A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset

Adil Hussain; Kashif Naseer Qureshi; Raja Waseem Anwar; Ayesha Aslam

doi:10.1109/UVS59630.2024.10467149

A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset

Adil Hussain
, Kashif Naseer Qureshi
, Raja Waseem Anwar
, Ayesha Aslam

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

Abstract

Image processing techniques can be used to detect potential defects in images of infrastructure elements that have been collected or scanned. Aside from image processing, machine learning technologies are increasingly being applied to increase crack detection performance and resilience. A novel Surface Crack Detection Convolutional Neural Network (CNN) named the SCD11 CNN model is proposed. The main aim of this research paper is to improve efficiency and minimize the loss rate. The proposed CNN model is compared with the CNNs, including Inception V3, VGG16, and ResNet50, using a Surface Cracks Dataset. The accuracy and loss of the proposed model are compared. The results show that the proposed SCD11 CNN model performs better in test accuracy than Inception V3 and VGG16 and has a slightly lower accuracy than ResNet50.

Original language	English
Title of host publication	2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024
Editors	Aliya Al-Hashim, Tasneem Pervez, Lazhar Khriji, Muhammad Bilal Waris
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350372557
DOIs	https://doi.org/10.1109/UVS59630.2024.10467149
Publication status	Published - 2024
Event	2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024 - Muscat, Oman Duration: 12 Feb 2024 → 14 Feb 2024

Publication series

Name	2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024

Conference

Conference	2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024
Country/Territory	Oman
City	Muscat
Period	12/02/24 → 14/02/24

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure

Keywords

cracks detection
neural networks
road cracks

Access to Document

10.1109/UVS59630.2024.10467149

Cite this

Hussain, A., Qureshi, K. N., Anwar, R. W., & Aslam, A. (2024). A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset. In A. Al-Hashim, T. Pervez, L. Khriji, & M. B. Waris (Eds.), 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024 (2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UVS59630.2024.10467149

Hussain, Adil ; Qureshi, Kashif Naseer ; Anwar, Raja Waseem et al. / A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset. 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024. editor / Aliya Al-Hashim ; Tasneem Pervez ; Lazhar Khriji ; Muhammad Bilal Waris. Institute of Electrical and Electronics Engineers Inc., 2024. (2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024).

@inproceedings{1346b870a81f49e483f181104a343f8e,

title = "A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset",

abstract = "Image processing techniques can be used to detect potential defects in images of infrastructure elements that have been collected or scanned. Aside from image processing, machine learning technologies are increasingly being applied to increase crack detection performance and resilience. A novel Surface Crack Detection Convolutional Neural Network (CNN) named the SCD11 CNN model is proposed. The main aim of this research paper is to improve efficiency and minimize the loss rate. The proposed CNN model is compared with the CNNs, including Inception V3, VGG16, and ResNet50, using a Surface Cracks Dataset. The accuracy and loss of the proposed model are compared. The results show that the proposed SCD11 CNN model performs better in test accuracy than Inception V3 and VGG16 and has a slightly lower accuracy than ResNet50.",

keywords = "cracks detection, neural networks, road cracks",

author = "Adil Hussain and Qureshi, \{Kashif Naseer\} and Anwar, \{Raja Waseem\} and Ayesha Aslam",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024 ; Conference date: 12-02-2024 Through 14-02-2024",

year = "2024",

doi = "10.1109/UVS59630.2024.10467149",

language = "English",

series = "2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Aliya Al-Hashim and Tasneem Pervez and Lazhar Khriji and Waris, \{Muhammad Bilal\}",

booktitle = "2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024",

}

Hussain, A, Qureshi, KN, Anwar, RW & Aslam, A 2024, A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset. in A Al-Hashim, T Pervez, L Khriji & MB Waris (eds), 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024. 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024, Institute of Electrical and Electronics Engineers Inc., 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024, Muscat, Oman, 12/02/24. https://doi.org/10.1109/UVS59630.2024.10467149

A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset. / Hussain, Adil; Qureshi, Kashif Naseer; Anwar, Raja Waseem et al.
2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024. ed. / Aliya Al-Hashim; Tasneem Pervez; Lazhar Khriji; Muhammad Bilal Waris. Institute of Electrical and Electronics Engineers Inc., 2024. (2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024).

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

TY - GEN

T1 - A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset

AU - Hussain, Adil

AU - Qureshi, Kashif Naseer

AU - Anwar, Raja Waseem

AU - Aslam, Ayesha

PY - 2024

Y1 - 2024

N2 - Image processing techniques can be used to detect potential defects in images of infrastructure elements that have been collected or scanned. Aside from image processing, machine learning technologies are increasingly being applied to increase crack detection performance and resilience. A novel Surface Crack Detection Convolutional Neural Network (CNN) named the SCD11 CNN model is proposed. The main aim of this research paper is to improve efficiency and minimize the loss rate. The proposed CNN model is compared with the CNNs, including Inception V3, VGG16, and ResNet50, using a Surface Cracks Dataset. The accuracy and loss of the proposed model are compared. The results show that the proposed SCD11 CNN model performs better in test accuracy than Inception V3 and VGG16 and has a slightly lower accuracy than ResNet50.

AB - Image processing techniques can be used to detect potential defects in images of infrastructure elements that have been collected or scanned. Aside from image processing, machine learning technologies are increasingly being applied to increase crack detection performance and resilience. A novel Surface Crack Detection Convolutional Neural Network (CNN) named the SCD11 CNN model is proposed. The main aim of this research paper is to improve efficiency and minimize the loss rate. The proposed CNN model is compared with the CNNs, including Inception V3, VGG16, and ResNet50, using a Surface Cracks Dataset. The accuracy and loss of the proposed model are compared. The results show that the proposed SCD11 CNN model performs better in test accuracy than Inception V3 and VGG16 and has a slightly lower accuracy than ResNet50.

KW - cracks detection

KW - neural networks

KW - road cracks

UR - https://www.scopus.com/pages/publications/85189616379

U2 - 10.1109/UVS59630.2024.10467149

DO - 10.1109/UVS59630.2024.10467149

M3 - Conference contribution

AN - SCOPUS:85189616379

T3 - 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024

BT - 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024

A2 - Al-Hashim, Aliya

A2 - Pervez, Tasneem

A2 - Khriji, Lazhar

A2 - Waris, Muhammad Bilal

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024

Y2 - 12 February 2024 through 14 February 2024

ER -

Hussain A, Qureshi KN, Anwar RW, Aslam A. A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset. In Al-Hashim A, Pervez T, Khriji L, Waris MB, editors, 2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024. Institute of Electrical and Electronics Engineers Inc. 2024. (2nd International Conference on Unmanned Vehicle Systems-Oman, UVS 2024). doi: 10.1109/UVS59630.2024.10467149

A Novel SCD11 CNN Model Performance Evaluation with Inception V3, VGG16 and ResNet50 Using Surface Crack Dataset

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this