13.4.3 Model Based Recognition Systems

Chapter Contents (Back)
Object Recognition. Matching, Models. Recognition, Model Based. Model Based Recognition. Recognition, Systems.

Recognition Robotics,Inc.,
2009. Recognition based on HVS techniques.
WWW Link. Vendor, Object Recognition.

Nerual ID,
2008. Recognition based on learning.
WWW Link. Vendor, Object Recognition.

Roberts, L.G.,
Machine Perception of 3-D Solids,
OE-OIP65(159-197). BibRef 6500 CMetImAly77(285-323). BibRef
And: Ph.D.Thesis, MIT, May 1963. Early Vision System. Recognize Line Models. This is the paper everyone should read. Early block analysis using edges, lines, models, graphics, etc. This system is the first three-dimensional vision system and contains many of the operations in all later complete systems. It used models of three-dimensional (polyhedral) objects and matches them to the representations computed from the input data to find blocks in the image. Complex shapes were composed of several blocks. Blocks are described by their edges--a wire-frame model. Thus image edges are extracted for the image by a simple 2X2 operator. The edges are collected into lines based on adjacency, the small lines are eliminated, and the long ones are extended to intersect at corners. These lines are matched against model objects that allow changes in the rotation and scaling parameters. Once an elementary object is recognized, its line segments are removed from the image representation and the match process continues with the other lines. BibRef

Rosenthal, D.A., and Bajcsy, R.,
Visual and Conceptual Hierarchy: A Paradigm for Studies of Automated Generation of Recognition Strategies,
PAMI(6), No. 3, May 1984, pp. 319-325. BibRef 8405

Bajcsy, R., Rosenthal, D.A.,
What One Can See on the Earth from Different Altitudes: A Hierarchical Control Structure in Computer Vision,
PRIP77(108-111). BibRef 7700

Rosenthal, D.A., and Bajcsy, R.,
Conceptual and Visual Focusing in the Recognition Process as Induced by Queries,
ICPR78(417-420). BibRef 7800

Rosenthal, D.A.,
An Inquiry Driven Vision System Based on Visual and Conceptual Hierarchies,
UMI Research PressAnn Arbor, MI, 1981. BibRef 8100 Ph.D.Thesis. Book from his thesis. BibRef

Bajcsy, R., Rosenthal, D.A.,
Visual Focusing and Defocusing: An Essential Part of Pattern Recognition Process,
CGPR75(130-134). BibRef 7500

Rummel, P., Beutel, W.,
Workpiece Recognition and Inspection by a Model-Based Scene Analysis System,
PR(17), No. 1, 1984, pp. 141-148.
Elsevier DOI BibRef 8400

Rummel, P., Kollensperger, P.,
GSS: A Fast, Model-Based Vision System for Workpiece Recognition,
PRAI(2), 1988, pp. 543-556. BibRef 8800

Chin, R.T., and Dyer, C.R.,
Model-Based Recognition in Robot Vision,
Surveys(18), No. 1, March 1986, pp. 67-108. Knowledge-Based Vision. Model Based Vision. Survey, Matching. Survey, Robot Vision. Matching, Models. Robot Vision, Survey. BibRef 8603
Earlier:
Model-Based Industrial Part Recognition: Systems and Algorithms,
Univ. of WisconsinTR 538, March 1984. Comparison of various techniques organized by 2-D, 2.5-D and 3-D representations considering feature extraction, modeling and matching for each. BibRef

Shneier, M.O., Lumia, R., and Herman, M.,
Prediction-Based Vision for Robot Control,
Computer(20), No. 8, August 1987, pp. 46-55. The use of feed-back to bring the internal representation of the environment into registration with the real world. BibRef 8708

Shneier, M.O.[Michael O.], Lumia, R.[Ronald], Kent, E.W.[Ernest W.],
Model-Based Strategies for High-Level Robot Vision,
CVGIP(33), No. 3, March 1986, pp. 293-306.
Elsevier DOI Talks about a general system, it doesn't give much specific. BibRef 8603

