顯著性輪廓提取、輪廓編組綜述要看的內(nèi)容（一）Berkeley學派：

http://blog.csdn.net/visionfans/article/details/6243831

Berkeley學派

Jitendra Malik

不用介紹了吧，太大的牛了。如果要介紹起來，可要花不少篇幅了。研究興趣：分割，知覺組織，紋理，立體視覺，識別等。他帶的26個學生都在學術和工業(yè)領域有重要影響力。

"Contour Detection and Hierarchical Image Segmentation "

P. Arbelaez, M. Maire, C. Fowlkes, J. Malik

IEEE Trans. on PAMI 2010 (in press)

paper

?

"LearningProbabilistic Models for Contour Completion in Natural Images "

X. Ren, C.C. Fowlkes and J. Malik

International Journal of Computer Vision ,77:47-63, 2008

paper

?

"Local Figure/Ground Cues are Valid for Natural Images, "

C.C. Fowlkes, D.R. Martin, J. Malik

Journal of Vision, 7(8):2, 1-9,http://journalofvision.org/7/8/2/, 2007

paper

?

"Learning to Detect Natural Image Boundaries Using Local Brightness, Color andTexture Cues"

David Martin, Charless Fowlkes and Jitendra Malik

IEEE Trans. on Pattern Analysis and Machine Intelligence, 26(5), 530-549, May 2004.

paper

?

"Contour and Texture Analysis for Image Segmentation"

Jitendra Malik, Serge Belongie, Thomas Leung and Jianbo Shi

International Journal of Computer Vision, 43(1),7-27, June 2001.

paper

"NormalizedCuts and Image Segmentation"

Jianbo Shi and Jitendra Malik

IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888-905, August 2000.

Paper

"ImageRecognition: Visual Grouping, Recognition and Learning"

Joachim M. Buhmann, Jitendra Malik and Pietro Perona

Proc. of National Academy of Sciences, 96(25), 14203-14204, Dec 1999.

Paper

Shi Jianbo

又一個華人大牛！是Malik 98年的博士，論文題目是：PerceptualOrganization and Image Segmentation，做的是Normalized Cuts。N-Cuts也奠定了他在視覺學術領域譜聚類算法研究方面的地位。在卡耐基梅隆做過研究，現(xiàn)在是賓夕法尼亞大學A.P.。

研究興趣是：識別、分割、行為分析。現(xiàn)在做的偏向高層了。

他相信，grouping是感知的通用計算引擎，如何指導grouping過程來達到特定的視覺任務是他們關心的問題。

重點看http://www.cis.upenn.edu/~jshi/grouping-thoughts.html。雖然沒有特別考慮contour，但看Shi的團隊在grouping問題上根本思想是什么，并且將其思想用在contour上是很有意義的，也是可能創(chuàng)新的地方所在。

Image Segmentation and Normalized Cuts

Top-downconstraints:

Segmentation GivenPartial Grouping Constraints

Stella X. Yu and Jianbo Shi

IEEE Transactions on Pattern Analysis and Machine Intelligence,26(2):173-83, 2004

Apreliminary version appeared as:

Grouping with Bias

Stella X. Yu and Jianbo Shi

Neural Information Processing Systems (NIPS'01), Vancouver, BC,December 3-5, 2001

?

Multi-classspectral graph partitioning:

Multiclass SpectralClustering

Stella X. Yu and Jianbo Shi

International Conference on Computer Vision, Nice, France, 11-17Oct 2003

?

Randomwalk view of segmentation, and learning spectral graph partitioning:

LearningSegmentation with Random Walk

Marina Maila and Jianbo Shi

Neural Information Processing Systems, NIPS, 2001

?

A Random Walks Viewof Spectral Segmentation

Marina Maila and Jianbo Shi

AI and STATISTICS 2001(AISTATS) 2001

?

Graphwith negative weights, and asymmetric weights:

UnderstandingPopout through Repulsion

Stella X. Yu and Jianbo Shi

IEEE Conf. On Computer Vision and Pattern Recognition (CVPR), Kauai, Hawaii,December 11-13, 2001

?

