Detection of patterns in images from piecewise linear contours

Authors:
G. Rives;M. Dhome;J. T. Lapresté;M. Richetin
Affiliations:
LERM, ERA 90 of the CNRS, University of Clermont II, B.P. 45, 63170 Aubière, France;LERM, ERA 90 of the CNRS, University of Clermont II, B.P. 45, 63170 Aubière, France;LERM, ERA 90 of the CNRS, University of Clermont II, B.P. 45, 63170 Aubière, France;LERM, ERA 90 of the CNRS, University of Clermont II, B.P. 45, 63170 Aubière, France
Venue:
Pattern Recognition Letters
Year:
1985

Citing 5
Cited 0

Algorithms for Graphics and Imag

Algorithms for Graphics and Imag
Two New Edge Detectors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Improving Consistency and Reducing Ambiguity in Stochastic Labeling: An Optimization Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Inexact graph matching for structural pattern recognition

Pattern Recognition Letters
Sequential piecewise-linear segmentation of binary contours

Pattern Recognition Letters

Quantified Score

Hi-index	0.10

Visualization

Abstract

Structural pattern recognition for image understanding is based on the detection of elementary patterns which compose the structural description of the objects to be recognized and located in scenes. Detection of these elementary patterns in piecewise linear contours is the first step in the recognition task for which a new algorithm is presented in this paper. The representation of a pattern model is the set of the linear segments obtained during the learning phase from the segmentation of its contour. The detection of the occurrences of a pattern in a scene is made according to a hypothesis-accumulation procedure followed by a peak picking search in a two dimensional array. Experimental results of pattern detection are also given.