12.3.2.3 Hierarchical/Scale-Space Contour Matching and Descriptions

Chapter Contents (Back)
Contour Matching. Scale-Space Matching. Matching, Contours. Matching, Scale-Space. Matching, Hierarchical. Hierarchical Matching.

Mokhtarian, F., and Mackworth, A.K.,
A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves,
PAMI(14), No. 8, August 1992, pp. 789-805.
IEEE DOI Curve representations. Shape descriptor expected to be an MPEG-7 standard. BibRef 9208

Mokhtarian, F.[Farzin], and Mackworth, A.K.,
Scale Based Description and Recognition of Planar Curves and Two-Dimensional Shapes,
PAMI(8), No. 1, January, 1986, pp. 34-43. BibRef 8601
And: Authors reply to comments: PAMI(8), No. 5, September 1986, pp. 675. BibRef
Earlier: A2, A1:
Scale Based Description of Planar Curves,
CSCSI84(114-119). BibRef
And:
The Renormalized Curvature Scale Space and the Evolution Properties of Planar Curves,
CVPR88(318-326).
IEEE DOI Scale Space. Represent different scales and generalize to a single representation. Used for matching parts of boundaries to the whole boundary. BibRef

Mokhtarian, F.[Farzin],
Multi-Scale Contour Segmentation,
ScaleSpace97(xx). 9702
BibRef

Mokhtarian, F.[Farzin], Suomela, R.[Riku],
Robust Image Corner Detection Through Curvature Scale Space,
PAMI(20), No. 12, December 1998, pp. 1376-1381.
IEEE DOI BibRef 9812
Earlier:
Curvature Scale Space for Robust Image Corner Detection,
ICPR98(Vol II: 1819-1821).
IEEE DOI 9808
Start with Canny, corners are points where image edges have maximum curvature. Find in high scale, track through lower scales to get positions. Proposes an improvement to Canny for 45 and 135 deg. edges. BibRef

Mokhtarian, F.[Farzin], Abbasi, S.[Sadegh],
Affine Curvature Scale Space with Affine Length Parametrisation,
PAA(4), No. 1, 2001, pp. 1-8.
Springer DOI 0105
BibRef
Earlier: A2, A1:
Curvature Scale Space with Affine Length Parametrisation,
ScaleSpace99(435-440).
See also Curvature Scale Space Image in Shape Similarity Retrieval. BibRef

Mokhtarian, F.,
Convergence Properties of Curvature and Torsion Scale Space Representations,
BMVC95(357-366).
PDF File. 9509
BibRef

Mokhtarian, F., Naito, S.,
Scale Properties of Curvature and Torsion Zero-Crossings,
ACCV93(303-308). BibRef 9300

Mokhtarian, F.,
Evolution Properties of Space Curve,
ICCV88(100-105).
IEEE DOI BibRef 8800

Mokhtarian, F.,
Fingerprint Theorems for Curvature and Torsion Zero-Crossings,
CVPR89(269-275).
IEEE DOI BibRef 8900

Mokhtarian, F.,
Multi-Scale Description of Space Curves and Three-Dimensional Objects,
CVPR88(298-303).
IEEE DOI BibRef 8800

Mokhtarian, F.[Farzin], Abbasi, S.[Sadegh],
Matching Shapes With Self-Intersections: Application to Leaf Classification,
IP(13), No. 5, May 2004, pp. 653-661.
IEEE DOI 0404
BibRef

Mokhtarian, F.,
Silhouette-Based Isolated Object Recognition through Curvature Scale-Space,
PAMI(17), No. 5, May 1995, pp. 539-544.
IEEE DOI BibRef 9505
Earlier: add: Murase, H.,
Silhouette-Based Object Recognition through Curvature Scale Space,
ICCV93(269-274).
IEEE DOI Multi-scale description using zero-crossings and extrema. BibRef

Mokhtarian, F.,
Silhouette-Based Occluded Object Recognition Through Curvature Scale-Space,
MVA(10), No. 3, 1997, pp. 87-97.
Springer DOI 9709
BibRef
Earlier: (no "-") ECCV96(I:566-578).
Springer DOI BibRef

Mokhtarian, F.,
A Theory of Multiscale, Torsion Based Shape Representation for Space Curves,
CVIU(68), No. 1, October 1997, pp. 1-17.
DOI Link 9710
BibRef

Mokhtarian, F.,
Robust Criteria for Automatic Multi-Scale Curve Segmentation,
SCIA99(Pattern Recognition). BibRef 9900

Mokhtarian, F.[Farzin],
Torsion Scale Space Images: Robust Representations for Space Curves,
SCIA97(xx-yy)
HTML Version. 9705
BibRef

Mokhtarian, F.,
Multi-Scale, Torsion-Based Shape Representations for Space Curves,
CVPR93(660-661).
IEEE DOI BibRef 9300

Goshtasby, A.A.,
Comments on 'Scale Based Description and Recognition of Planar Curves and Two-Dimensional Shapes',
PAMI(8), No. 5, September 1986, pp. 674-675.
See also Scale Based Description and Recognition of Planar Curves and Two-Dimensional Shapes. BibRef 8609