Segmentationwith Directed Relationships

Stella X. Yu and Jianbo Shi

Third International Workshop on Energy Minimization Methods in ComputerVision and Pattern Recognition(EMMCVPR'01 ), INRIASophia-Antipolis, France,September 3 - 5, 2001

?

Segmentationwith Pairwise Attraction and Repulsion

Stella X. Yu and Jianbo Shi

International Conference on Computer Vision(ICCV), 2001

?

NomalizedCuts for Image segmentation:

Contour andTexture Analysis for Image Segmentation

Jitendra Malik Serge Belongie Thomas Leung and Jianbo Shi

International Journal of Computer Vision 2001

Apreliminary version appeared as

Textons,Contours and Regions: Cue Integration in Image Segmentation

Jitendra Malik Serge Belongie Thomas Leung and Jianbo Shi

Int. Conf. Computer Vision, Sept 1999(ICCV), Corfu, Greece,1999

?

Normalized Cutsand Image Segmentation

Jianbo Shi and Jitendra Malik

IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI)2000

Apreliminary version appeared as

Normalized Cuts andImage Segmentation

Jianbo Shi and Jitendra Malik

IEEE Conf. Computer Vision and Pattern Recognition(CVPR), June1997, Puerto Rico

?

Self InducingRelational Distance and its Application to Image Segmentation

Jianbo Shi and Jitendra Malik

In Fifth European Conference on Computer Vision(ECCV), June 1998

Charless C. Fowlkes

原來在UC Berkeley，現(xiàn)在UC Irvine。05年博士畢業(yè)，論文題目是：Measuringthe Ecological Validity of Grouping and Figure-Ground Cues。做的是buttom-up的segmentation跟top-down的recognition相結合方面的研究。brightness、color、texture，這些visual cues都有研究。這也是UC學派的典型研究特點。

?

P.Arbelaez, M. Maire, C. Fowlkes, J. Malik, "Contour Detection andHierarchical Image Segmentation", TPAMI,in press (2010) [pdf] [webpage]

J.Burge, C. Fowlkes, M. Banks, ``Natural-scene statistics predict how thefigure-ground cue of convexity affects human depth perception'', Journal ofNeuroscience, 30(21):7269-7280 [pdf] [supplement]

X.Ren, C. Fowlkes, J. Malik. "Learning Probabilistic Models for ContourCompletion in Natural Images", IJCV(2008), 77:47-63. [pdf]

C. Fowlkes, D. Martin, J. Malik. "LocalFigure/Ground Cues are Valid for Natural Images" Journal ofVision, 7(8):2, 1-9. [pdf] [dataset]

X. Ren, C. Fowlkes, J. Malik. "Figure/GroundAssignment in Natural Images", ECCV,Graz, Austria, (May 2006). [pdf]

X. Ren, C. Fowlkes, J. Malik. "Cue Integration forFigure/Ground Labeling", NIPS, Vancouver, Canada, (Dec.2005). [pdf]

X. Ren, C. Fowlkes, J. Malik. "Scale-InvariantContour Completion using Conditional Random Fields", ICCV,Beijing, China, (Oct. 2005). [pdf]

X. Ren, C. Fowlkes, J. Malik. "Mid-level CuesImprove Boundary Detection", Technical Report CSD-05-1382, Division ofComputer Science, University of California, Berkeley,(March 2005). [pdf]

C. Fowlkes "A Note on Planar Factor Graphs",(Oct. 2004). [pdf]

C. Fowlkes, J. Malik. "How Much Does GlobalizationHelp Segmentation?", Technical Report CSD-04-1340, Division of ComputerScience, University of California, Berkeley,(July 2004). [pdf]

D. Martin, C. Fowlkes, J. Malik. "Learning to DetectNatural Image Boundaries Using Local Brightness, Color and Texture Cues", TPAMI 26 (5) p.530-549 [pdf]

C. Fowlkes, D. Martin, J. Malik. "Learning AffinityFunctions for Image Segmentation: Combining Patch-based and Gradient-basedApproaches", CVPR, Madison, WI, (June 2003). [pdf]

D. Martin, C. Fowlkes, J. Malik. "Learning to DetectNatural Image Boundaries Using Brightness and Texture", NIPS, Vancouver,(Dec 2002). [pdf]

