Computer vision and deep transfer learning for automatic gauge reading detection
Scientific Reports · 03.10.2024 · 14 (1)
DOI: 10.1038/s41598-024-71270-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Scientific Reports, online erschienen am 03.10.2024. Verfasst von Hitesh Ninama und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Engineering and Technology, Devi Ahilya University, Indore, M.P., 452001, India. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Deanship of Scientific Research at King Khalid University for funding this work through large Research Groups Project under grant number (RGP.2/127/44).,, Deanship of Scientific Research, King Khalid University.
Abstract (Originalsprache)
This manuscript proposes an automatic reading detection system for an analogue gauge using a combination of deep learning, machine learning, and image processing. The study suggests image-processing techniques in manual analogue gauge reading that include generating readings for the image to provide supervised data to address difficulties in unsupervised data in gauges and to achieve better accuracy using DenseNet 169 compared to other approaches. The model uses artificial intelligence to automate reading detection using deep transfer learning models like DenseNet 169, InceptionNet V3, and VGG19. The models were trained using 1011 labeled pictures, 9 classes, and readings from 0 to 8. The VGG19 model exhibits a high training precision of 97.00% but a comparatively lower testing precision of 75.00%, indicating the possibility of overfitting. On the other hand, InceptionNet V3 demonstrates consistent precision across both datasets, but DenseNet 169 surpasses other models in terms of precision and generalization capabilities.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Engineering and Technology, Devi Ahilya University, Indore, M.P., 452001, India.
- School of Computer Science and Information Technology, Devi Ahilya University, Indore, M.P., 452001, India.
- Senior Software Engineer, Intel Corporation, Hillsboro, OR, 97006, USA.
- Department of CSE, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad, 500090, India.
- Department of Computer Science and Engineering, Parala Maharaja Engineering College (Govt.), Berhampur, Odisha, 761003, India.
- School of Computer Science, SCS Taylor's University, 47500, Subang Jaya, Malaysia. Noorzaman.jhanjhi@taylors.edu.my.
Förderung
- Deanship of Scientific Research at King Khalid University for funding this work through large Research Groups Project under grant number (RGP.2/127/44).,
- Deanship of Scientific Research, King Khalid University
Zitieren
APA
Ninama, H., Raikwal, J., Ravuri, A., Sukheja, D., Bhoi, S. K., Jhanjhi, N. Z., Elnour, A. A. H., & Abdelmaboud, A. (2024). Computer vision and deep transfer learning for automatic gauge reading detection. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-71270-0
Vancouver
Ninama H, Raikwal J, Ravuri A, Sukheja D, Bhoi SK, Jhanjhi NZ, et al. Computer vision and deep transfer learning for automatic gauge reading detection. Scientific Reports. 2024;14(1). doi:10.1038/s41598-024-71270-0
BibTeX
@article{Ninama2024,
author = {Ninama, Hitesh and Raikwal, Jagdish and Ravuri, Ananda and Sukheja, Deepak and Bhoi, Sourav Kumar and Jhanjhi, N Z and Elnour, Asma Abbas Hassan and Abdelmaboud, Abdelzahir},
title = {Computer vision and deep transfer learning for automatic gauge reading detection},
journal = {Scientific Reports},
year = {2024},
volume = {14},
number = {1},
doi = {10.1038/s41598-024-71270-0}
}
EUVIMED