8.6 Techniques for Model Guided Segmentation, Context in Segmentation

Chapter Contents (Back)
Segmentation, Knowledge. Segmentation, Context. Segmentation, Guided. Model Based Segmentation. Segmentation, Model Based.

Shaheen, S.I.[Samir I.], Levine, M.D.[Martin D.],
Some Experiments with the Interpretation Strategy of a Modular Computer Vision System,
PR(14), No. 1-6, 1981, pp. 87-90.
WWW Version. 0309
BibRef

Levine, M.D., and Shaheen, S.I.,
A Modular Computer Vision System for Picture Segmentation and Interpretation,
PAMI(3), No. 5, September 1981, pp. 540-556. BibRef 8109
Earlier:
A Modular Computer Vision System for Picture Segmentation,
PRIP79(523-539). BibRef

Kropatsch, W.G.,
Segmentation of Digital Images Using a Priori Information about the Expected Image Contents,
PDA83(107-132). BibRef 8300

Zamperoni, P.,
Model-Based Segmentation of Grey-Tone Images,
IVC(2), No. 3, August 1984, pp. 123-133.
WWW Version. BibRef 8408

Zamperoni, P.,
Feature Extraction by Rank-Order Filtering for Image Segmentation,
PRAI(2), 1988, pp. 301-319. BibRef 8800

Zamperoni, P.,
Some Adaptive Rank Order Filters for Image Enhancement,
PRL(11), 1990, pp. 81-86. BibRef 9000

Zamperoni, P.,
Mode Estimation and Non-Linear Image Smoothing with Adaptive Rank-Order Filters,
Draft1989. BibRef 8900

Hyde, J., Fullwood, J.A., Corrall, D.R.,
An Approach to Knowledge-Driven Segmentation,
IVC(3), No. 4, November 1985, pp. 198-205.
WWW Version. BibRef 8511

Matsuyama, T.,
Expert Systems for Image Processing: Knowledge-Based Composition of Image Analysis Processes,
CVGIP(48), No. 1, October 1989, pp. 22-49.
WWW Version. BibRef 8910
Earlier: ICPR88(I: 125-133).
IEEE DOI Link 8811
Rule Based Systems. System: SIGMA. This builds on the general systems such as SIGMA and is directed toward segmentation. BibRef

Nagao, M., Matsuyama, T., and Ikeda, Y.,
Region Extraction and Shape Analysis in Aerial Photographs,
CGIP(10), No. 3, July 1979, pp. 195-223.
WWW Version. BibRef 7907
Earlier:
Region Extraction and Shape Analysis of Aerial Photographs,
ICPR78(620-628). This uses a global to detailed analysis technique. BibRef

Tenenbaum, J.M., and Barrow, H.G.,
Experiments in Interpretation Guided Segmentation,
AI(8), No. 3, June 1977, pp. 241-274.
WWW Version. BibRef 7706
And: SRI AICenter-TN 123, March 1976. BibRef
And:
IGS: A Paradigm for Integrating Image Segmentation and Interpretation,
PRAI-76(472-507). BibRef
And: ICPR76(504-513). BibRef
And: CMetImAly77(435-444). Segmentation, Knowledge. System: IGS. The key idea is that image elements can be reliably clustered into regions if semantic interpretations are used in addition to the raw image values. This builds on the interpretation ideas of MSYS ( See also MSYS: A System for Reasoning about Scenes. ). Unlike the work in Yakimovsky and Feldman, the relations between different types of regions are either possible or impossible. Initial interpretations are based on the image data, but extra interpretations at this point are not harmful. An iterative procedure is used to eliminate interpretations that are not valid given all the possible interpretations of the neighbors. When adjacent regions have the same interpretation they can be merged. This method requires a very specific model of the possible scene to provide any benefit. BibRef

Chassery, J.M., and Garbay, C.,
An Iterative Segmentation Method Based on a Contextual Color and Shape Criterion,
PAMI(6), No. 6, November 1984, pp. 794-799. BibRef 8411
Earlier: ICPR84(642-644). Segmentation, Color. BibRef

Garbay, C.,
Image Structure Representation and Processing: A Discussion of Some Segmentation Methods in Cytology,
PAMI(8), No. 2, March 1986, pp. 140-146. BibRef 8603
Earlier:
Knowledge and Strategies for Image Segmentation,
ICPR86(669-671). BibRef

Vasselle, B., Giraudon, G.,
A Multiscale Regularity Measure as a Geometric Criterion for Image Segmentation,
MVA(7), No. 4, 1994, pp. 229-236. BibRef 9400