Ren Xiaofeng

本科是在浙大讀的，06年從berkeley博士畢業(yè)，師從大牛Jitendra Malik，所以，是Fowlkes的師弟。博士論文是：Probabilistic Models for Mid-Level Vision。現(xiàn)在是華盛頓大學的affiliate A.P.(不知道跟A.P.有何不同)，西雅圖Intel實驗室的研究科學家。

研究興趣包括圖像特征、編組、分割，目標識別，食品分析。現(xiàn)在做的是RGB-D數(shù)據(jù)（kinect hacking）的利用。做過視頻中行人的檢測跟蹤，目標輪廓提取，superpixel。

· Multi-ScaleImproves Boundary Detection in Natural Images. ? [abstract][pdf]

? Xiaofeng Ren,in ECCV'08, Marseille, 2008.

·? Local Grouping for Optical Flow.? [abstract][pdf]

? Xiaofeng Ren,in CVPR '08,Anchorage,2008.

·? Tracking as Repeated Figure/GroundSegmentation. ? [abstract][pdf][ps][bibtex][video]

? Xiaofeng Renand JitendraMalik, in CVPR '07, Minneapolis 2007.

·? Figure/Ground Assignment in Natural Images.? [abstract][pdf][ps][bibtex]

? Xiaofeng Ren, CharlessFowlkes and Jitendra Malik, in ECCV '06,volume 2, pages 614-627, Graz 2006.

·? Learning Probabilistic Models for ContourCompletion in Natural Images. ? [pdf]

? Xiaofeng Ren, CharlessFowlkes and Jitendra Malik, in IJCV Special Issue onMachine Learning for Vision, May 2008.

·? Cue Integration in Figure/Ground Labeling.? [abstract][pdf][bibtex]

? Xiaofeng Ren, CharlessFowlkes and Jitendra Malik, in NIPS'05, Vancouver 2005.

·? Scale-InvariantContour Completion using Conditional Random Fields. ? [abstract][pdf][ps][bibtex]

?Xiaofeng Ren, Charless Fowlkes and JitendraMalik, in ICCV '05, volume 2, pages 1214-1221, Beijing2005.

·? FamiliarConfiguration Enables Figure/Ground Assignment in Natural Scenes. ?[abstract][poster][bibtex]

?Xiaofeng Ren, Charless Fowlkes and JitendraMalik, in VSS 05, Sarasota, FL 2005.

·? Mid-levelCues Improve Boundary Detection. ? [abstract][pdf][ps][bibtex]

?Xiaofeng Ren, Charless Fowlkes and JitendraMalik, BerkeleyTechnical Report 05-1382, CSD 2005.

·? TheEcological Statistics of Good Continuation: Multi-scale Markov Models forContours. ? [abstract][talk][bibtex]

?Xiaofeng Ren and Jitendra Malik, in VSS 02,Sarasota, FL2002.

·? AProbabilistic Multi-scale Model for Contour Completion Based on ImageStatistics. ? [abstract][pdf][ps][bibtex]

?Xiaofeng Ren and Jitendra Malik, in ECCV '02,volume 1, pages 312-327, Copenhagen 2002.

Michael Maire

09年從berkeley畢業(yè)，師從JitendraMalik，博士論文題目：ContourDetection and Image Segmentation。現(xiàn)在在加州理工學院ComputerVision Lab做博士后。

【gPb分割算法】Using Contours to Detect and Localize Junctions in Natural Images

Michael Maire, PabloArbelaez, Charless Fowlkes, and Jitendra Malik,Computer Vision and PatternRecognition (CVPR), 2008.[PDF] [Slides][Software][Code]

Stella Yu

在卡耐基梅隆讀的博士。ShiJianbo 03的博士學生，博士題目是：Computational Models of PerceptualOrganization。從CMU畢業(yè)后到Berkeley做博士后，05年到波士頓大學做A.P.。從事譜聚類方法用于圖像分割方向的研究。

我對她的Multiscale邊緣檢測感興趣。另外，Groupingwith bias，Grouping with repulsion這些都是譜聚類的方法，看看吧，看能不能用得上。

