Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition

Kh Tohidul Islam; Ram Gopal Raj; Abdullah Al-Murad

doi:10.1109/CEEE.2017.8412925

Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition

Kh Tohidul Islam
, Ram Gopal Raj
, Abdullah Al-Murad

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

27 Citations (Scopus)

Abstract

In this study, we present the performance of Support Vector Machine (SVM), Convolution Neural Network (CNN), and Artificial Neural Network (ANN) with Bag of Words (BoW), Histogram of Oriented Gradients (HOG), and Image Pixels (IP) for face recognition. SVM, CNN, and ANN are machine learning approaches and has been used for pattern recognition, especially in face recognition technology. BoW, HOG, and IP are being used for image feature extraction. The testing has been conducted from publicly available ATT face database. Every individual subject consists of 10 images with different facial expression, different illumination and the dimensions of the images is unified as 92-by-112 pixels with PGM formats. SVM achieved recognition accuracy of 97.00%, 96.00%, and 98.00% with subsequently BoW, HOG, and IP. CNN achieved recognition accuracy of 94.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. ANN achieved recognition accuracy of 96.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. The experimental results show that the IP with ANN approach clearly outperformed the others approaches.

Original language	English
Title of host publication	2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017)
Editors	Amar Mezache, Diaa Fawzy, Vanco Cabukovski, Yasar Birbir
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	288-291
Number of pages	4
ISBN (Electronic)	9781538633403, 9781538633410
ISBN (Print)	9781538633427
DOIs	https://doi.org/10.1109/CEEE.2017.8412925
Publication status	Published - 2017
Externally published	Yes
Event	International Conference on Electrical and Electronic Engineering (EEE) 2017 - Rajshahi, Bangladesh Duration: 27 Dec 2017 → 29 Dec 2017 Conference number: 2nd https://ieeexplore.ieee.org/xpl/conhome/8405515/proceeding (Proceedings) http://www.iceee.org/iceee17.html (Website)

Conference

Conference	International Conference on Electrical and Electronic Engineering (EEE) 2017
Abbreviated title	ICEEE 2017
Country/Territory	Bangladesh
City	Rajshahi
Period	27/12/17 → 29/12/17
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8405515/proceeding (Proceedings) http://www.iceee.org/iceee17.html (Website)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

ANN
BoW
CNN
face recognition
HOG
IP
SVM

Access to Document

10.1109/CEEE.2017.8412925

Cite this

Islam, K. T., Raj, R. G., & Al-Murad, A. (2017). Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition. In A. Mezache, D. Fawzy, V. Cabukovski, & Y. Birbir (Eds.), 2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017) (pp. 288-291). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CEEE.2017.8412925

Islam, Kh Tohidul ; Raj, Ram Gopal ; Al-Murad, Abdullah. / Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition. 2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017). editor / Amar Mezache ; Diaa Fawzy ; Vanco Cabukovski ; Yasar Birbir. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 288-291

@inproceedings{baa099d136584dbc80a23a3158213c1b,

title = "Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition",

abstract = "In this study, we present the performance of Support Vector Machine (SVM), Convolution Neural Network (CNN), and Artificial Neural Network (ANN) with Bag of Words (BoW), Histogram of Oriented Gradients (HOG), and Image Pixels (IP) for face recognition. SVM, CNN, and ANN are machine learning approaches and has been used for pattern recognition, especially in face recognition technology. BoW, HOG, and IP are being used for image feature extraction. The testing has been conducted from publicly available ATT face database. Every individual subject consists of 10 images with different facial expression, different illumination and the dimensions of the images is unified as 92-by-112 pixels with PGM formats. SVM achieved recognition accuracy of 97.00\%, 96.00\%, and 98.00\% with subsequently BoW, HOG, and IP. CNN achieved recognition accuracy of 94.00\%, 99.00\%, and 99.50\% with subsequently BoW, HOG, and IP. ANN achieved recognition accuracy of 96.00\%, 99.00\%, and 99.50\% with subsequently BoW, HOG, and IP. The experimental results show that the IP with ANN approach clearly outperformed the others approaches.",

keywords = "ANN, BoW, CNN, face recognition, HOG, IP, SVM",

author = "Islam, \{Kh Tohidul\} and Raj, \{Ram Gopal\} and Abdullah Al-Murad",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; International Conference on Electrical and Electronic Engineering (EEE) 2017, ICEEE 2017 ; Conference date: 27-12-2017 Through 29-12-2017",

year = "2017",

doi = "10.1109/CEEE.2017.8412925",

language = "English",

isbn = "9781538633427",

pages = "288--291",

editor = "Amar Mezache and Diaa Fawzy and Vanco Cabukovski and Yasar Birbir",

booktitle = "2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017)",

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

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/8405515/proceeding, http://www.iceee.org/iceee17.html",

