Detecting Symmetry and Symmetric Constellations of Features

Loy, Gareth; Eklundh, Jan‐Olof

doi:10.1007/11744047_39

Cited by 270 publications

(431 citation statements)

References 36 publications

Supporting

Mentioning

428

Contrasting

Order By: Relevance

“…For comparison, in Fig. 5 we show an example of symmetry detection using the voting method of Loy and Ecklundh [13]. One can observe that strong articulation tamper with this algorithm, bringing in some cases to a failure to detect all the symmetries or an incorrect result.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Shape Palindromes: Analysis of Intrinsic Symmetries in 2D Articulated Shapes

Hooda

Bronstein

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Analysis of intrinsic symmetries of non-rigid and articulated shapes is an important problem in pattern recognition with numerous applications ranging from medicine to computational aesthetics. Considering articulated planar shapes as closed curves, we show how to represent their extrinsic and intrinsic symmetries as self-similarities of local descriptor sequences, which in turn have simple interpretation in the frequency domain. The problem of symmetry detection and analysis thus boils down to analysis of descriptor sequence patterns. For that purpose, we show two efficient computational methods: one based on Fourier analysis, and another on dynamic programming. Metaphorically, the later can be compared to finding palindromes in text sequences.

show abstract

Section: Resultsmentioning

confidence: 99%

“…A wide spectrum of methods employed for this purpose includes approaches based on dual spaces [7], genetic algorithms [9], moments [5], pair matching [13,6], and local shape descriptors [33]. For an up-to-date overview, the reader is referred to the survey article of Liu et al [12].…”

Section: Introductionmentioning

confidence: 99%

Shape Palindromes: Analysis of Intrinsic Symmetries in 2D Articulated Shapes

Hooda

Bronstein

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…al. [9] explored edge features to measure symmetry similarity and Loy and Eklundh [10] matched feature points and then extracted reflection (and also rotation) symmetry patterns via clustering; Mitra et.al. [11] developed partial or approximate Euclidean reflection symmetry detection in subsampled 3D data.…”

Section: Introductionmentioning

confidence: 99%

“…We adopt the bottom-up framework of [18,10] that first detects and matches symmetric feature points to form symmetry particles (including both inliers and outliers), while build up symmetric regions in the higher level. The major novel advantage of detecting deformed symmetry patterns from bottom-up is that feature points are free of global deformation, meanwhile local deformation can be handled by more sophisticated feature points such as SIFT [19], which is robust against scale change and rotation with good repeatability and high efficiency.…”

Section: Introductionmentioning

confidence: 99%

Curved Reflection Symmetry Detection with Self-validation

Liu

2011

Computer Vision – ACCV 2010

View full text Add to dashboard Cite

Abstract. We propose a novel, self-validating approach for detecting curved reflection symmetry patterns from real, unsegmented images. Our method benefits from the observation that any curved symmetry pattern can be approximated by a sequence of piecewise rigid reflection patterns. Pairs of symmetric feature points are first detected (including both inliers and outliers) and treated as 'particles'. Multiple-hypothesis sampling and pruning are used to sample a smooth path going through inlier particles to recover the curved reflection axis. Our approach generates an explicit supporting region of the curved reflection symmetry, which is further used for intermediate self-validation, making the detection process more robust than prior state-of-the-art algorithms. Experimental results on 200+ images demonstrate the effectiveness and superiority of the proposed approach.

show abstract

“…Symmetry and structure detection in images and shapes is a wellresearched topic in the computer vision and graphics communities (see e.g. [10][11][12][13][14][15][16][17][18][19]) with applications including segmentation [20], scan completion [9], pose invariant representation [21], image de-fencing [22], shape retrieval [12], and editing images with repeated elements [23].…”

Section: Introductionmentioning

confidence: 99%

Intrinsic Regularity Detection in 3D Geometry

Mitra

Bronstein

2010

Computer Vision – ECCV 2010

View full text Add to dashboard Cite

Abstract. Automatic detection of symmetries, regularity, and repetitive structures in 3D geometry is a fundamental problem in shape analysis and pattern recognition with applications in computer vision and graphics. Especially challenging is to detect intrinsic regularity, where the repetitions are on an intrinsic grid, without any apparent Euclidean pattern to describe the shape, but rising out of (near) isometric deformation of the underlying surface. In this paper, we employ multidimensional scaling to reduce the problem of intrinsic structure detection to a simpler problem of 2D grid detection. Potential 2D grids are then identified using an autocorrelation analysis, refined using local fitting, validated, and finally projected back to the spatial domain. We test the detection algorithm on a variety of scanned plaster models in presence of imperfections like missing data, noise and outliers. We also present a range of applications including scan completion, shape editing, super-resolution, and structural correspondence.

show abstract

Detecting Symmetry and Symmetric Constellations of Features

Cited by 270 publications

References 36 publications

Shape Palindromes: Analysis of Intrinsic Symmetries in 2D Articulated Shapes

Shape Palindromes: Analysis of Intrinsic Symmetries in 2D Articulated Shapes

Curved Reflection Symmetry Detection with Self-validation

Intrinsic Regularity Detection in 3D Geometry

Contact Info

Product

Resources

About