顯著性輪廓提取、輪廓編組綜述要看的內(nèi)容（二）Stochastic Completion Fields學派

： http://blog.csdn.net/visionfans/article/details/6252015

Stochastic Completion Fields學派

97年提出來后來好像沒啥發(fā)展了。。。

David W. Jacobs

92年從MIT博士畢業(yè)，師從Eric Grimson。現(xiàn)在是Maryland大學的A.P.。關注的問題是圖像中目標的識別，知覺組織方面研究的大牛，做了很多知覺組織方面計算的和心理學方面的研究。知覺組織干的事情是，如何在識別目標前就將目標標記出來。Jacobs認為，知覺組織是識別所必須的過程，他做了研究展示二者的結合。

Perceptual Organization

· D. Jacobs, ``What Makes Viewpoint Invariant Properties Perceptually Salient?'', JOSA (A), 2003.

· Z. Liu, D. Jacobs, R. Basri ``The role of convexity in perceptual completion -- beyond good continuation''. Vision Research 39: 4244-4257, 1999.?

· D. Jacobs, ``Robust and Efficient Detection of Convex Groups'', IEEE Trans. PAMI, 18(1):23-37, 1996. Copyright (c) 1996 by IEEE.

· L. Williams, and D. Jacobs ``Local Parallel Computation of Stochastic Completion Fields'' ,? Neural Computation, 9(4):859-881, 1997.??

· L. Williams and D. Jacobs ``Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience'' , Neural Computation, 9(4):837-858, 1997.?

Lance R. Williams

94年，馬薩諸塞州大學博士畢業(yè)，題目是：Perceptual Completion of Occluded Surfaces。在NEC研究中心做過博士后，現(xiàn)在是新墨西哥大學的A.P.。跟Jacobs應該是在NEC的時候是好哥們兒，隨機完全場的理論也是他們那個期間提出來的。現(xiàn)在在學術領域已經(jīng)不活躍了。

Zweck, J.W. and L.R. Williams, Euclidean Group Invariant Computation of Stochastic Completion Fields Using Shiftable-Twistable Functions, Journal of Mathematical Imaging and Vision 21(2), pp. 135-154, 2004.

Mahamud, S., Williams, L.R., Thornber, K.K. and K. Xu, Segmentation of Multiple Salient Closed Contours from Real Images, IEEE Trans. on Pattern Analysis and Machine Intelligence 25(4), pp. 433-444, 2003.

Williams, L.R. and K.K. Thornber, Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape, Neural Computation 13(8), pp. 1683-1711, 2001.

Thornber, K.K. and L.R. Williams, Characterizing the Distribution of Completion Shapes with Corners Using a Mixture of Random Processes, Pattern Recognition 33, pp. 543-553, 2000.

Williams, L.R., Zweck, J.W., Wang, T. and K.K. Thornber, Computing Stochastic Completion Fields in Linear-Time Using a Resolution Pyramid, Computer Vision and Image Understanding 76(3), pp. 289-297, 1999.

Williams, L.R. and K.K. Thornber, A Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds, Intl. Journal of Computer Vision 34 (2/3), pp. 81-96, 1999.

Williams, L.R. and D.W. Jacobs, Local Parallel Computation of Stochastic Completion Fields, Neural Computation 9(4), pp. 859-881, 1997.

Williams, L.R. and D.W. Jacobs, Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience, Neural Computation 9(4), pp. 837-858, 1997.

Thornber, K.K. and L.R. Williams, Analytic Solution of Stochastic Completion Fields, Biological Cybernetics 75, pp. 141-151, 1996.

Williams, L.R. and A.R. Hanson, Perceptual Completion of Occluded Surfaces, Computer Vision and Image Understanding 64(1), pp. 1-20, 1996.

他還有一個碩士學生，也做顯著性閉合輪廓，碩士論文題目是：Improved Segmentation of Salient Closed Contours。

Shyjan Mahamud

02年從CMU博士畢業(yè)，題目是Discriminative Distance Measures for Object Detection。研究興趣是目標識別，知覺組織，機器學習，Structure from Motion。貌似現(xiàn)在已近不在學術界了。

在我所關注的contour grouping方面的研究，還是基于Jacobs和Williams在97年提出的Stochastic Completion Fields。

Segmentation of Salient Closed Contours from Real Images

S. Mahamud, K.K. Thornber and L.R. Williams,

IEEE International Conference on Computer Vision (ICCV),

Korfu, Greece, September 1999.