}

Islam, KT, Raj, RG & Al-Murad, A 2017, Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition. in A Mezache, D Fawzy, V Cabukovski & Y Birbir (eds), 2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017). IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 288-291, International Conference on Electrical and Electronic Engineering (EEE) 2017, Rajshahi, Bangladesh, 27/12/17. https://doi.org/10.1109/CEEE.2017.8412925

Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition. / Islam, Kh Tohidul; Raj, Ram Gopal; Al-Murad, Abdullah.
2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017). ed. / Amar Mezache; Diaa Fawzy; Vanco Cabukovski; Yasar Birbir. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 288-291.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition

AU - Islam, Kh Tohidul

AU - Raj, Ram Gopal

AU - Al-Murad, Abdullah

N1 - Conference code: 2nd

PY - 2017

Y1 - 2017

N2 - In this study, we present the performance of Support Vector Machine (SVM), Convolution Neural Network (CNN), and Artificial Neural Network (ANN) with Bag of Words (BoW), Histogram of Oriented Gradients (HOG), and Image Pixels (IP) for face recognition. SVM, CNN, and ANN are machine learning approaches and has been used for pattern recognition, especially in face recognition technology. BoW, HOG, and IP are being used for image feature extraction. The testing has been conducted from publicly available ATT face database. Every individual subject consists of 10 images with different facial expression, different illumination and the dimensions of the images is unified as 92-by-112 pixels with PGM formats. SVM achieved recognition accuracy of 97.00%, 96.00%, and 98.00% with subsequently BoW, HOG, and IP. CNN achieved recognition accuracy of 94.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. ANN achieved recognition accuracy of 96.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. The experimental results show that the IP with ANN approach clearly outperformed the others approaches.

AB - In this study, we present the performance of Support Vector Machine (SVM), Convolution Neural Network (CNN), and Artificial Neural Network (ANN) with Bag of Words (BoW), Histogram of Oriented Gradients (HOG), and Image Pixels (IP) for face recognition. SVM, CNN, and ANN are machine learning approaches and has been used for pattern recognition, especially in face recognition technology. BoW, HOG, and IP are being used for image feature extraction. The testing has been conducted from publicly available ATT face database. Every individual subject consists of 10 images with different facial expression, different illumination and the dimensions of the images is unified as 92-by-112 pixels with PGM formats. SVM achieved recognition accuracy of 97.00%, 96.00%, and 98.00% with subsequently BoW, HOG, and IP. CNN achieved recognition accuracy of 94.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. ANN achieved recognition accuracy of 96.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. The experimental results show that the IP with ANN approach clearly outperformed the others approaches.

KW - ANN

KW - BoW

KW - CNN

KW - face recognition

KW - HOG

KW - IP

KW - SVM

UR - https://www.scopus.com/pages/publications/85050972791

U2 - 10.1109/CEEE.2017.8412925

DO - 10.1109/CEEE.2017.8412925

M3 - Conference Paper

AN - SCOPUS:85050972791

SN - 9781538633427

SP - 288

EP - 291

BT - 2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017)

A2 - Mezache, Amar

A2 - Fawzy, Diaa

A2 - Cabukovski, Vanco

A2 - Birbir, Yasar

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - International Conference on Electrical and Electronic Engineering (EEE) 2017

Y2 - 27 December 2017 through 29 December 2017

ER -

Islam KT, Raj RG, Al-Murad A. Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition. In Mezache A, Fawzy D, Cabukovski V, Birbir Y, editors, 2nd International Conference on Electrical and Electronic Engineering (ICEEE 2017). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 288-291 doi: 10.1109/CEEE.2017.8412925

Performance of SVM, CNN, and ANN with BoW, HOG, and Image Pixels in face recognition

Abstract

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Cite this