Shift-Invariant Fuzzy-Morphology Neural Network for Automatic Target Recognition

Yonggwan WON

Shift-Invariant Fuzzy-Morphology Neural Network for Automatic Target Recognition

Yonggwan WON

Full Text Views

0

Share
Cite this

Summary :

This paper describes a theoretical foundation of fuzzy morphological operations and architectural extension of the shared-weight neural network (SWNN). The network performs shift-invariant filtering using fuzzy-morphological operations for feature extraction. The nodes in the feature extraction stage employ the generalized-mean operator to implement fuzzy-morphological operations. The parameters of the SWNN, weights, morphological structuring element and fuzziness, are optimized by the error back-propagation (EBP) training method. The parameter values of the trained SWNN are then implanted into the extended SWNN (ESWNN) which is a simple convolution neural network. The ESWNN architecture dramatically reduces the amount of computation by avoiding segmentation process. The neural network is applied to automatic recognition of a vehicle in visible images. The network is tested with several sequences of images that include targets ranging from no occlusion to almost full occlusion. The results demonstrate an ability to detect occluded targets, while trained with non-occluded ones. In comparison, the proposed network was superior to the Minimum-Average Correlation filter systems and produced better results than the ordinary SWNN.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E81-A No.6 pp.1119-1127

Publication Date: 1998/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section of Papers Selected from ITC-CSCC'97)

Category: Neural Networks

Cite this

Copy

Yonggwan WON, "Shift-Invariant Fuzzy-Morphology Neural Network for Automatic Target Recognition" in IEICE TRANSACTIONS on Fundamentals, vol. E81-A, no. 6, pp. 1119-1127, June 1998, doi: .
Abstract: This paper describes a theoretical foundation of fuzzy morphological operations and architectural extension of the shared-weight neural network (SWNN). The network performs shift-invariant filtering using fuzzy-morphological operations for feature extraction. The nodes in the feature extraction stage employ the generalized-mean operator to implement fuzzy-morphological operations. The parameters of the SWNN, weights, morphological structuring element and fuzziness, are optimized by the error back-propagation (EBP) training method. The parameter values of the trained SWNN are then implanted into the extended SWNN (ESWNN) which is a simple convolution neural network. The ESWNN architecture dramatically reduces the amount of computation by avoiding segmentation process. The neural network is applied to automatic recognition of a vehicle in visible images. The network is tested with several sequences of images that include targets ranging from no occlusion to almost full occlusion. The results demonstrate an ability to detect occluded targets, while trained with non-occluded ones. In comparison, the proposed network was superior to the Minimum-Average Correlation filter systems and produced better results than the ordinary SWNN.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e81-a_6_1119/_p

Copy

@ARTICLE{e81-a_6_1119,
author={Yonggwan WON, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Shift-Invariant Fuzzy-Morphology Neural Network for Automatic Target Recognition},
year={1998},
volume={E81-A},
number={6},
pages={1119-1127},
abstract={This paper describes a theoretical foundation of fuzzy morphological operations and architectural extension of the shared-weight neural network (SWNN). The network performs shift-invariant filtering using fuzzy-morphological operations for feature extraction. The nodes in the feature extraction stage employ the generalized-mean operator to implement fuzzy-morphological operations. The parameters of the SWNN, weights, morphological structuring element and fuzziness, are optimized by the error back-propagation (EBP) training method. The parameter values of the trained SWNN are then implanted into the extended SWNN (ESWNN) which is a simple convolution neural network. The ESWNN architecture dramatically reduces the amount of computation by avoiding segmentation process. The neural network is applied to automatic recognition of a vehicle in visible images. The network is tested with several sequences of images that include targets ranging from no occlusion to almost full occlusion. The results demonstrate an ability to detect occluded targets, while trained with non-occluded ones. In comparison, the proposed network was superior to the Minimum-Average Correlation filter systems and produced better results than the ordinary SWNN.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Shift-Invariant Fuzzy-Morphology Neural Network for Automatic Target Recognition
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1119
EP - 1127
AU - Yonggwan WON
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E81-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 1998
AB - This paper describes a theoretical foundation of fuzzy morphological operations and architectural extension of the shared-weight neural network (SWNN). The network performs shift-invariant filtering using fuzzy-morphological operations for feature extraction. The nodes in the feature extraction stage employ the generalized-mean operator to implement fuzzy-morphological operations. The parameters of the SWNN, weights, morphological structuring element and fuzziness, are optimized by the error back-propagation (EBP) training method. The parameter values of the trained SWNN are then implanted into the extended SWNN (ESWNN) which is a simple convolution neural network. The ESWNN architecture dramatically reduces the amount of computation by avoiding segmentation process. The neural network is applied to automatic recognition of a vehicle in visible images. The network is tested with several sequences of images that include targets ranging from no occlusion to almost full occlusion. The results demonstrate an ability to detect occluded targets, while trained with non-occluded ones. In comparison, the proposed network was superior to the Minimum-Average Correlation filter systems and produced better results than the ordinary SWNN.
ER -