Segmentation of Multiple Salient Closed Contours from Real Images

Shyjan Mahamud, Lance R. Williams, Karvel K. Thornber and Kanglin Xu,

IEEE Trans. on Pattern Analysis and Machine Intelligence,

Vol. 25(4), April 2003.

Tensor Voting學派

Gérard Medioni

這個也是大牛了，在Microsoft Academic上索引數(shù)量達到3559。

83年南加州大學博士畢業(yè)，現(xiàn)在是南加州大學計算機與工程學院教授，01-07年是南加州大學計算機學院的Chairman。

他是Tensor Voting方法的始祖，從95年跟他的學生Gideon Guy一起提出Tensor Voting的雛形，經(jīng)過十幾年的發(fā)展，現(xiàn)在Tensor Voting方法的數(shù)學模型已經(jīng)很成熟了，而且，Tensor Voting方法在視覺的眾多領域都有廣泛應用。Tensor Voting方面已經(jīng)出了三本專著，Tensor Voting，Emerging Topics in Computer Vision，A Computational Framework for Segmentation and Grouping。

Gerard確實在十幾年鍥而不舍的打造Tensor Voting方法，有幾個學生很好的繼承并且發(fā)揚了Tensor Voting方法，

98年的博士生Min-Suen Lee，Tensor Voting for Salient Feature Inference in Computer Vision；

2000年的博士生Chi-Keung (CK) Tang，Tensor Voting in Computer Vision, Visualization, and Higher Dimensional Inferences；

03年的博士Mircea Nicolescu，A Voting-Based Computational Framework for Visual Motion Analysis and Interpretation。

05年的博士Philippos Mordohai，A Perceptual Organization Approach for Figure Completion, Binocular and Multiple-View Stereo and Machine Learning using Tensor Voting。

圖書章節(jié)：

? G. Medioni and P. Mordohai, "Saliency in Computer Vision",

In Neurobiology of attention

Edited by L. Itti, G. Rees, and J. Tsotsos, Elsevier Science, 2005

? G. Medioni, P. Mordohai, and M. Nicolescu, "The Tensor Voting Framework",

In Handbook of Geometric Computing : Applications in Pattern Recognition,

Edited by Computer Vision, E. Bayro-Corrochano, Neuralcomputing, and Robotics,

Springer-Verlag, 2005

? G. Medioni and P. Mordohai, "The Tensor Voting Framework",

Emerging Topics in Computer Vision,

Edited by S.B. Kang and G. Medioni , Prentice Hall, 2004

? G. Medioni and P. Mordohai, "Saliency in Computer Vision",

Neurobiology of Attention,

Edited by L. Itti, G. Rees, and J. Tsotsos , Elsevier Science, 2004

? C.K. Tang and G. Medioni, “Tensor Voting and Visual Segmentation”,

The Handbook of Brain Theory and Neural Networks: The Second Edition

Edited by Michael A. Arbib, 2003

? G. Medioni, P. Mordohai and M. Nicolescu, "The Tensor Voting Framework",

Handbook of Computational Geometry for Pattern Recognition,

Computer Vision, Neurocomputing and Robotics,

Edited by Eduardo Bayro-Corrochano, Springer-Verlag ,2003.

Gerard的論文有250多篇，看是看不完的，挑幾個重要期刊上發(fā)表的看吧。

Nicolescu M, Medioni G., "A voting-based computational framework for visual motion analysis and interpretation." IEEE Trans Pattern Anal Mach Intell. 2005 May;27(5):739-752

C.K. Tang, G. Medioni, P. Mordohai and W.S. Tong, "First Order Augmentations to Tensor Voting for Boundary Inference and Multiscale Analysis in 3-D", in IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume: 26, Issue: 5, pp. 594-611 May 2004

M. Nicolescu and G. Medioni, "Perceptual Grouping from Motion Cues - A 4-D Voting Approach", IEEE Transactions on Pattern Analysis and Machine Intelligence , Special Issue on Perceptual Organization in Computer Vision, vol. 25, no. 4, pp. 492-501, April 2003

