT v CONTENTS vii LIST OF FIGURES xiii LIST OF TABLES xxv Chapter 1 Introduction 1 Chapter 2 The Spectral-Spatio Structure of Color Images and Color Image Formation 7 2.1 Introduction 7 2.2 Integration of the Spectral and Spatial Structures of Color with the Gaussian Color Model 7 2.2.1 The Spectral Structure of Color 7 2.2.2 The Spatial Structure of Color 9 2.3 The Relation between Opponent, IHS, and Gaussian Color Spaces 11 2.3.1 The General Opponent Color Space 12 2.3.2 The IHS Color Space 12 2.3.3 The Color Space 13 2.4 Color Image Formation Model 14 Chapter 3 Photometric Invariant Descriptors 19 3.1 Introduction 19 3.2 Derivation of Photometric Invariant Descriptors 19 3.2.1 Photometric Color Invariants for equal energy but uneven illumination 19 3.2.2 Photometric Color Invariants for equal energy but uneven illumination and Matte, Dull Surfaces 21 3.2.3 Photometric Color Invariants for equal energy and uniform illumination and Matte, Dull Surfaces 23 3.2.4 Photometric Color Invariants for colored but Uneven Illumination and matte, dull surfaces 24 3.2.5 Geometrical Photometric Color Invariants in Two Dimensions 26 3.3 Edge Detection with Full Photometric Color Invariants 28 3.3.1 Edge Detection Using Hue Gradient 29 3.3.2 Edge Detection Using Normalized Color Gradient and 30 3.3.3 Edge Detection Using 31 3.3.4 Edge Detection Using 31 3.3.5 Edge Detection Using Total Edge Strength for the Various Color Invariant Sets 32 Chapter 4 Photometric Variants and Quasi Invariants 35 4.1 Introduction 35 4.2 The Physical Meanings for the Derivatives of the Dichromatic Reflection Model 36 4.3 Derivation of Photometric Variants and Quasi Invariants 39 4.4 Relations between Quasi Invariants and Full Invariants 41 4.4.1 Spherical Color Space for Shadow-Shading Variants and Quasi-Invariants 41 4.4.2 Opponent Color Space for Specular Variants and Quasi Invariants 44 4.4.3 The Hue Saturation Intensity Color Space for Shadow-Shading-Specular Variants and Quasi Invariants 45 4.5 The Characteristics of the Quasi Invariants 48 4.6 Feature Detection and Classification by Photometric Quasi Invariants 51 4.6.1 Photometric Invariant Edge Detection 51 4.6.2 Photometric Invariant Corner Detection 52 4.6.3 Edge Classification by Photometric Variants and Quasi Invariants 54 Chapter 5 Incorporation of Robust Photometric Invariants and the Color Tensor 57 5.1 Introduction 57 5.2 Robust Full Photometric Invariants with Uncertainty Measures 58 5.3 Feature Detection with Structure Tensor for Color Images 59 5.3.1 The Structure Tensor 59 5.3.2 Tensor Based Edge and Corner Detection 62 5.3.3 Tensor Based Star and Circle Detection 63 5.4 Integration of Photometric Invariants and Structure Tensor 65 5.4.1 Tensor Based Color Canny Edge Detection 66 5.4.2 Tensor based Color Harris Corner Detection 68 5.4.3 Local Color Symmetry Detection 69 Chapter 6 Color Saliency Boosting for Corner Detection 71 6.1 Introduction 71 6.2 Color Boosting with Color Transformation and Eigen-Decomposition 71 Chapter 7 Color Constancy at a Pixel and Shadow Removal 81 7.1 Introduction 81 7.2 The Derivation of One Dimensional Shadow-Free Images 84 7.2.1 1D Shadow-free Images in Illuminant Invariant Color Spaces 84 7.2.2 1D Shadow-Free Images by Entropy Minimization 86 7.2.3 Experimental Results and Discussions 92 7.3 The Derivation of the Two Dimensional Shadow-Free Images 95 7.3.1 Experimental Results and Discussions 96 7.4 The Derivation of Three Dimensional Shadow-Free Images 98 7.4.1 The Lightness Algorithm 99 7.4.2 