Shneier, M.O.[Michael O.],
A Compact Relational Structure Representation,
IJCAI79(818-826). BibRef 7900
Earlier:
Recognition Using Semantic Constraints,
IJCAI77(585-589). BibRef

Fisher, R.B.,
SMS: A Suggestive Modelling System for Object Recognition,
IVC(5), No. 2, May 1987, pp. 98-104.
Elsevier DOI BibRef 8705
Earlier:
SMS: A Suggestive Modeling System for Object Recognition,
Alvey86(xx). BibRef Edinburghobject modelling for visual recognition. Curve, surface and volumetric structural descriptions.
See also Representing 3D Structures for Visual Recognition. BibRef

Fitzgibbon, A.W., Fisher, R.B.,
Suggestive Modeling for Machine Vision,
SPIE(1830), 1992, pp. 315-320. BibRef 9200 Edinburghgeometric modelling for object recognition BibRef

Fisher, R.B.,
Model Invocation for Three Dimensional Scene Understanding,
IJCAI87(805-807). BibRef 8700 EdinburghKW: visual model-base selection BibRef

Brown, M.D., Fisher, R.B.,
A Distributed Blackboard System for Vision Applications,
BMVC90(163-168).
PDF File. BibRef 9000 Edinburghvisual processing control BibRef

Fisher, R.B., Orr, M.J.L.,
Geometric Reasoning in a Parallel Network,
IJRR(10), 1991, pp. 103-122. BibRef 9100 Edinburgh BibRef

Orr, M.J.L., Fisher, R.B.,
Geometric Reasoning for Computer Vision,
IVC(5), No. 3, August 1987, pp. 233-238.
Elsevier DOI BibRef 8708 EdinburghGeneral reasoning tasks. BibRef

Orr, M.J.L., Fisher, R.B.,
Interval-Based Geometric Reasoning in a Parallel Network,
MRSC91(xx). BibRef 9100 Edinburgh BibRef

Fisher, R.B., Orr, M.J.L.,
Experiments with a Network-Based Geometric Reasoning Engine,
IJCAI89(1623-1628). BibRef 8900 Edinburghgeometric reasoning, pose estimation BibRef

Fisher, R.B.,
Recognizing Objects Using Surface Information and Object Models,
IEE-ICIP86(149-153). BibRef 8600 EdinburghJune 1986. model-based 3D object recognition BibRef

Kane, T.B., McAndrew, P., Wallace, A.M.,
Model-Based Object Recognition Using Probabilistic Logic and Maximum Entropy,
PRAI(5), 1991, pp. 425-437. BibRef 9100

Arman, F., and Aggarwal, J.K.,
Model-Based Object Recognition in Dense Range Images,
Surveys(25), No. 1, March 1993, pp. 5-43. Survey, Recognition.
See also Segmentation of 3-D Range Images Using Pyramidal Data Structures. BibRef 9303

Arman, F.[Farshid], Aggarwal, J.K.,
CAD-Based Vision: Object Recognition in Cluttered Range Images Using Recognition Strategies,
CVGIP(58), No. 1, July 1993, pp. 33-48.
DOI Link Froa a model, overlapping objects. BibRef 9307

Puliti, P.[Paolo], Tascini, G.[Guido],
Knowledge-based approach to image interpretation,
IVC(11), No. 3, April 1993, pp. 122-128.
Elsevier DOI 0401
image segmentation; low level object interpretation; and high level biomedical object interpretation. BibRef

Stilla, U.,
Map-Aided Structural-Analysis of Aerial Images,
PandRS(50), No. 4, August 1995, pp. 3-10. Blackboard system. Context applied to aerial images. BibRef 9508

Arbel, T., Whaite, P., Ferrie, F.P.,
Parametric Shape-Recognition Using a Probabilistic Inverse-Theory,
PRL(17), No. 5, May 1 1996, pp. 491-501. 9606
BibRef
Earlier:
Recognizing Volumetric Objects in the Presence of Uncertainty,
ICPR94(A:470-476).
IEEE DOI BibRef