P. Havaldar, G. Medioni and F. Stein, "Perceptual Grouping for Generic Recognition", International Journal of Computer Vision and Image Understanding, vol. 20, no. 1/2, pp. 59-80, 1996

G. Gideon and G. Medioni, "Inferring Global Perceptual Contours from Local Features", International Journal of Computer Vision and Image Understanding, vol. 20, no. 1/2, pp. 113-133, 1996

Philippos Mordohai

Philippos Mordohai在Gerard的學生中現(xiàn)在是Tensor Voting研究最活躍的。05年從南加州大學博士畢業(yè)，現(xiàn)在是史蒂文斯理工學院的A.P.。

P. Mordohai and G. Medioni, "Tensor Voting: A Perceptual Organization Approach to Computer Vision And Machine Learning", A.C. Bovik (editor), Synthesis Lectures on Image, Video, and Multimedia Processing, Morgan & Claypool, 136 pages, November, 2006

P. Mordohai, "A Perceptual Organization Approach for Figure Completion, Binocular and Multiple-View Stereo and Machine Learning using Tensor Voting", Ph.D. Thesis, August, 2005

Probabilistic學派(主要是York 大學)

Steve W. Zucker

Yale大牛。在CMU讀的書，Maryland做的博士后。96年前是McGrill大學的Professor，研究AI和Robotics，96年到耶魯大學任教授，是大衛(wèi)&露西帕卡德基金名譽教授。

研究范疇很廣，包括Edge，Curve，Stereo，Texture，Color，Shape，Surface，Shading and lighting，計算神經(jīng)學，視覺心理學，知覺組織，Relaxation labeling，Geometric Harmonics等。

Perceptual Organization

• Dubuc, B., and Zucker, S.W., Complexity, Confusion, and Perceptual Grouping. Part I: the curve like representation, Int. J. of Computer Vision, 42(1/2): 55-82, 2001; reprinted in J. Math. Imaging and Vision, 15(1/2): 55-82, 2001.
• Dubuc, B., and Zucker, S.W., Complexity, Confusion, and Perceptual Grouping. Part II: mapping complexity, Int. J. of Computer Vision, 42(1/2): 83-115, 2001; reprinted in J. Math. Imaging and Vision, 15 (1/2): 83-115, 2001.
• Elder, J., and Zucker, S.W., Computing Contour Closure, in B. Buxton and R. Cipolla (eds), ECCV'96 (Proc. Fourth European Conf. on Computer Vision, Cambridge, U.K., April 1996), Vol. 1: 399-412, Springer-Verlag, LNCS 1064, 1996.
• August, J., Siddiqi, K., and Zucker, S.W., Ligature Instabilities in the Perceptual Organization of Shape, Computer Vision and Image Understanding, 76(3): 231-243.
• August, J., Siddiqi, K., and Zucker, S.W., Contour Fragment Grouping and Shared, Simple Occluders, Computer Vision and Image Understanding, 76(2): 146-162, 1999.
• Elder, J., and Zucker, S.W., The Effect of Contour Closure on the Rapid Discrimination of Two-Dimensional Shapes, Vision Research, 33(7): 981-991, 1993.

§ David, C., and Zucker, S.W., Potentials, Valleys, and Dynamic Global Coverings, International Journal of Computer Vision, 5(3): 219-238, 1990.

James H. Elder

在McGill大學電子工程學院讀的碩士和博士，碩士題目是Contour closure and the perception of shape。博士師從大牛Steven W. Zucker。95年畢業(yè)，題目是The visual computation of bounding contours。畢業(yè)后在NEC研究中心干過，現(xiàn)在是York大學的A.P.。

從他碩士和博士的論文題目看，他在獲取圖像閉合輪廓方面做了很長時間的研究，要看的Elder的論文也比較多。

Journal Articles (Refereed)

Elder, J.H., Prince, S.J.D., Hou, Y., Sizintsev, M. & Olevskiy, E. (2007) Pre-attentive and attentive detection of humans in wide-field scenes, International Journal of Computer Vision, vol. 72, no. 1, 47-66.

