Image Band-Distributive PCA-Based Face Recognition Technique

H Ndu; Akbar  Sheikh-Akbari; Iosif Mporas; J Deng

doi:10.1007/978-3-031-47594-8_11

Image Band-Distributive PCA-Based Face Recognition Technique

H Ndu, Akbar Sheikh-Akbari, Iosif Mporas, J Deng

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

Abstract

This paper presents an Image Band-Distributive PCA (IBD-PCA) based technique for face recognition. The proposed method consists of four steps. In the first step, the reference image is pre-processed by converting its pixel values and performing histogram equalization to increase its contrast. In the second step, the equal-size boundary calculation method is used to calculate the boundary splitting values to divide the input image into multiple images with respect to band intensities of pixels. In the third step, Principal Component Analysis (PCA) is used to extract features from the images which will then be used as the input for the fourth step. In the last step, matching is performed by calculating the Euclidean distance between principal components. The proposed technique has been tested on the ORL Face Database and Yale Face Database. The experimental results demonstrate that the proposed technique outperforms other techniques on the same database.

Original language	English
Title of host publication	Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs
Subtitle of host publication	Proceedings of the 15th International Conference on Global Security, Safety and Sustainability, London, October 2023
Editors	Hamid Jahankhani
Publisher	Springer Nature
Pages	219-230
Number of pages	12
Edition	1
ISBN (Electronic)	978-3-031-47594-8
ISBN (Print)	978-3-031-47593-1, 978-3-031-47596-2
DOIs	https://doi.org/10.1007/978-3-031-47594-8_11
Publication status	Published - 22 Mar 2024
Event	Virtual 15th International Conference on global Security, Safety & Sustainability - Virtual Conference, London, United Kingdom Duration: 11 Oct 2023 → 12 Oct 2023 Conference number: 15 https://london.northumbria.ac.uk/icgs3-23/

Publication series

Name	Advanced Sciences and Technologies for Security Applications
Volume	Part F2308
ISSN (Print)	1613-5113
ISSN (Electronic)	2363-9466

Conference

Conference	Virtual 15th International Conference on global Security, Safety & Sustainability
Abbreviated title	ICGS3 2023
Country/Territory	United Kingdom
City	London
Period	11/10/23 → 12/10/23
Internet address	https://london.northumbria.ac.uk/icgs3-23/

Keywords

Face recognition
Image band-distributive PCA
Principal component analysis

Access to Document

10.1007/978-3-031-47594-8_11Licence: Unspecified

Cite this

Ndu, H., Sheikh-Akbari, A., Mporas, I., & Deng, J. (2024). Image Band-Distributive PCA-Based Face Recognition Technique. In H. Jahankhani (Ed.), Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs: Proceedings of the 15th International Conference on Global Security, Safety and Sustainability, London, October 2023 (1 ed., pp. 219-230). (Advanced Sciences and Technologies for Security Applications; Vol. Part F2308). Springer Nature. https://doi.org/10.1007/978-3-031-47594-8_11

Ndu, H ; Sheikh-Akbari, Akbar ; Mporas, Iosif et al. / Image Band-Distributive PCA-Based Face Recognition Technique. Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs: Proceedings of the 15th International Conference on Global Security, Safety and Sustainability, London, October 2023. editor / Hamid Jahankhani. 1. ed. Springer Nature, 2024. pp. 219-230 (Advanced Sciences and Technologies for Security Applications).

@inproceedings{10a7a9c3a9fb4527baf2e385ccb54abe,

title = "Image Band-Distributive PCA-Based Face Recognition Technique",

abstract = "This paper presents an Image Band-Distributive PCA (IBD-PCA) based technique for face recognition. The proposed method consists of four steps. In the first step, the reference image is pre-processed by converting its pixel values and performing histogram equalization to increase its contrast. In the second step, the equal-size boundary calculation method is used to calculate the boundary splitting values to divide the input image into multiple images with respect to band intensities of pixels. In the third step, Principal Component Analysis (PCA) is used to extract features from the images which will then be used as the input for the fourth step. In the last step, matching is performed by calculating the Euclidean distance between principal components. The proposed technique has been tested on the ORL Face Database and Yale Face Database. The experimental results demonstrate that the proposed technique outperforms other techniques on the same database.",

keywords = "Face recognition, Image band-distributive PCA, Principal component analysis",

