# Combining Appearance and Gradient Information for Image Symmetry Detection

01 Jan 2021-IEEE Transactions on Image Processing (Institute of Electrical and Electronics Engineers (IEEE))-Vol. 30, pp 5708-5723

TL;DR: In this article, a stable metric is proposed to extract subsets of consistently oriented candidate segments, whenever the underlying 2D signal appearance exhibits definite near symmetric correspondences, and the ranking of such segments on the basis of the surrounding gradient orientation specularity, in order to reflect real symmetric object boundaries.

Abstract: This work addresses the challenging problem of reflection symmetry detection in unconstrained environments. Starting from the understanding on how the visual cortex manages planar symmetry detection, it is proposed to treat the problem in two stages: i) the design of a stable metric that extracts subsets of consistently oriented candidate segments, whenever the underlying 2D signal appearance exhibits definite near symmetric correspondences; ii) the ranking of such segments on the basis of the surrounding gradient orientation specularity, in order to reflect real symmetric object boundaries. Since these operations are related to the way the human brain performs planar symmetry detection, a better correspondence can be established between the outcomes of the proposed algorithm and a human-constructed ground truth. When compared to the testing sets used in recent symmetry detection competitions, a remarkable performance gain can be observed. In additional, further validation has been achieved by conducting perceptual validation experiments with users on a newly built dataset.

##### Citations

More filters

••

TL;DR: Wang et al. as mentioned in this paper presented two shape signature-based reflection symmetry detection methods with their theoretical underpinning and empirical evaluation, which can effectively deal with compound shapes which are challenging for traditional contour-based methods.

8 citations

••

31 Mar 2022

TL;DR: This work introduces a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation.

Abstract: The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation. The proposed network is built end-to-end with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.

6 citations

••

01 Jun 2022TL;DR: Zhang et al. as mentioned in this paper proposed a group-equivariant convolutional network for symmetry detection, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation.

Abstract: The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation. The proposed network is built end-to-end with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.

1 citations

•

TL;DR: In this paper, the authors propose a statistical estimator for the plane of reflection symmetry that is robust to outliers and missing parts, which is based on the spectral properties of the geodesic distance matrix constructed from the neighbors of a point.

Abstract: Detecting the reflection symmetry plane of an object represented by a 3D point cloud is a fundamental problem in 3D computer vision and geometry processing due to its various applications such as compression, object detection, robotic grasping, 3D surface reconstruction, etc. There exist several efficient approaches for solving this problem for clean 3D point clouds. However, this problem becomes difficult to solve in the presence of outliers and missing parts due to occlusions while scanning the objects through 3D scanners. The existing methods try to overcome these challenges mostly by voting-based techniques but fail in challenging settings. In this work, we propose a statistical estimator for the plane of reflection symmetry that is robust to outliers and missing parts. We pose the problem of finding the optimal estimator as an optimization problem on a 2-sphere that quickly converges to the global solution. We further propose a 3D point descriptor that is invariant to 3D reflection symmetry using the spectral properties of the geodesic distance matrix constructed from the neighbors of a point. This helps us in decoupling the chicken-and-egg problem of finding optimal symmetry plane and correspondences between the reflective symmetric points. We show that the proposed approach achieves the state-of-the-art performance on the benchmarks dataset.

••

01 Oct 2022

TL;DR: This work points out an efficient detector of reflectionally symmetric shapes by addressing a class of projection-based signatures that are structured by a generalized $\mathcal{R}_{fm}$-transform model in accordance with reflectional symmetry detection.

Abstract: Analyzing reflectionally symmetric features inside an image is one of the important processes for recognizing the peculiar appearance of natural and man-made objects, biological patterns, etc. In this work, we will point out an efficient detector of reflectionally symmetric shapes by addressing a class of projection-based signatures that are structured by a generalized $\mathcal{R}_{fm}$-transform model. To this end, we will firstly prove the $\mathcal{R}_{fm^{-}}$transform in accordance with reflectional symmetry detection. Then different corresponding $\mathcal{R}_{fm}$-signatures of binary shapes are evaluated in order to determine which the corresponding exponentiation of the $\mathcal{R}_{fm}$-transform is the best for the detection. Experimental results of detecting on single/compound contour-based shapes have validated that the exponentiation of 10 is the most discriminatory, with over 2.7% better performance on the multiple-axis shapes in comparison with the conventional one. Additionally, the proposed detector also outperforms most of other existing methods. This finding should be recommended for applications in practice.

##### References

More filters

••

06 Sep 2014

TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.

Abstract: We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

30,462 citations

••

TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.

Abstract: This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.

28,073 citations

••

TL;DR: The theory of edge detection explains several basic psychophysical findings, and the operation of forming oriented zero-crossing segments from the output of centre-surround ∇2G filters acting on the image forms the basis for a physiological model of simple cells.

Abstract: A theory of edge detection is presented. The analysis proceeds in two parts. (1) Intensity changes, which occur in a natural image over a wide range of scales, are detected separately at different scales. An appropriate filter for this purpose at a given scale is found to be the second derivative of a Gaussian, and it is shown that, provided some simple conditions are satisfied, these primary filters need not be orientation-dependent. Thus, intensity changes at a given scale are best detected by finding the zero values of delta 2G(x,y)*I(x,y) for image I, where G(x,y) is a two-dimensional Gaussian distribution and delta 2 is the Laplacian. The intensity changes thus discovered in each of the channels are then represented by oriented primitives called zero-crossing segments, and evidence is given that this representation is complete. (2) Intensity changes in images arise from surface discontinuities or from reflectance or illumination boundaries, and these all have the property that they are spatially. Because of this, the zero-crossing segments from the different channels are not independent, and rules are deduced for combining them into a description of the image. This description is called the raw primal sketch. The theory explains several basic psychophysical findings, and the operation of forming oriented zero-crossing segments from the output of centre-surround delta 2G filters acting on the image forms the basis for a physiological model of simple cells (see Marr & Ullman 1979).

6,893 citations

••

TL;DR: It is proposed that understanding the algorithm that produces core object recognition will require using neuronal and psychophysical data to sift through many computational models, each based on building blocks of small, canonical subnetworks with a common functional goal.

1,524 citations

••

TL;DR: Overall, these results indicate that the lateral occipital complex plays an important role in human object recognition.

1,272 citations