Reprint (pdf)

Elder, J.H. & Sachs, A.J. (2004) Psychophysical receptive fields of edge detection mechanisms, Vision Research, vol. 44, no. 8, 795-813.

Reprint (pdf)

Elder, J.H., Krupnik, A. & Johnston, L.A. (2003) Contour grouping with prior models, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 25, 661-674.

Reprint (pdf)

Elder, J.H., & Goldberg, R. M. (2002). Ecological statistics of Gestalt laws for the perceptual organization of contours. Journal of Vision, 2(4), 324-353, http://journalofvision.org/2/4/5/, DOI 10.1167/2.4.5.

Reprint (pdf)

Elder, J.H. & Goldberg, R.M. (2001). Image editing in the contour domain. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, 291-296.

Reprint (pdf)

Elder, J.H. (1999) Are edges incomplete? International Journal of Computer Vision, vol. 34, no. 2/3, 97-122.

Reprint (pdf)

Elder, J.H. & Zucker, S.W. (1998). Local scale control for edge detection and blur estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 7, 699-716.

Reprint (pdf)

Elder, J.H. & Zucker, S.W. (1998). Evidence for boundary-specific grouping in human vision. Vision Research, vol. 38, no. 1, 143-152.

Reprint (pdf)

Elder, J.H. & Zucker, S.W. (1994). A measure of closure. Vision Research, vol. 34, no. 24, 3361-3370

Reprint (pdf)

Elder, J.H. & Zucker, S.W. (1993). The effect of contour closure on the rapid discrimination of two-dimensional shapes. Vision Research, vol. 33, no. 7, 981-991.

Reprint (pdf)

Francisco J. Estrada

在新聞聚合公司Thoora，瑞士洛桑理工大學的視覺小組，York大學視覺研究中心的ElderLab干過，期間跟James Elder一起做過Multi-scale的Contour Extraction。現(xiàn)在是加拿大多倫多大學的Computational Vision Group。

? Adaptive methods for boundary detection

http://www.cs.utoronto.ca/~strider/publications/POCV_adaptive.pdf

? Probabilistic inference, algorithms based on natural scene statistics

http://www.cs.utoronto.ca/~strider/publications/POCV_multiscale.pdf

http://www.cs.utoronto.ca/~strider/MultiScaleGroup.mpg

? Feature-point and patch-based clustering by appearance

http://www.cs.utoronto.ca/~strider/publications/CVPR09_ABKC.pdf

http://www.cs.utoronto.ca/~strider/KeypointClusters.mov

Vida Movahedi

Jmaes H. Elder的學生，09年博士畢業(yè)（Quality Examination），題目是Contour Grouping。沒有什么算法上的貢獻，只是給Contour Grouping提出了一種評估方法，可供Survey的評估這部分參考。

Michael Lindenbaum

以色列理工大學，研究興趣集中在分析和預測視覺處理方法的性能，跟通常實驗性的方法不同，Michael傾向于建立統(tǒng)計學模型來分析。

A. Amir and M. Lindenbaum, Quantitative Analysis of Grouping Processes. IEEE Trans. on PAMI-20, No. 2, pp. 168-185, 1998. (A shorter version appeared in ECCV, pp. 371-384, 1996.)

A. Berengolts and M. Lindenbaum, On the Performance of Connected Components Grouping . IJCV 41(3), pp. 195-216, 2001.

M. Lindenbaum and A. Berengolts, A Probabilistic Interpretation of the Saliency Network . ECCV, vol. II, pp. 257-272, 2000.

A. Berengolts and M. Lindenbaum, On the Distribution of Saliency . CVPR (2), pp. 543-549, 2004.

E.A. Engbers, M. Lindenbaum and A.W.M. Smeulders, An Information-Based Measure for Grouping Quality. ECCV (3), pp. 392-404, 2004

Ratio Cut學派

Song Wang

南卡羅來納大學——哥倫比亞分校(USCC)，A.P.。研究范疇包括計算機詩視覺，醫(yī)學圖像處理，機器學習。USC Computer Vision Lab的頭兒，2010年CVPR workshop POCV Chair。