author = "H Ndu and Akbar Sheikh-Akbari and Iosif Mporas and J Deng",

note = "{\textcopyright} 2024 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.; Virtual 15th International Conference on global Security, Safety & Sustainability, ICGS3 2023 ; Conference date: 11-10-2023 Through 12-10-2023",

year = "2024",

month = mar,

day = "22",

doi = "10.1007/978-3-031-47594-8_11",

language = "English",

isbn = "978-3-031-47593-1",

series = "Advanced Sciences and Technologies for Security Applications",

publisher = "Springer Nature",

pages = "219--230",

editor = "Hamid Jahankhani",

booktitle = "Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs",

address = "Netherlands",

edition = "1",

url = "https://london.northumbria.ac.uk/icgs3-23/",

}

Ndu, H, Sheikh-Akbari, A, Mporas, I & Deng, J 2024, Image Band-Distributive PCA-Based Face Recognition Technique. in H Jahankhani (ed.), Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs: Proceedings of the 15th International Conference on Global Security, Safety and Sustainability, London, October 2023. 1 edn, Advanced Sciences and Technologies for Security Applications, vol. Part F2308, Springer Nature, pp. 219-230, Virtual 15th International Conference on global Security, Safety & Sustainability, London, United Kingdom, 11/10/23. https://doi.org/10.1007/978-3-031-47594-8_11

Image Band-Distributive PCA-Based Face Recognition Technique. / Ndu, H; Sheikh-Akbari, Akbar ; Mporas, Iosif et al.
Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs: Proceedings of the 15th International Conference on Global Security, Safety and Sustainability, London, October 2023. ed. / Hamid Jahankhani. 1. ed. Springer Nature, 2024. p. 219-230 (Advanced Sciences and Technologies for Security Applications; Vol. Part F2308).

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

TY - GEN

T1 - Image Band-Distributive PCA-Based Face Recognition Technique

AU - Ndu, H

AU - Sheikh-Akbari, Akbar

AU - Mporas, Iosif

AU - Deng, J

N1 - Conference code: 15

PY - 2024/3/22

Y1 - 2024/3/22

N2 - This paper presents an Image Band-Distributive PCA (IBD-PCA) based technique for face recognition. The proposed method consists of four steps. In the first step, the reference image is pre-processed by converting its pixel values and performing histogram equalization to increase its contrast. In the second step, the equal-size boundary calculation method is used to calculate the boundary splitting values to divide the input image into multiple images with respect to band intensities of pixels. In the third step, Principal Component Analysis (PCA) is used to extract features from the images which will then be used as the input for the fourth step. In the last step, matching is performed by calculating the Euclidean distance between principal components. The proposed technique has been tested on the ORL Face Database and Yale Face Database. The experimental results demonstrate that the proposed technique outperforms other techniques on the same database.

AB - This paper presents an Image Band-Distributive PCA (IBD-PCA) based technique for face recognition. The proposed method consists of four steps. In the first step, the reference image is pre-processed by converting its pixel values and performing histogram equalization to increase its contrast. In the second step, the equal-size boundary calculation method is used to calculate the boundary splitting values to divide the input image into multiple images with respect to band intensities of pixels. In the third step, Principal Component Analysis (PCA) is used to extract features from the images which will then be used as the input for the fourth step. In the last step, matching is performed by calculating the Euclidean distance between principal components. The proposed technique has been tested on the ORL Face Database and Yale Face Database. The experimental results demonstrate that the proposed technique outperforms other techniques on the same database.

KW - Face recognition

KW - Image band-distributive PCA

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=85186462084&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-47594-8_11

DO - 10.1007/978-3-031-47594-8_11

M3 - Conference contribution

SN - 978-3-031-47593-1

SN - 978-3-031-47596-2

T3 - Advanced Sciences and Technologies for Security Applications

SP - 219

EP - 230

BT - Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs

A2 - Jahankhani, Hamid

PB - Springer Nature

T2 - Virtual 15th International Conference on global Security, Safety & Sustainability

Y2 - 11 October 2023 through 12 October 2023

ER -

Ndu H, Sheikh-Akbari A, Mporas I, Deng J. Image Band-Distributive PCA-Based Face Recognition Technique. In Jahankhani H, editor, Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs: Proceedings of the 15th International Conference on Global Security, Safety and Sustainability, London, October 2023. 1 ed. Springer Nature. 2024. p. 219-230. (Advanced Sciences and Technologies for Security Applications). Epub 2024 Feb 20. doi: 10.1007/978-3-031-47594-8_11

Image Band-Distributive PCA-Based Face Recognition Technique

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this