Multiscale object recognition under affine transformation

Wen Huei Lin, Chin-Hsing Chen, Jiann Shu Lee, Yung-Nien Sun

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A method to recognize planar objects undergoing affine transformation is proposed in this paper. The method is based upon wavelet multiscale features and Hopfield neural networks. The feature vector consists of the multiscale wavelet transformed extremal evolution. The evolution contains the information of the contour primitives in a multiscale manner, which can be used to discriminate dominant points, hence a good initial state of the Hopfield network can be obtained. Such good initiation enables the network to converge more efficiently. A wavelet normalization scheme was applied to make our method scale invariant and to reduce the distortion resulting from normalizing the object contours. The Hopfield neural network was employed as a global processing mechanism for feature matching and made our method suitable to recognize planar objects whose shape distortion arising from an affine transformation. The Hopfield network was improved to guarantee unique and more stable matching results. A new matching evaluation scheme, which is computationally efficient, was proposed to evaluate the goodness of matching. Two sets of images, noiseless and noisy industrial tools, undergoing affine transformation were used to test the performance of the proposed method. Experimental results showed that our method is not only effective and robust under affine transformation but also can limit the effect of noises.

Original languageEnglish
Pages (from-to)1474-1482
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE82-D
Issue number11
Publication statusPublished - 1999 Jan 1

Fingerprint

Hopfield neural networks
Object recognition
Processing

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

@article{6053d9effdb546e3bc4f4d9a16dfac6f,
title = "Multiscale object recognition under affine transformation",
abstract = "A method to recognize planar objects undergoing affine transformation is proposed in this paper. The method is based upon wavelet multiscale features and Hopfield neural networks. The feature vector consists of the multiscale wavelet transformed extremal evolution. The evolution contains the information of the contour primitives in a multiscale manner, which can be used to discriminate dominant points, hence a good initial state of the Hopfield network can be obtained. Such good initiation enables the network to converge more efficiently. A wavelet normalization scheme was applied to make our method scale invariant and to reduce the distortion resulting from normalizing the object contours. The Hopfield neural network was employed as a global processing mechanism for feature matching and made our method suitable to recognize planar objects whose shape distortion arising from an affine transformation. The Hopfield network was improved to guarantee unique and more stable matching results. A new matching evaluation scheme, which is computationally efficient, was proposed to evaluate the goodness of matching. Two sets of images, noiseless and noisy industrial tools, undergoing affine transformation were used to test the performance of the proposed method. Experimental results showed that our method is not only effective and robust under affine transformation but also can limit the effect of noises.",
author = "Lin, {Wen Huei} and Chin-Hsing Chen and Lee, {Jiann Shu} and Yung-Nien Sun",
year = "1999",
month = "1",
day = "1",
language = "English",
volume = "E82-D",
pages = "1474--1482",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "11",

}

Multiscale object recognition under affine transformation. / Lin, Wen Huei; Chen, Chin-Hsing; Lee, Jiann Shu; Sun, Yung-Nien.

In: IEICE Transactions on Information and Systems, Vol. E82-D, No. 11, 01.01.1999, p. 1474-1482.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multiscale object recognition under affine transformation

AU - Lin, Wen Huei

AU - Chen, Chin-Hsing

AU - Lee, Jiann Shu

AU - Sun, Yung-Nien

PY - 1999/1/1

Y1 - 1999/1/1

N2 - A method to recognize planar objects undergoing affine transformation is proposed in this paper. The method is based upon wavelet multiscale features and Hopfield neural networks. The feature vector consists of the multiscale wavelet transformed extremal evolution. The evolution contains the information of the contour primitives in a multiscale manner, which can be used to discriminate dominant points, hence a good initial state of the Hopfield network can be obtained. Such good initiation enables the network to converge more efficiently. A wavelet normalization scheme was applied to make our method scale invariant and to reduce the distortion resulting from normalizing the object contours. The Hopfield neural network was employed as a global processing mechanism for feature matching and made our method suitable to recognize planar objects whose shape distortion arising from an affine transformation. The Hopfield network was improved to guarantee unique and more stable matching results. A new matching evaluation scheme, which is computationally efficient, was proposed to evaluate the goodness of matching. Two sets of images, noiseless and noisy industrial tools, undergoing affine transformation were used to test the performance of the proposed method. Experimental results showed that our method is not only effective and robust under affine transformation but also can limit the effect of noises.

AB - A method to recognize planar objects undergoing affine transformation is proposed in this paper. The method is based upon wavelet multiscale features and Hopfield neural networks. The feature vector consists of the multiscale wavelet transformed extremal evolution. The evolution contains the information of the contour primitives in a multiscale manner, which can be used to discriminate dominant points, hence a good initial state of the Hopfield network can be obtained. Such good initiation enables the network to converge more efficiently. A wavelet normalization scheme was applied to make our method scale invariant and to reduce the distortion resulting from normalizing the object contours. The Hopfield neural network was employed as a global processing mechanism for feature matching and made our method suitable to recognize planar objects whose shape distortion arising from an affine transformation. The Hopfield network was improved to guarantee unique and more stable matching results. A new matching evaluation scheme, which is computationally efficient, was proposed to evaluate the goodness of matching. Two sets of images, noiseless and noisy industrial tools, undergoing affine transformation were used to test the performance of the proposed method. Experimental results showed that our method is not only effective and robust under affine transformation but also can limit the effect of noises.

UR - http://www.scopus.com/inward/record.url?scp=4544317199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544317199&partnerID=8YFLogxK

M3 - Article

VL - E82-D

SP - 1474

EP - 1482

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 11

ER -