A Comparative Study for Fisheye Image Classification: SVM or DNN

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

A Comparative Study for Fisheye Image Classification: SVM or DNN. / Chen, Zhen; Georgiadis, Anthimos.
Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020. Hrsg. / Ajith Abraham; Yukio Ohsawa; Niketa Gandhi; M. A. Jabbar; Abdelkrim Haqiq; Seán McLoone; Biju Issac. Springer Science and Business Media Deutschland GmbH, 2021. S. 424-433 (Advances in Intelligent Systems and Computing; Band 1383 AISC).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Chen, Z & Georgiadis, A 2021, A Comparative Study for Fisheye Image Classification: SVM or DNN. in A Abraham, Y Ohsawa, N Gandhi, MA Jabbar, A Haqiq, S McLoone & B Issac (Hrsg.), Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020. Advances in Intelligent Systems and Computing, Bd. 1383 AISC, Springer Science and Business Media Deutschland GmbH, S. 424-433, 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020, Virtual, Online, 15.12.20. https://doi.org/10.1007/978-3-030-73689-7_41

APA

Chen, Z., & Georgiadis, A. (2021). A Comparative Study for Fisheye Image Classification: SVM or DNN. In A. Abraham, Y. Ohsawa, N. Gandhi, M. A. Jabbar, A. Haqiq, S. McLoone, & B. Issac (Hrsg.), Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 (S. 424-433). (Advances in Intelligent Systems and Computing; Band 1383 AISC). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-73689-7_41

Vancouver

Chen Z, Georgiadis A. A Comparative Study for Fisheye Image Classification: SVM or DNN. in Abraham A, Ohsawa Y, Gandhi N, Jabbar MA, Haqiq A, McLoone S, Issac B, Hrsg., Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020. Springer Science and Business Media Deutschland GmbH. 2021. S. 424-433. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-73689-7_41

Bibtex

@inbook{dae030d4563c4e518e45fce5332c9eb2,
title = "A Comparative Study for Fisheye Image Classification: SVM or DNN",
abstract = "The comparison between the feature-based method and the learning-based method is conducted in the training time, the accuracy and the generalization capacity, to address the optimisation for the multi-style fisheye imagery classification. We construct an srd-SIFT descriptor based SVM classifier to present the feature-based method for describing the influence of the dataset scale and the visual word scale on the classifier. The SVM classifier achieves 15.98% accuracy on the test set after 162 h training, with the condition that includes 800 images per class in 12 classes and 1500 visual words. For the learning-based method, we propose to expand training samples{\textquoteright} style variety, via style transformation, to facilitate the contemporary architecture retraining. Following this approach, we retrain the ResNet-50 by an artificial multi-style fisheye image dataset without complementing new training labels. The performance of the obtained ResNet classifier is evaluated on 6000 images collected in the real-world. The result shows that the retrained classifier has great generalization capacity and reaches 97.19% top-3 accuracy.",
keywords = "DNN, Fisheye image, Style expansion, Super vector machine, Engineering",
author = "Zhen Chen and Anthimos Georgiadis",
year = "2021",
month = jan,
day = "1",
doi = "10.1007/978-3-030-73689-7_41",
language = "English",
isbn = "978-3-030-73688-0",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "424--433",
editor = "Ajith Abraham and Yukio Ohsawa and Niketa Gandhi and Jabbar, {M. A.} and Abdelkrim Haqiq and Se{\'a}n McLoone and Biju Issac",
booktitle = "Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020",
address = "Germany",
note = "12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020, SocPar & IAS 2020 ; Conference date: 15-12-2020 Through 18-12-2020",

}

RIS

TY - CHAP

T1 - A Comparative Study for Fisheye Image Classification

T2 - 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020

AU - Chen, Zhen

AU - Georgiadis, Anthimos

N1 - Conference code: 12 & 16

PY - 2021/1/1

Y1 - 2021/1/1

N2 - The comparison between the feature-based method and the learning-based method is conducted in the training time, the accuracy and the generalization capacity, to address the optimisation for the multi-style fisheye imagery classification. We construct an srd-SIFT descriptor based SVM classifier to present the feature-based method for describing the influence of the dataset scale and the visual word scale on the classifier. The SVM classifier achieves 15.98% accuracy on the test set after 162 h training, with the condition that includes 800 images per class in 12 classes and 1500 visual words. For the learning-based method, we propose to expand training samples’ style variety, via style transformation, to facilitate the contemporary architecture retraining. Following this approach, we retrain the ResNet-50 by an artificial multi-style fisheye image dataset without complementing new training labels. The performance of the obtained ResNet classifier is evaluated on 6000 images collected in the real-world. The result shows that the retrained classifier has great generalization capacity and reaches 97.19% top-3 accuracy.

AB - The comparison between the feature-based method and the learning-based method is conducted in the training time, the accuracy and the generalization capacity, to address the optimisation for the multi-style fisheye imagery classification. We construct an srd-SIFT descriptor based SVM classifier to present the feature-based method for describing the influence of the dataset scale and the visual word scale on the classifier. The SVM classifier achieves 15.98% accuracy on the test set after 162 h training, with the condition that includes 800 images per class in 12 classes and 1500 visual words. For the learning-based method, we propose to expand training samples’ style variety, via style transformation, to facilitate the contemporary architecture retraining. Following this approach, we retrain the ResNet-50 by an artificial multi-style fisheye image dataset without complementing new training labels. The performance of the obtained ResNet classifier is evaluated on 6000 images collected in the real-world. The result shows that the retrained classifier has great generalization capacity and reaches 97.19% top-3 accuracy.

KW - DNN

KW - Fisheye image

KW - Style expansion

KW - Super vector machine

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85105858576&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/2d6c1b60-da08-3bbe-b5b5-9d4c1c4207ab/

U2 - 10.1007/978-3-030-73689-7_41

DO - 10.1007/978-3-030-73689-7_41

M3 - Article in conference proceedings

AN - SCOPUS:85105858576

SN - 978-3-030-73688-0

T3 - Advances in Intelligent Systems and Computing

SP - 424

EP - 433

BT - Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020

A2 - Abraham, Ajith

A2 - Ohsawa, Yukio

A2 - Gandhi, Niketa

A2 - Jabbar, M. A.

A2 - Haqiq, Abdelkrim

A2 - McLoone, Seán

A2 - Issac, Biju

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 15 December 2020 through 18 December 2020

ER -

DOI