A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks

Jung Hyoun Kim; Sung Ho Yoon; Kwanghoon H. Sohn

doi:10.1016/S0031-3203(96)00043-X

A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks

Jung Hyoun Kim, Sung Ho Yoon, Kwanghoon H. Sohn

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

27 Citations (Scopus)

Abstract

This paper presents a new method of occluded object matching for machine vision applications. The current methods for occluded object matching lack robustness and require high computational effort. In this paper, a new Hybrid Hopfield Neural Network (HHN) algorithm, which combines the advantages of both a Continuous Hopfield Network (CHN) and a Discrete Hopfield Network (DHN), will be described and applied for partially occluded object recognition in a multi-context scenery. The HHN proposed as a new approach provides great fault tolerance and robustness and requires less computation time. Also, advantages of HHN such as reliability and speed will be discussed.

Original language	English
Pages (from-to)	2047-2060
Number of pages	14
Journal	Pattern Recognition
Volume	29
Issue number	12
DOIs	https://doi.org/10.1016/S0031-3203(96)00043-X
Publication status	Published - 1996 Dec

Bibliographical note

Funding Information:
Acknowledgements--This research has been supported by FAA under Grant No. 93-G-012, ARO under Grant No. DAAL03-90-0913, NASA-CORE under Grant No. NAGW-2924, and ARPA under Grant No. N00600-93-K-2051.

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/S0031-3203(96)00043-X

Cite this

@article{a1db33c8ce8a4a7b89d9f16a29ae4936,

title = "A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks",

abstract = "This paper presents a new method of occluded object matching for machine vision applications. The current methods for occluded object matching lack robustness and require high computational effort. In this paper, a new Hybrid Hopfield Neural Network (HHN) algorithm, which combines the advantages of both a Continuous Hopfield Network (CHN) and a Discrete Hopfield Network (DHN), will be described and applied for partially occluded object recognition in a multi-context scenery. The HHN proposed as a new approach provides great fault tolerance and robustness and requires less computation time. Also, advantages of HHN such as reliability and speed will be discussed.",

author = "Kim, {Jung Hyoun} and Yoon, {Sung Ho} and Sohn, {Kwanghoon H.}",

note = "Funding Information: Acknowledgements--This research has been supported by FAA under Grant No. 93-G-012, ARO under Grant No. DAAL03-90-0913, NASA-CORE under Grant No. NAGW-2924, and ARPA under Grant No. N00600-93-K-2051.",

year = "1996",

month = dec,

doi = "10.1016/S0031-3203(96)00043-X",

language = "English",

volume = "29",

pages = "2047--2060",

journal = "Pattern Recognition",

issn = "0031-3203",

publisher = "Elsevier Limited",

number = "12",

}

TY - JOUR

T1 - A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks

AU - Kim, Jung Hyoun

AU - Yoon, Sung Ho

AU - Sohn, Kwanghoon H.

N1 - Funding Information: Acknowledgements--This research has been supported by FAA under Grant No. 93-G-012, ARO under Grant No. DAAL03-90-0913, NASA-CORE under Grant No. NAGW-2924, and ARPA under Grant No. N00600-93-K-2051.

PY - 1996/12

Y1 - 1996/12

N2 - This paper presents a new method of occluded object matching for machine vision applications. The current methods for occluded object matching lack robustness and require high computational effort. In this paper, a new Hybrid Hopfield Neural Network (HHN) algorithm, which combines the advantages of both a Continuous Hopfield Network (CHN) and a Discrete Hopfield Network (DHN), will be described and applied for partially occluded object recognition in a multi-context scenery. The HHN proposed as a new approach provides great fault tolerance and robustness and requires less computation time. Also, advantages of HHN such as reliability and speed will be discussed.

AB - This paper presents a new method of occluded object matching for machine vision applications. The current methods for occluded object matching lack robustness and require high computational effort. In this paper, a new Hybrid Hopfield Neural Network (HHN) algorithm, which combines the advantages of both a Continuous Hopfield Network (CHN) and a Discrete Hopfield Network (DHN), will be described and applied for partially occluded object recognition in a multi-context scenery. The HHN proposed as a new approach provides great fault tolerance and robustness and requires less computation time. Also, advantages of HHN such as reliability and speed will be discussed.

UR - http://www.scopus.com/inward/record.url?scp=0030398036&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030398036&partnerID=8YFLogxK

U2 - 10.1016/S0031-3203(96)00043-X

DO - 10.1016/S0031-3203(96)00043-X

M3 - Article

AN - SCOPUS:0030398036

SN - 0031-3203

VL - 29

SP - 2047

EP - 2060

JO - Pattern Recognition

JF - Pattern Recognition

IS - 12

ER -

A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this