Arbel, T., Ferrie, F.P., Mitran, M.,
Recognizing Objects From Curvilinear Motion,
BMVC00(xx-yy).
PDF File. 0009
BibRef

Morton, S.K., Popham, S.J.,
Algorithm Design Specification for Interpreting Segmented Image Data Using Schemas and Support Logic,
IVC(5), No. 3, August 1987, pp. 206-216.
Elsevier DOI BibRef 8708

Freytag, R., Haettich, W., Wandres, H.,
Development Tools for a Model Directed Workpiece Recognition System,
PR(19), No. 4, 1986, pp. 267-278.
Elsevier DOI From models. BibRef 8600

Haettich, W., Wandres, H.,
Automatic learning of structural models for workpiece recognition systems,
ICPR90(I: 279-281).
IEEE DOI 9006
BibRef

Ogata, H., Takahashi, T.,
Robotic Assembly Operation Teaching in a Virtual Environment,
RA(10), 1994, pp. 391-399. BibRef 9400

Gao, Q.G.,
Man Made Object Recognition Based on Visual Perception,
JEI(7), No. 1, January 1998, pp. 104-110. 9807
BibRef

Robert, L., Malandain, G.,
Fast Binary Image Processing Using Binary Decision Diagrams,
CVIU(72), No. 1, October 1998, pp. 1-9.
DOI Link BibRef 9810
Earlier: CVPR97(97-102).
IEEE DOI 9704
Generate C code from BDD for simple tasks. BibRef

Pece, A.E.C.[Arthur E.C.], Larsen, R.[Rasmus],
Generative model based vision,
CVIU(106), No. 1, April 2007, pp. 3-4.
Elsevier DOI 0704
BibRef
Earlier: A1, Only: IVC(21), No. 1, January 2003, pp. 1-3.
Elsevier DOI 0401
Special issue introductions. BibRef

Estevez, L.W., Kehtarnavaz, N.,
Real-Time Object Specific Recognition via Raster Scan Video Processing,
RealTimeImg(5), No. 1, February 1999, pp. 49-62. BibRef 9902

Huang, Y., Trinder, J.C.,
Object Recognition Based on Boundary Description,
PhEngRS(65), No. 8, August 1999, pp. 915. Objects in the scene are reconstructed by digital photogrammetry, models by CAD. BibRef 9908

Batlle, J.[Joan], Casals, A.[Alícia], Freixenet, J.[Jordi], Martí, J.[Joan],
A review on strategies for recognizing natural objects in colour images of outdoor scenes,
IVC(18), No. 6-7, 1 May 2000, pp. 515-530.
Elsevier DOI 0003
BibRef

Martí, J.[Joan], Freixenet, J.[Jordi], Batlle, J.[Joan], Casals, A.[Alícia],
A new approach to outdoor scene description based on learning and top-down segmentation,
IVC(19), No. 14, December 2001, pp. 1041-1055.
Elsevier DOI 0111
BibRef

Torres-Mendez, L.A., Ruiz-Suarez, J.C., Sucar, L.E., Gomez, G.,
Translation, Rotation, and Scale-Invariant Object Recognition,
SMC-C(30), No. 1, February 2000, pp. 125-130.
IEEE Top Reference. 0004
BibRef

Douville, P.[Phil],
Real-Time Classification of Traffic Signs,
RealTimeImg(6), No. 3, June 2000, pp. 185-193. 0008
BibRef

Tagare, H.D.[Hemant D.], Toyama, K.[Kentaro], Wang, J.G.[Jonathan G.],
A Maximum-Likelihood Strategy for Directing Attention during Visual Search,
PAMI(23), No. 5, May 2001, pp. 490-500.
IEEE DOI 0105
From the model that objects are composed of parts, hypothesize object parts and image features that are likely from the target object. BibRef

