scispace - formally typeset
Journal ArticleDOI

Viewpoint independent representation and recognition of polygonal faces in 3-D

H. Bunke, +1 more
- Vol. 9, Iss: 4, pp 457-463
TLDR
A new set of local shape descriptors for polygons are proposed that are invariant under affine transformation and complete in the sense that they allow the reconstruction of any polygon in 3-D space from three consecutive vertices.
Abstract
The recognition of polygons in 3-D space is an important task in robot vision. Two particular problems are addressed in the paper. First a new set of local shape descriptors for polygons are proposed that are invariant under affine transformation. Furthermore, they are complete in the sense that they allow the reconstruction of any polygon in 3-D space from three consecutive vertices. The second problem discussed in this paper is the recognition of 2-D polygonal objects under affine transformation and the presence of partial occlusion. A recognition procedure that is based on the matching of edge length ratios is introduced using a simplified version of the standard dynamic programming procedure commonly employed for string matching. The algorithm is conceptually very simple, easy to implement and has a low computational complexity. It is in a set of experiments that the method is reliable and robust. >

read more

Citations
More filters
Book ChapterDOI

Jigsaw Puzzle Solving Using Approximate String Matching and Best-First Search

TL;DR: A new method for jigsaw puzzle solving that takes real images of puzzle pieces as input data and resolves ambiguities that may result from local shape matching using a best-first tree search procedure with backtracking.
Journal ArticleDOI

Finding rotational symmetries by cyclic string matching

TL;DR: A simple and fast method to detect perfect and distorted rotational symmetries of 2D objects is described and some experimental results are presented to show the reliability of the proposed algorithm.
Journal ArticleDOI

Acquisition of 2D Shape Models from Scenes with Overlapping Objects using String Matching

TL;DR: A system that is able to acquire models of 2D shapes from cluttered scenes by identifying matching partial shapes across different images and combines them into complete 2D shape models, thus giving a complete interpretation of the input scenes.
Journal ArticleDOI

VLSI architectures for polygon recognition

TL;DR: A class of VLSI architectures is proposed for the computationally intensive task of polygon recognition in 3-D space that makes use of a set of local shape descriptors for polygons that are invariant under affine transformations.
Journal ArticleDOI

Feature Mapping and View Planning with Localized Surface Parameters

TL;DR: A three-phase filtering method that eliminates candidate models when their differences with the object show up, and has a low computational complexity upper bounded byO(m2n2) and lower bounded by O(mn),ssswhere m and n are the numbers of model and object features.
References
More filters
Journal ArticleDOI

Visual pattern recognition by moment invariants

TL;DR: It is shown that recognition of geometrical patterns and alphabetical characters independently of position, size and orientation can be accomplished and it is indicated that generalization is possible to include invariance with parallel projection.
Journal ArticleDOI

Generalizing the hough transform to detect arbitrary shapes

TL;DR: It is shown how the boundaries of an arbitrary non-analytic shape can be used to construct a mapping between image space and Hough transform space, which makes the generalized Houghtransform a kind of universal transform which can beused to find arbitrarily complex shapes.
Journal ArticleDOI

Fourier Descriptors for Plane Closed Curves

TL;DR: It is established that the Fourier series expansion is optimal and unique with respect to obtaining coefficients insensitive to starting point and the amplitudes are pure form invariants as well as are certain simple functions of phase angles.
Journal ArticleDOI

HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects

TL;DR: The method has been integrated within a vision system coupled to an indutrial robot arm, to provide automatic picking and repositioning of partially overlapping industrial parts to provide strong robustness to partial occlusions.