Image redundancy reduction for neural network classification using discrete cosine transforms

Z. Pan; A.G. Rust; H. Bolouri

doi:10.1109/IJCNN.2000.861296

Image redundancy reduction for neural network classification using discrete cosine transforms

Z. Pan, A.G. Rust, H. Bolouri

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

66 Citations (Scopus)

41 Downloads (Pure)

Abstract

High information redundancy and strong correlations in face images result in inefficiencies when such images are used directly in recognition tasks. In this paper, discrete cosine transforms (DCT) are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features, such as hair outline, eyes and mouth. We demonstrate experimentally that when DCT coefficients are fed into a backpropagation neural network for classification, high recognition rates can be achieved using only a small proportion (0.19%) of available transform components. This makes DCT-based face recognition more than two orders of magnitude faster than other approaches.

Original language	English
Title of host publication	Procs of IEEE-INNS-ENNS Int Jt Conf on Neural Networks
Subtitle of host publication	IJCNN 2000
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	149-154
Volume	3
ISBN (Print)	0-7695-0619-4
DOIs	https://doi.org/10.1109/IJCNN.2000.861296
Publication status	Published - 2000
Event	IEEE-INNS-ENNS Int Joint Conf on Neural Networks - Como, Italy Duration: 24 Jul 2000 → 27 Jul 2000

Conference

Conference	IEEE-INNS-ENNS Int Joint Conf on Neural Networks
Country/Territory	Italy
City	Como
Period	24/07/00 → 27/07/00

Keywords

backpropagation
face recognition

Access to Document

10.1109/IJCNN.2000.861296

903609
“This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder." “Copyright IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.”
Final published version, 491 KB

Cite this

@inproceedings{d33d66d71c7e448c8e1c22e7cd706c24,

title = "Image redundancy reduction for neural network classification using discrete cosine transforms",

abstract = "High information redundancy and strong correlations in face images result in inefficiencies when such images are used directly in recognition tasks. In this paper, discrete cosine transforms (DCT) are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features, such as hair outline, eyes and mouth. We demonstrate experimentally that when DCT coefficients are fed into a backpropagation neural network for classification, high recognition rates can be achieved using only a small proportion (0.19%) of available transform components. This makes DCT-based face recognition more than two orders of magnitude faster than other approaches.",

keywords = "backpropagation, face recognition",

author = "Z. Pan and A.G. Rust and H. Bolouri",

note = "“This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.{"} “Copyright IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.” DOI: 10.1109/IJCNN.2000.861296; IEEE-INNS-ENNS Int Joint Conf on Neural Networks ; Conference date: 24-07-2000 Through 27-07-2000",

year = "2000",

doi = "10.1109/IJCNN.2000.861296",

language = "English",

isbn = "0-7695-0619-4",

volume = "3",

pages = "149--154",

booktitle = "Procs of IEEE-INNS-ENNS Int Jt Conf on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Pan, Z, Rust, AG & Bolouri, H 2000, Image redundancy reduction for neural network classification using discrete cosine transforms. in Procs of IEEE-INNS-ENNS Int Jt Conf on Neural Networks: IJCNN 2000. vol. 3, Institute of Electrical and Electronics Engineers (IEEE), pp. 149-154, IEEE-INNS-ENNS Int Joint Conf on Neural Networks , Como, Italy, 24/07/00. https://doi.org/10.1109/IJCNN.2000.861296

TY - GEN

T1 - Image redundancy reduction for neural network classification using discrete cosine transforms

AU - Pan, Z.

AU - Rust, A.G.

AU - Bolouri, H.

N1 - “This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder." “Copyright IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.” DOI: 10.1109/IJCNN.2000.861296

PY - 2000

Y1 - 2000

N2 - High information redundancy and strong correlations in face images result in inefficiencies when such images are used directly in recognition tasks. In this paper, discrete cosine transforms (DCT) are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features, such as hair outline, eyes and mouth. We demonstrate experimentally that when DCT coefficients are fed into a backpropagation neural network for classification, high recognition rates can be achieved using only a small proportion (0.19%) of available transform components. This makes DCT-based face recognition more than two orders of magnitude faster than other approaches.

AB - High information redundancy and strong correlations in face images result in inefficiencies when such images are used directly in recognition tasks. In this paper, discrete cosine transforms (DCT) are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features, such as hair outline, eyes and mouth. We demonstrate experimentally that when DCT coefficients are fed into a backpropagation neural network for classification, high recognition rates can be achieved using only a small proportion (0.19%) of available transform components. This makes DCT-based face recognition more than two orders of magnitude faster than other approaches.

KW - backpropagation

KW - face recognition

U2 - 10.1109/IJCNN.2000.861296

DO - 10.1109/IJCNN.2000.861296

M3 - Conference contribution

SN - 0-7695-0619-4

VL - 3

SP - 149

EP - 154

BT - Procs of IEEE-INNS-ENNS Int Jt Conf on Neural Networks

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - IEEE-INNS-ENNS Int Joint Conf on Neural Networks

Y2 - 24 July 2000 through 27 July 2000

ER -

Image redundancy reduction for neural network classification using discrete cosine transforms

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this