Houzelle, S., and Giraudon, G.,
Model Based Region Segmentation Using Cooccurrence Matrices,
CVPR92(636-639).
IEEE Abstract. IEEE Top Reference. Base segmentation on second order statistics. BibRef 9200

Tucker, L.W., (Cornell and Polytechnic I of NY)
Model-Guided Segmentation Using Quadtrees,
ICPR84(216-219). BibRef 8400
And:
Control Strategy for an Expert Vision System Using Quadtree Refinement,
CVWS84(214-218). Innovative use of quadtrees in segmentation. BibRef

Harwood, D.A., Chang, S., and Davis, L.S.,
Interpreting Aerial Photographs by Segmentation and Search,
DARPA87(507-520). ( See also Sigma Image Understanding System, The. ) Find segments (homogeneous regions), then find instances which satisfy definitions of object types, then search for support, then improve instances, then iterate with new estimates of parameters. See also Fua and Leclerc Guided Segmentation Papers. BibRef 8700

Kestner, W.,
Segmentation and Abstract Interpretation in an Image Understanding System,
ICPR82(1011-1013). BibRef 8200
Earlier:
Considerations About Knowledge-Based Image Interpretation,
ICPR80(330-332). High level discussion of a high level system for image analysis using different descriptions and the different levels of abstraction and different programs to link between the different levels. BibRef

Kestner, W., Bohner, M., Scharf, R., and Sties, M.,
Object Guided Segmentation of Aerial Images,
ICPR80(529-531). (Karlsruhe). Starting from (interactively selected) elements (line segments, rough contours, centers of regions) expand to complete lines or regions. Interactive. Basically grow the object as long as the feature values remain constant or change gradually. Boundaries between regions handled by pixel level analysis - initial expansion is based on features over larger areas. BibRef 8000

Selfridge, P.G., Sloan, Jr., K.R.,
Reasoning About Images: Using Meta-Knowledge in Aerial Image Understanding,
IJCAI81(755-757). BibRef 8100
Earlier:
Reasoning About Images: Application to Aerial Image Understanding,
DARPA81(1-6). BibRef
And:
Locating Objects under Different Conditions: An Example in Aerial Image Understanding,
PRIP81(470-472). (Rochester). Segmentation and analysis system to use partial results to perform matching then update parameters for segmentation. Given an appearance model, an initial threshold based segmentation is applied, e.g., building and shadow. Candidate regions are matched to select most likely, and the threshold is varied to find the region which produces the best match. Extensive use of partial matching results. BibRef

Selfridge, P.G.,
Reasoning About Success and Failure in Aerial Image Understanding,
Ph.D.Thesis (CS), May 1983, BibRef 8305 Univ. of Rochester-TR-103. BibRef
And: with Sloan, Jr., K.R., PRIP82(44-49). Segmentation problems: what to look for, which technique to use, and the parameters for the procedure. Goal directed processing at every stage. Given a model of the objects, pick a segmentation method (thresholding), set arbitrary thresholds (almost), change them to get candidate regions, evaluate based on other features. Then in conjunction with higher level model descriptions composed into groups or structures and look at where other pieces can occur. BibRef

Sloan, Jr., K.R.,
Representation and Communication of Image-Related Information,
DARPAN79(136-139). BibRef 7900

Mota, F.A., and Velasco, F.R.D.,
A Method for the Analysis of Ambiguous Segmentations of Images,
PAMI(8), No. 6, November 1986, pp. 755-760. Seems to be a discussion of using the model (interpretation) information to eliminate segmentation "errors." BibRef 8611

Mason, P., Buggy, T.W.,
Knowledge-Based Segmentation of Sonar Data,
IVC(5), No. 2, May 1987, pp. 127-131.
WWW Version. BibRef 8705

Sunil Kumar, K., Desai, U.B.,
Joint segmentation and image interpretation,
PR(32), No. 4, April 1999, pp. 577-589.
WWW Version. BibRef 9904
Earlier: ICIP96(I: 853-856).
IEEE DOI Link 9610
See also Image Interpretation Using Bayesian Networks. BibRef

Kopparapu, S.I.K.[Sun-Il K.], Desai, U.B.[Uday B.],
Bayesian Approach to Image Interpretation,
KluwerBoston, July 2001. ISBN 0-7923-7372-3.
WWW Version. Combine segmentation and interpretation modules. BibRef 0107

Figov, Z., Tal, Y., and Koppel, M.[Moshe],
Detecting and Removing Shadows,
ICCGI04(xx-yy).
PDF Version. BibRef 0400