Meribout, M.[Mahmoud], Nakanishi, M.[Mamoru], Ogura, T.[Takeshi],
A parallel algorithm for real-time object recognition,
PR(35), No. 9, September 2002, pp. 1917-1931.
Elsevier DOI 0206
Generalized Hough hardware.
See also Accurate and Real-time Image Processing on a New PC-compatible Board. BibRef

Kumar, S.[Sanjiv], Louis, A.C.[Alexander C.], Hebert, M.[Martial],
An observation-constrained generative approach for probabilistic classification of image regions,
IVC(21), No. 1, January 2003, pp. 87-97.
Elsevier DOI 0301
BibRef

Schneiderman, H.[Henry], Kanade, T.[Takeo],
Object Detection Using the Statistics of Parts,
IJCV(56), No. 3, February-March 2004, pp. 151-177.
DOI Link 0402
BibRef
Earlier:
Probabilistic Formulation for Object Recognition,
CVPR98(45-51).
IEEE DOI Award, Longuet-Higgins. (after 10 years) Trainable detector for faces and cars. Exhaustive scan with multiple detectors for different sizes. BibRef

Carmichael, O.T., Hebert, M.,
Shape-Based Recognition of Wiry Objects,
PAMI(26), No. 12, December 2004, pp. 1537-1552.
IEEE Abstract. 0411
BibRef
Earlier: CVPR03(II: 401-408).
IEEE DOI 0307
Recognition of complex-shaped objects in cluttered environments based on edge cues. Train classifier, apply to new image to filter edges. BibRef

Carmichael, O.T., Hebert, M.,
A Hybrid Object-Level/Pixel-Level Framework For Shape-based Recognition,
BMVC04(xx-yy).
HTML Version. 0508
BibRef

Carmichael, O.T.[Owen T.], Huber, D.F.[Daniel F.], Hebert, M.[Martial],
Large Data Sets and Confusing Scenes in 3-D Surface Matching and Recognition,
3DIM99(358-367).
IEEE DOI 9910
BibRef

Johnson, A.E.[Andrew Edie], Carmichael, O.T.[Owen T.], Huber, D.F.[Daniel F.], Hebert, M.[Martial],
Toward a General 3-D matching Engine: Multiple Models, Complex scenes, and Efficient Data Filtering,
DARPA98(1097-1108). BibRef 9800

Ferrari, V.[Vittorio], Tuytelaars, T.[Tinne], Van Gool, L.J.[Luc J.],
Simultaneous Object Recognition and Segmentation from Single or Multiple Model Views,
IJCV(67), No. 2, April 2006, pp. 159-188.
Springer DOI 0605
BibRef
And:
Simultaneous Object Recognition and Segmentation by Image Exploration,
CLOR06(145-169).
Springer DOI 0711
BibRef
Earlier: ECCV04(Vol I: 40-54).
Springer DOI 0405
Find initial matches, then expand the region of matches. For high occlusion problems. BibRef

Ferrari, V.[Vittorio], Tuytelaars, T.[Tinne], Van Gool, L.J.[Luc J.],
Object Detection by Contour Segment Networks,
ECCV06(III: 14-28).
Springer DOI 0608
Find in clutter, given hand-drawn model. BibRef

Ferrari, V.[Vittorio], Tuytelaars, T.[Tinne], Van Gool, L.J.[Luc J.],
Real-Time Affine Region Tracking and Coplanar Grouping,
CVPR01(II:226-233).
IEEE DOI 0110
Track locally planar regions and group. BibRef

Pece, A.E.C.[Arthur E.C.],
On the computational rationale for generative models,
CVIU(106), No. 1, April 2007, pp. 130-143.
Elsevier DOI 0704
Generative model; Graphical model; Generate-and-test; Sparse coding; Basis pursuit; Top-down processing BibRef

