2-D Shape Recognition using Recursive Landmark Determination and Fuzzy ART Network Learning

Authors:
Apiwat Saengdeejing;Zhihua Qu;Nopphamas Chaeroenlap;Yufang Jin
Affiliations:
School of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA;School of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA. e-mail: qu@pegasus.cc.ucf.edu;School of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA;School of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA
Venue:
Neural Processing Letters
Year:
2003

Citing 10
Cited 0

A new chain-coding algorithm for binary images using run-length codes

Computer Vision, Graphics, and Image Processing
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Geometric invariance in computer vision

Geometric invariance in computer vision
A simple algorithm for detection of significant vertices for polygonal approximation of chain-coded curves

Pattern Recognition Letters
Variational methods in image segmentation

Variational methods in image segmentation
Shape characterization with the wavelet transform

Signal Processing
Recognizing Planar Objects Using Invariant Image Features

Recognizing Planar Objects Using Invariant Image Features
Robust Tracking Control of Robot Manipulators

Robust Tracking Control of Robot Manipulators
Locating Perceptually Salient Points on Planar Curves

IEEE Transactions on Pattern Analysis and Machine Intelligence
Geometric Invariants for Rational Polynomial Cameras

AIPR '00 Proceedings of the 29th Applied Imagery Pattern Recognition Workshop

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this Letter, 2-D shape recognition is done using a combination of recursive search of landmarks, landmark-based invariant features, and a fuzzy ART neural-network classifier. To make this novel combination work well, an upper limit is imposed on the number of total landmarks allowed, and this maximum size is then translated into fixed dimensions of invariant features and into the neural processing of the features. It is shown that the recursive landmark search approximates very well any smooth 2-D shape contour, that the shape features used are independent of perspective transformation, and that, when combinedwitha fuzzy ART classifier, unknown features can be efficiently learned on-line to identify multiple distinct objects. An illustrative example is used to demonstrate effectiveness of the proposed algorithm.