Kamath, N.[Nidish], Kopparapu, S.I.K.[Sun-Il K.], Desai, U.B., Dugud, R.[Rakesh],
Joint Segmentation and Image Interpretation Using Hidden Markov Models,
ICPR98(Vol II: 1840-1842).
IEEE DOI Link 9808
BibRef

Molander, S., Broman, H.,
Knowledge-based segmentation and state-based control in image analysis: Two examples from the biomedical domain,
SP(32), No. 1-2, 1993, pp. 201-215. BibRef 9300

Ezquerra, N.[Norberto], Mullick, R.[Rakesh],
Knowledge-Guided Segmentation of 3D Imagery,
GMIP(58), No. 6, November 1996, pp. 510-523. 9701
BibRef

Ezquerra, N.[Norberto], Mullick, R.[Rakesh],
An Approach to 3D Pose Estimation,
TOG(15), No. 2, April 1996, pp. 99-120. BibRef 9604

Haker, S., Sapiro, G., Tannenbaum, A.,
Knowledge-Based Segmentation of SAR Data with Learned Priors,
IP(9), No. 2, February 2000, pp. 299-301.
IEEE DOI Link 0003
BibRef

Baujard, O., Garbay, C.,
KISS: A Multiagent Segmentation System,
OptEng(32), No. 6, June 1993, pp. 1235-1249. BibRef 9306

Manon, G., Pesty, S., Garbay, C.,
KIDS (knowledge-based diagnosis system)-a specialized architecture,
ICPR88(II: 995-997).
IEEE DOI Link 8811
BibRef

Rushing, J.A., Ranganath, H., Hinke, T.H., Graves, S.J.,
Image segmentation using association rule features,
IP(11), No. 5, May 2002, pp. 558-567.
IEEE DOI Link 0206
BibRef

Evans, C., Jones, R., Svalbe, I., Berman, M.,
Segmenting Multispectral Landsat TM Images into Field Units,
GeoRS(40), No. 5, May 2002, pp. 1054-1064.
IEEE Top Reference. 0206
BibRef

Goldberger, J.[Jacob], Greenspan, H.[Hayit],
Context-Based Segmentation of Image Sequences,
PAMI(28), No. 3, March 2006, pp. 463-468.
IEEE DOI Link 0602
New frames segmented based on the segmentation of prior frames. BibRef

Eriksson, A.P.[Anders P.], Olsson, C.[Carl], Kahl, F.[Fredrik],
Normalized Cuts Revisited: A Reformulation for Segmentation with Linear Grouping Constraints,
ICCV07(1-8).
IEEE DOI Link 0710
BibRef
And:
Image Segmentation with Context,
SCIA07(283-292).
Springer DOI Link 0706
BibRef

Mu, Y.D.[Ya-Dong], Zhou, B.F.[Bing-Feng],
Co-segmentation of Image Pairs with Quadratic Global Constraint in MRFs,
ACCV07(II: 837-846).
Springer DOI Link 0711
BibRef

Toyoda, T.[Takahiro], Hasegawa, O.[Osamu],
Random Field Model for Integration of Local Information and Global Information,
PAMI(30), No. 8, August 2008, pp. 1483-1489.
IEEE DOI Link 0806
BibRef

Toyoda, T.[Takahiro], Tagami, K.[Keisuke], Hasegawa, O.[Osamu],
Integration of Top-down and Bottom-up Information for Image Labeling,
CVPR06(I: 1106-1113).
IEEE DOI Link 0606
BibRef

Rahmani, R.[Rouhollah], Goldman, S.A.[Sally A.], Zhang, H.[Hui], Cholleti, S.R.[Sharath R.], Fritts, J.E.[Jason E.],
Localized Content-Based Image Retrieval,
PAMI(30), No. 11, November 2008, pp. 1902-1912.
IEEE DOI Link 0809
System, ACCIO. Interested only in part of the iamge. Extend traditional segmentation-based and salient point-based techniques to capture content. Salient points using SPARSE (filtered Haar-wavelet points) Wavelet (Variably Split Window with Neighbor) SIFT ( See also Distinctive Image Features from Scale-Invariant Keypoints. ) BibRef

Zhang, H.[Hui], Goldman, S.A.,
Image Segmentation using Salient Points-Based Object Templates,
ICIP06(765-768). 0610

IEEE DOI Link BibRef

Gould, S.[Stephen], Rodgers, J.[Jim], Cohen, D.[David], Elidan, G.[Gal], Koller, D.[Daphne],
Multi-Class Segmentation with Relative Location Prior,
IJCV(80), No. 3, December 2008, pp. xx-yy.
Springer DOI Link 0810
Using spatial relations in segmentation. BibRef

