Surface shape and curvature scales

Koenderink, Jan J.; Doorn, Andrea J. van

doi:10.1016/0262-8856(92)90076-f

Cited by 1,060 publications

(651 citation statements)

References 3 publications

Supporting

Mentioning

627

Contrasting

Unclassified

Order By: Relevance

“…We began with a class of smooth-flowing threedimensional shapes defined by Koenderink and van Doorn [5] and used in the shape recognition task of Kappers et al [2]. These shapes are constructed from two orthogonal parabolas and are a canonical set in the following sense: Any more complex solid shape can be constructed from a combination of these shapes.…”

Section: The Shape Recognition Task and Stimulimentioning

confidence: 99%

A shape recognition benchmark for evaluating usability of a haptic environment

Kirkpatrick

Douglas

2001

Haptic Human-Computer Interaction

View full text Add to dashboard Cite

This paper describes a benchmark task for evaluating the usability of haptic environments for a shape perception task. The task measures the ease with which observers can recognize members of a standard set of five shapes defined by Koenderink. Median time for 12 participants to recognize these shapes with the PHANToM was 23 seconds. This recognition time is within the range for shape recognition of physical objects using 1 finger but far slower than recognition using the whole hand. The results suggest haptic environments must provide multiple points of contact with an object for rapid performance of shape recognition.

show abstract

Section: The Shape Recognition Task and Stimulimentioning

confidence: 99%

A shape recognition benchmark for evaluating usability of a haptic environment

Kirkpatrick

Douglas

2001

Haptic Human-Computer Interaction

View full text Add to dashboard Cite

show abstract

“…-the shape index sh(x) [13] that describes the local shape irrespective of the scale and that is invariant to similarities -the curvedness cu(x) [13] that specifies the amount of curvature and that is invariant to rigid-body transformations -the (normalised) total geodesic distance tgd(x) [14] that is invariant to isometries in the shape space (including non-elastic deformations). Using labels.…”

Section: Using Descriptors C Can Be Computed Via the Comparison Betwmentioning

confidence: 99%

Setting Priors and Enforcing Constraints on Matches for Nonlinear Registration of Meshes

Combès

Prima

2009

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

View full text Add to dashboard Cite

Abstract. We show that a simple probabilistic modelling of the registration problem for surfaces allows to solve it by using standard clustering techniques. In this framework, point-to-point correspondences are hypothesized between the two free-form surfaces, and we show how to specify priors and to enforce global constraints on these matches with only minor changes to the optimisation algorithm. The purpose of these two modifications is to increase its capture range and to obtain more realistic geometrical transformations between the surfaces. We conclude with some validation experiments and results on synthetic and real data.

show abstract

“…This has encouraged research into the development of a number of shape inspired features for 3D, several of which are extensions to popular 2D features [23,12,5] and do not directly operate on point cloud data, while others [18,17] are not robust enough to sensor noise. In this work, we propose a novel feature called the Multi Scale Shape Index (MSSI) which is jointly motivated by scale space filtering theory [21,10] and the shape categorization work of Koenderink [6]. Shape Index (SI) maps points on surfaces to a linear scale [−1 : 1] and thus classifies them into categories such as Umbilics, Parabolics and Saddle points.…”

Section: Introductionmentioning

confidence: 99%

“…Illustration of shape index measure mapping shapes to real number. From [6]. characteristic scale, shape index and a measure of curvedness [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi Scale Shape Index for 3D Object Recognition

Bonde

Badrinarayanan

Cipolla

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We present Multi Scale Shape Index (MSSI), a novel feature for 3D object recognition. Inspired by the scale space filtering theory and Shape Index measure proposed by Koenderink & Van Doorn [6], this feature associates different forms of shape, such as umbilics, saddle regions, parabolic regions to a real valued index. This association is useful for representing an object based on its constituent shape forms. We derive closed form scale space equations which computes a characteristic scale at each 3D point in a point cloud without an explicit mesh structure. This characteristic scale is then used to estimate the Shape Index. We quantitatively evaluate the robustness and repeatability of the MSSI feature for varying object scales and changing point cloud density. We also quantify the performance of MSSI for object category recognition on a publicly available dataset.

show abstract

Surface shape and curvature scales

Cited by 1,060 publications

References 3 publications

A shape recognition benchmark for evaluating usability of a haptic environment

A shape recognition benchmark for evaluating usability of a haptic environment

Setting Priors and Enforcing Constraints on Matches for Nonlinear Registration of Meshes

Multi Scale Shape Index for 3D Object Recognition

Contact Info

Product

Resources

About