EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16

Subhrangshu Adhikary, Saikat Banerjee, Rajani Singh, Ashutosh Dhar Dwivedi

PeerJ Computer Science · 30.04.2025 · 11 · e2860

DOI: 10.7717/peerj-cs.2860 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 30.04.2025. Verfasst von Subhrangshu Adhikary und 3 weiteren Autor:innen. Beteiligte Einrichtung: Research and Development, Spiraldevs Automation Industries Pvt. Ltd., Raiganj, West Bengal, India. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An intelligent detection and recognition model for the fish species from camera footage is urgently required as fishery contributes to a large portion of the world economy, and these kinds of advanced models can aid fishermen on a large scale. Such models incorporating a pick-and-place machine can be beneficial to sorting different fish species in bulk without human intervention, significantly reducing costs for large-scale fishing industries. Existing methods for detecting and recognizing fish species have many limitations, such as limited scalability, detection accuracy, failure to detect multiple species, degraded performance at a lower resolution, or pinpointing the exact location of the fish. Modifying the head of a compelling deep learning model, namely VGG-16, with pre-trained weights, can be used to detect both the species of the fish and find the exact location of the fish in an image by implementing a modified You Only Look Once (YOLO) to incorporate the bounding box regression head. We have proposed using the Enhanced Super Resolution Generative Adversarial Network (ESRGAN) algorithm and the proposed neural network to amplify the image resolution by a factor of 4. With this method, an overall detection accuracy of 96.5% has been obtained. The experiment has been conducted based on a total of 9,460 images spread across nine species. After further improving the model, a pick-and-place machine could be integrated to quickly sort the fish according to their species in different large-scale fish industries.

Schlagwörter

Stichwörter der Autor:innen

Deep learningObject detectionSuper resolution

Autor:innen und Institutionen

  • Research and Development, Spiraldevs Automation Industries Pvt. Ltd., Raiganj, West Bengal, India.
  • Remote Sensing, Aerosys Defence and Aerospace Pvt. Ltd., Pune, Maharashtra, India.
  • Department of Digitalization, Copenhagen Business School, Copenhagen, Denmark.
  • Cyber Security Group, Department of Electronic Systems, Aalborg University, Copenhagen, Denmark.

Zitieren

APA

Adhikary, S., Banerjee, S., Singh, R., & Dwivedi, A. D. (2025). Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16. PeerJ Computer Science, 11, e2860. https://doi.org/10.7717/peerj-cs.2860

Vancouver

Adhikary S, Banerjee S, Singh R, Dwivedi AD. Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16. PeerJ Computer Science. 2025;11:e2860. doi:10.7717/peerj-cs.2860

BibTeX
@article{Adhikary2025,
  author = {Adhikary, Subhrangshu and Banerjee, Saikat and Singh, Rajani and Dwivedi, Ashutosh Dhar},
  title = {Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e2860},
  doi = {10.7717/peerj-cs.2860}
}
Kostenlos starten →