Crevier, D.[Daniel],
Image segmentation algorithm development using ground truth image data sets,
CVIU(112), No. 2, November 2008, pp. 143-159.
WWW Version. 0811
BibRef
Earlier:
Extracting Salient Objects from Operator-Framed Images,
CRV07(36-43).
IEEE DOI Link 0705
Computer vision; Image segmentation; Performance measures; Ground truth images; Image data sets; Parameter learning; Texture; Edge detection; Region growing; Data engineering tools and techniques; Stochastic optimization BibRef

Borenstein, E.[Eran], Ullman, S.[Shimon],
Combined Top-Down/Bottom-Up Segmentation,
PAMI(30), No. 12, December 2008, pp. 2109-2125.
IEEE DOI Link 0811
BibRef
Earlier:
Learning to Segment,
ECCV04(Vol III: 315-328).
WWW Version. 0405
BibRef
Earlier:
Class-Specific, Top-Down Segmentation,
ECCV02(II: 109 ff.).
HTML Version. 0205
Guided by a stored representation of the shape. Find the foreground objects, they generally are more fragmented (textured?). BibRef

Borenstein, E.[Eran], Sharon, E.[Eitan], Ullman, S.[Shimon],
Combining Top-Down and Bottom-Up Segmentation,
PercOrg04(46).
IEEE DOI Link 0502
BibRef

Ross, M.G.[Michael G.], Kaelbling, L.P.[Leslie Pack],
Segmentation According to Natural Examples: Learning Static Segmentation from Motion Segmentation,
PAMI(31), No. 4, April 2009, pp. 661-676.
IEEE DOI Link 0903
BibRef
Earlier:
Learning object segmentation from video data,
MIT AIM-2003-022, September 8, 2003.
WWW Version. 0501
Trained on video that uses background subtraction to find objects in video. Then segment static scene using learned values. BibRef

Burrus, N.[Nicolas], Bernard, T.M.[Thierry M.], Jolion, J.M.[Jean-Michel],
Image segmentation by a contrario simulation,
PR(42), No. 7, July 2009, pp. 1520-1532.
Elsevier DOI Link
WWW Version. 0903
BibRef
Earlier:
Bottom-Up and Top-Down Object Matching Using Asynchronous Agents and a Contrario Principles,
CVS08(xx-yy).
Springer DOI Link 0805
Segmentation; A contrario reasoning; Statistical image processing; Monte-Carlo simulation. hierarchy of independent agents. Strength based on relevance of visual data. BibRef

Burrus, N.[Nicolas], Bernard, T.M.[Thierry M.],
Adaptive Vision Leveraging Digital Retinas: Extracting Meaningful Segments,
ACIVS06(220-231).
Springer DOI Link 0609
Extract segments that depart from the norm. BibRef


Warrell, J.[Jonathan], Prince, S.J.D.[Simon J.D.], Moore, A.P.[Alastair P.],
Epitomized priors for multi-labeling problems,
CVPR09(2812-2819).
IEEE DOI Link 0906
Combine local and context for segmentation. BibRef

Mukherjee, L.[Lopamudra], Singh, V.[Vikas], Dyer, C.R.[Charles R.],
Half-integrality based algorithms for cosegmentation of images,
CVPR09(2028-2035).
IEEE DOI Link 0906
Segment same object in pair of images. Segment each with constraint from the other. BibRef

Li, T.[Teng], Mei, T.[Tao], Yan, S.C.[Shui-Cheng], Kweon, I.S.[In-So], Lee, C.W.[Chil-Woo],
Contextual decomposition of multi-label images,
CVPR09(2270-2277).
IEEE DOI Link 0906
Context for segmentation. BibRef

Driesen, J., Scheunders, P.,
A Multicomponent Image Segmentation Framework,
ACIVS08(xx-yy).
Springer DOI Link 0810
BibRef

Besbes, A.[Ahmed], Komodakis, N.[Nikos], Langs, G.[Georg], Paragios, N.[Nikos],
Shape priors and discrete MRFs for knowledge-based segmentation,
CVPR09(1295-1302).
IEEE DOI Link 0906
BibRef

Essafi, S.[Salma], Langs, G.[Georg], Paragios, N.[Nikos],
Sparsity, redundancy and optimal image support towards knowledge-based segmentation,
CVPR08(1-7).
IEEE DOI Link 0806
BibRef