Ratio-Cut是輪廓編組比較有名的一個重要算法，是Wang Song跟J. M. Siskind在01年提出的，03年發(fā)到PAMI上。我擦，Wang Song的Ratio-Cut剛剛提出來的時候也只是用于Segmentation，并沒有用于Contour Grouping。后來，往Contour Grouping上一遷移，又發(fā)了篇PAMI！

后期CG相關的文章都是跟Joachim S. Stahl一起發(fā)的，Convex Grouping，結合region和boundary信息。

o S. Wang, J. M. Siskind. Image Segmentation with Minimum Mean Cut, IEEE International Conference on Computer Vision (ICCV), I:517-524, Vancouver, Canada, 2001 (PDF)

o S. Wang, J. M. Siskind. Image Segmentation with Ratio Cut, IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(6):675-690, 2003 (PDF)

o S. Wang, T. Kubota, J. M. Siskind. Salient Boundary Detection Using Ratio Contour, Neural Information Processing Systems Conference (NIPS), 1571-1578, Vancouver, Canada, 2003 (PDF)

o S. Wang, J. Wang, T. Kubota. From Fragments to Salient Closed Boundaries: An In-Depth Study, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), I:291-298, Washington, DC, 2004 (PDF)

o S. Wang, T. Kubota, J. M. Siskind, J. Wang. Salient Closed Boundary Extraction with Ratio Contour,? IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(4):546-561, 2005 (PDF)

o J. S. Stahl, S. Wang. Convex Grouping Combining Boundary and Region Information, IEEE International Conference on Computer Vision (ICCV), II:946-953, Beijing, China, 2005 (PDF)

o J. S. Stahl, S. Wang, Globally Optimal Grouping for Symmetric Boundaries, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), I:1030-1037, New York, NY, 2006 (PDF)

o S. Wang, J. S. Stahl, A. Bailey, M. Dropps. Global Detection of Salient Convex Boundaries, International Journal of Computer Vision, 71(3):337-359, 2007 (PDF)

o J. S. Stahl, S. Wang. Edge Grouping Combining Boundary and Region Information, IEEE Transactions on Image Processing, 16(10):2590-2606, 2007 (PDF)

o J. S. Stahl, K. Oliver, S. Wang. Open Boundary Capable Edge Grouping with Feature Maps, IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV), Anchorage, AK, 2008 (PDF)

o J. S. Stahl, S. Wang. Globally Optimal Grouping for Symmetric Closed Boundaries by Combining Boundary and Region Information, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(3):395-411, 2008 (PDF)

Joachim S. Stahl

USC Computer Vision Lab 08年的博士，題目是：Combining Boundary and Region Information for Perceptual Organization。04-08在USC當助教，現(xiàn)在是克拉克森大學的A.P.。研究集中于圖像分割，知覺組織，編組。

J. S. Stahl "Edge Grouping for Detecting Salient Boundaries with Sharp Corners", Indian International Conference on Artificial Intelligence - IICAI , pp. 2237-2248, 2009

J. S. Stahl, K. Oliver, S. Wang. "Open Boundary Capable Edge Grouping with Feature Maps", IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV), Anchorage, AK, June 2008. (PDF)

J. S. Stahl, S.Wang, "Globally Optimal Grouping for Symmetric Closed Boundaries by Combining Boundary and Region Information" IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 30, no. 3, pp. 395-411, March 2008. (PDF)

J. S. Stahl, S. Wang. "Edge Grouping Combining Boundary and Region Information", IEEE Transactions on Image Processing (TIP), vol. 16, no. 10, pp. 2590-2606, October 2007. (PDF 11 MB!)

S. Wang, J. S. Stahl, A. Bailey, M. Dropps. "Global Detection of Salient Convex Boundaries", International Journal of Computer Vision (IJCV), vol. 71, no. 3, pp. 337-359, March 2007. (PDF)

J. S. Stahl, S. Wang. "Globally Optimal Grouping for Symmetric Boundaries", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 1030-1037, New York, NY, 2006. (PDF)

J. S. Stahl, S. Wang. "Convex Grouping Combining Boundary and Region Information", IEEE International Conference on Computer Vision (ICCV), vol. 2, pp. 946-953, Beijing, China, 2005. (PDF)

總結

以上是生活随笔為你收集整理的边缘提取和场景分割 学派？的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。