Demiris, Y.[Yiannis], Billard, A.[Aude],
Guest Editorial: Special Issue on Robot Learning by Observation, Demonstration, and Imitation,
SMC-B(37), No. 2, April 2007, pp. 254-255.
IEEE DOI 0704
BibRef

Shevchenko, M.[Mikhail], Windridge, D.[David], Kittler, J.V.[Josef V.],
A linear-complexity reparameterisation strategy for the hierarchical bootstrapping of capabilities within perception-action architectures,
IVC(27), No. 11, 2 October 2009, pp. 1702-1714.
Elsevier DOI 0909
BibRef
Earlier: A2, A1, A3:
An Entropy-Based Approach to the Hierarchical Acquisition of Perception-Action Capabilities,
CogVis08(79-92).
Springer DOI 0805
BibRef
Earlier: A3, A1, A2:
Visual Bootstrapping for Unsupervised Symbol Grounding,
ACIVS06(1037-1046).
Springer DOI 0609
Perception-action architectures; Cognitive vision; Subsumption architecture; Machine learning (unsupervised); Optimisation Symbol grounding: i.e. assigning a symbolic name to the image features. BibRef

Le Yaouanc, J.M.[Jean-Marie], Saux, É.[Éric], Claramunt, C.[Christophe],
A semantic and language-based representation of an environmental scene,
GeoInfo(14), No. 3, July 2010, pp. xx-yy.
Springer DOI 1003
BibRef

Chang, L.B.[Lo-Bin], Jin, Y.[Ya], Zhang, W.[Wei], Borenstein, E.[Eran], Geman, S.[Stuart],
Context, Computation, and Optimal ROC Performance in Hierarchical Models,
IJCV(93), No. 2, June 2011, pp. 117-140.
WWW Link. 1104
BibRef

Jin, Y.[Ya], Geman, S.[Stuart],
Context and Hierarchy in a Probabilistic Image Model,
CVPR06(II: 2145-2152).
IEEE DOI 0606
Use context, apply to license plate reading. BibRef

Geman, S.[Stuart],
Generative hierarchical models for image analysis,
SIG09(1-1).
IEEE DOI 0906
BibRef

Andreopoulos, A.[Alexander], Tsotsos, J.K.[John K.],
50 Years of object recognition: Directions forward,
CVIU(117), No. 8, August 2013, pp. 827-891.
Elsevier DOI 1306
Survey, Object Recognition. Active vision; Object recognition; Object representations; Object learning; Dynamic vision; Cognitive vision systems 50 year revie, limitations, drawbacks, future directions. BibRef

Watanabe, T.[Toshinori],
Toward a compression-based self-organizing recognizer: Preliminary implementation of PRDC-CSOR,
PRL(34), No. 14, 2013, pp. 1569-1576.
Elsevier DOI 1308
Design scheme (Pattern Representation scheme using Data Compression - Compression based Self ORganizing Recognizer) BibRef

Luo, C.[Cai], Yu, L.J.[Lei-Jian], Yang, E.[Erfu], Zhou, H.Y.[Hui-Yu], Ren, P.[Peng],
A benchmark image dataset for industrial tools,
PRL(125), 2019, pp. 341-348.
Elsevier DOI 1909
Dataset, Tools. Benchmark, Industrial tools, Image dataset BibRef

Li, X.L.[Xiang-Li], Guo, M.H.[Meng-Hao], Mu, T.J.[Tai-Jiang], Martin, R.R.[Ralph R.], Hu, S.M.[Shi-Min],
Long Range Pooling for 3D Large-Scale Scene Understanding,
CVPR23(10300-10311)
IEEE DOI 2309
BibRef

Ding, R.[Runyu], Yang, J.[Jihan], Xue, C.[Chuhui], Zhang, W.Q.[Wen-Qing], Bai, S.[Song], Qi, X.J.[Xiao-Juan],
PLA: Language-Driven Open-Vocabulary 3D Scene Understanding,
CVPR23(7010-7019)
IEEE DOI 2309
BibRef