The Finlayson’s Algorithm 100 7.4.3 Shadow Removal by Fuzzy C-means and Inpainting 103 7.4.4 Experimental Results and Discussions 109 Chapter 8 Illuminant Estimation and Color Correction 115 8.1 Introduction 115 8.2 The Illuminant Estimation Problem and Color Correction 119 8.3 The Setup of Image Sets 121 8.4 The Evaluation Measures 122 8.5 The Statistics-based Approaches 124 8.5.1 Gamut Mapping and Its variants 124 8.5.2 Color by Correlation 129 8.5.3 Neural Network based Method 132 8.6 The Physics-based Techniques 133 8.6.1 The White Patch Retinex Algorithm 133 8.6.2 The Gray World Hypothesis 134 8.6.3 The Shades of Gray Method 135 8.6.4 The Gray Edge Hypothesis 136 8.6.5 The Unifying Framework for the White Patch Retinex, The Gray World and The Gray Edge Measures 139 8.6.6 Local Space Average Color 140 8.6.7 Experimental Results and Discussions 143 8.7 Improvement for Physics-based Techniques 154 8.7.1 Improved White Patch Retinex by Adaptive Scanning of Accumulative Color Histogram with Color Cast Analysis 154 8.7.2 Improved Gray World with Structure Tensor 159 8.7.3 Generalized Weighted Gray Edge Algorithm with Structure Tensor and Singular Value Decomposition 160 8.7.4 Experimental Results and Discussions 166 8.8 Illuminant Selection based on Natural Image Statistics 180 8.8.1 The Motivation of Using Natural Image Statistics and Scene Semantics for Illuminant Selection 181 8.8.2 The Spatial Image Structures by Weibull Distribution 182 8.8.3 The Relation between the Spatial Image Structures and the Illuminant Estimation Methods 188 8.8.4 Selection Schemes 191 8.9 Illuminant Combination by Natural image Statistics, Least Mean Square or Best Frequency Ratio Weighting Scheme 193 8.9.1 Natural Image Statistics based Weighting Method 194 8.9.2 Least Mean Square Weighting Method 194 8.9.3 Best Frequency Ratio Weighting Method 196 8.9.4 Fuzzy Frequency Ratio Weighting Method 197 8.10 Integration of Illuminants by Regularized Local Regression with Muti-Scale Texture Matching 199 8.10.1 Image Representation by More Discriminative Weibull Statistics and Gabor Features 200 8.10.2 Image Matching Schemes 208 8.10.3 Illuminant Fusion by Regularized Local Regression 210 8.11 Experimental Results and Discussions 213 8.11.1 Experiments for the SFU real world data set 215 8.11.2 The Experiments for the MS real world data set 219 Chapter 9 Conclusion and Future Works 229 Chapter 10 References 233 | |
| dc.language.iso | en | |
| dc.subject | 色彩校正 | zh_TW |
| dc.subject | 色彩恆常性 | zh_TW |
| dc.subject | 半色彩 | zh_TW |
| dc.subject | 色彩張量 | zh_TW |
| dc.subject | 光源估計 | zh_TW |
| dc.subject | Color invariance | en |
| dc.subject | Color correction | en |
| dc.subject | Illuminant estimation | en |
| dc.subject | Color tensor | en |
| dc.subject | Quasi-invariants | en |
| dc.title | 不受光源影響之色彩特徵暨光源偵測之色彩校正 | zh_TW |
| dc.title | Color Invariant Descriptors and Color Correction Based on Illuminant Estimation | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 99-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李枝宏(Chih-Hung Li),曾建誠(Chien-Cheng Tseng),徐忠枝(Chung-Chih Hsu) | |
| dc.subject.keyword | 色彩恆常性,半色彩,色彩張量,光源估計,色彩校正, | zh_TW |
| dc.subject.keyword | Color invariance,Quasi-invariants,Color tensor,Illuminant estimation,Color correction, | en |
| dc.relation.page | 240 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2011-07-20 | |
| 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-100-1.pdf 未授權公開取用 | 12.25 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。