Neveu, C.F.[Charles F.], Dyer, C.R.[Charles R.], Chin, R.T.[Roland T.],
Two-Dimensional Object Recognition Using Multiresolution Models,
CVGIP(34), No. 1, April 1986, pp. 52-65.
Elsevier DOI Hough. Recognize Two-Dimensional Objects. The object is modeled as a graph of the boundary elements with different models for each resolution. Matching is by the Hough technique (accumulation array portion of the technique). It seems similar to an earlier BibRef 8604 CVPR85(426-428). paper with Luo as the first author. BibRef

Crowley, J.L., and Sanderson, A.C.,
Multiple Resolution Representation and Probabilistic Matching of 2-D Gray-Scale Shape,
PAMI(9), No. 1, January 1987, pp. 113-121. BibRef 8701
And: CVWS84(95-105). Multiple Resolutions. The use of the DOLP transform, derived from Crowley's thesis. Several levels are computed and the matching proceeds from the lowest resolution up. BibRef

Sanderson, A.C.[Arthur C.], and Foster, N.[Nigel],
Attributed Image Matching Using a Minimum Representation Size Criterion,
CRA89(360-365). BibRef 8900

Tortora, G.[Genoveffa], Costagliola, G.[Gennaro], Arndt, T.[Timothy], Chang, S.K.[Shi-Kuo],
Pyramidal Algorithms for Iconic Indexing,
CVGIP(52), No. 1, October 1990, pp. 26-56.
Elsevier DOI Pyramid Structures, Matching. Matching of the image using a pyramid structure to simplify the search. BibRef 9010

Choudhary, A.[Alok], Ranka, S.[Sanjay],
Mesh and pyramid algorithms for iconic indexing,
PR(25), No. 9, September 1992, pp. 1061-1067.
Elsevier DOI 0401
BibRef
And: Authors Reply: PR(31), No. 6, June 1998, pp. 821-822.
Elsevier DOI 9806
BibRef

Arndt, T.[Timothy], Costagliola, G.[Gennaro], Chang, S.K.[Shi-Kuo],
Comments on Mesh and Pyramid Algorithms for Iconic Indexing,
PR(31), No. 6, June 1998, pp. 819-820.
Elsevier DOI 9806
BibRef

Tu, Z.W.[Zhuo-Wen], Zheng, S.F.[Song-Feng], Yuille, A.L.[Alan L.],
Shape matching and registration by data-driven EM,
CVIU(109), No. 3, March 2008, pp. 290-304.
Elsevier DOI 0802
Shape matching; Registration; Soft assign; EM; Shape context BibRef

Tu, Z.W.[Zhuo-Wen], Yuille, A.L.[Alan L.],
Shape Matching and Recognition: Using Generative Models and Informative Features,
ECCV04(Vol III: 195-209).
Springer DOI 0405
Generative model for how one shape can be generated by the other. Allow affine and non-rigid transformations. DDMCMC (
See also Image Parsing: Unifying Segmentation, Detection, and Recognition. ) Shape Contexts (
See also Shape Matching and Object Recognition Using Shape Contexts. ) Softassign (
See also new point matching algorithm for non-rigid registration, A. ) BibRef

Drew, M.S.[Mark S.], Lee, T.K.[Tim K.], Rova, A.[Andrew],
Shape retrieval with eigen-CSS search,
IVC(27), No. 6, 4 May 2009, pp. 748-755.
Elsevier DOI 0904
BibRef
Earlier: A2, A1, Only:
3D Object Recognition by Eigen-Scale-Space of Contours,
SSVM07(883-894).
Springer DOI 0705
Shape; 2D contour; Scale-space; Matching; Retrieval; Curvature; CSS; Eigen-analysis BibRef

Li, Z.K.[Ze-Kun], Seah, H.S.[Hock Soon], Guo, B.L.[Bao-Long], Yang, M.[Muli],
MLGPnet: Multi-granularity neural network for 3D shape recognition using pyramid data,
CVIU(239), 2024, pp. 103904.
Elsevier DOI 2402
3D shape recognition, Multi-granularity, Point-granularity, Line-granularity, Pyramid-granularity, Pyramid data BibRef


Alvino, C.V.[Christopher V.], Yezzi, Jr., A.J.[Anthony J.],
A Scale Space for Contour Registration Using Minimal Surfaces,
ScaleSpace03(164-179).
Springer DOI 0310
BibRef

Zhang, X., Burkhardt, H.,
Hierarchical Primitives Based Contour Matching,
DAGM02(298 ff.).
Springer DOI 0303
BibRef

Luo, Y., Dyer, C.R., and Chin, R.T.,
2-D Object Recognition Using Hierarchical Boundary Segments,
CVPR85(426-428). (Univ. of Wisconsin) Pyramid Structure. Recognize Two-Dimensional Objects. Model driven, pyramid based, coarse to fine matching. BibRef 8500

Wu, Y., and Maitre, H.,
Registration of a SPOT Image and a SAR Image Using Multiresolution Representation of a Coastline,
ICPR90(I: 913-917).
IEEE DOI BibRef 9000

Venkateswar, V.,
Hierarchical Representation, Matching and Search for Some Computer Vision Problems,
Ph.D.Thesis (EE), USC, June 1991. Uses a Truth Maintenance System to explore the search space in matching. For applications:
See also Hierarchical Stereo and Motion Correspondence Using Feature Groupings. BibRef 9106

Chapter on Registration, Matching and Recognition Using Points, Lines, Regions, Areas, Surfaces continues in
Surface Matching, Deformable Surface Matching .


Last update:Mar 16, 2024 at 20:36:19