Ahmad, J.E.[Jawad Elsayed], Takakura, Y.[Yoshitate],
Improving Segmentation Maps using Polarization Imaging,
ICIP07(I: 281-284).
IEEE DOI Link 0709
BibRef

Wallhoff, F.[Frank], Rub, M.[Martin], Rigoll, G.[Gerhard], Gobel, J.[Johann], Diehl, H.[Hermann],
Improved Image Segmentation using Photonic Mixer Devices,
ICIP07(VI: 53-56).
IEEE DOI Link 0709
BibRef

Gallagher, C.[Claire], Kokaram, A.[Anil],
Bayesian Example Based Segmentation using a Hybrid Energy Model,
ICIP07(II: 41-44).
IEEE DOI Link 0709
BibRef

Cheng, D.S.[Dong Seon], Figueiredo, M.A.T.[Mario A.T.],
Cosegmentation for Image Sequences,
CIAP07(635-640).
IEEE DOI Link 0709
Simultaneous segmentation of the same features in multiple images. BibRef

Hong, X.[Xin], McClean, S.[Sally], Scotney, B.W.[Bryan W.], Morrow, P.J.[Philip J.],
Model-Based Segmentation of Multimodal Images,
CAIP07(604-611).
Springer DOI Link 0708
BibRef

Vasconcelos, M.[Manuela], Vasconcelos, N.[Nuno], Carneiro, G.[Gustavo],
Weakly Supervised Top-down Image Segmentation,
CVPR06(I: 1001-1006).
IEEE DOI Link 0606
BibRef

Borenstein, E.[Eran], Malik, J.[Jitendra],
Shape Guided Object Segmentation,
CVPR06(I: 969-976).
IEEE DOI Link 0606
BibRef

Johnson, M.A., Cipolla, R.,
Improved Image Annotation and Labelling through Multi-Label Boosting,
BMVC05(xx-yy).
HTML Version. 0509
Learning based on multi-labelled data. BibRef

Schnitman, Y.[Yaar], Caspi, Y.[Yaron], Cohen-Or, D.[Daniel], Lischinski, D.[Dani],
Inducing Semantic Segmentation from an Example,
ACCV06(II:373-384).
Springer DOI Link 0601
BibRef

Clark, A.A., Thomas, B.T.,
Evolving Image Segmentations for the Analysis of Video Sequences,
CVPR01(II:290-295).
IEEE Abstract. IEEE Top Reference. 0110
Use initial segmentation to guide later ones. BibRef

Perner, P.[Petra],
Controlling the Segmentation Parameters by Case-based Reasoning,
ICPR00(Vol III: 963-966).
IEEE DOI Link 0009
BibRef
Earlier:
Case based reasoning for image interpretation,
CAIP95(532-537).
Springer DOI Link 9509
BibRef

Hug, J., Brechbuhler, C., Szekely, G.,
Model-Based Initialisation for Segmentation,
ECCV00(II: 290-306).
WWW Version. 0003
BibRef

Charroux, B., Philipp, S., Cocquerez, J.P.,
Image Analysis: Segmentation Operator Cooperation Led by the Interpretation,
ICIP96(III: 939-942).
IEEE DOI Link BibRef 9600

Paulus, D.,
Object oriented image segmentation,
ICIPA92(482-485).
Postscript Version. BibRef 9200

Baker, D.C., Aggarwal, J.K., and Hwang, V.S.,
Geometry Guided Incremental Segmentation,
CVWS87(237-239). BibRef 8700

Price, K.E., Medioni, G.,
Segmentation Using Scene Models,
USC_ISG-102, October 1982. BibRef 8210 USC Computer VisionCombine region and edge models. BibRef

Medioni, G.G.[Gerard G.],
Segmentation of Images Into Regions Using Edge Information,
AAAI-82(42-45). BibRef 8200 USC Computer Vision BibRef

Sze, T.W., and Yang, Y.H.,
Goal Directed Segmentation,
PRIP82(504-511). How to use some of the a priori information in segmentation (such as shape). Compares this to gradient based boundary extraction followed by labeling of inside or outside (unclean). Also to split and merge. Method generates initial regions (either method) polygonal approximation, shape matching using syntactic methods and merge regions which improve the shape match. BibRef 8200

Aggarwal, R.K.,
Adaptive Image Segmentation Using Prototype Similarity,
PRIP78(354-359) BibRef 7800

Chapter on 2-D Region Segmentation Techniques, Snakes, Active Contours continues in
Fua and Leclerc Guided Segmentation Papers .


Last update:Nov 16, 2009 at 19:35:14