Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16
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 b...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-04-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2860.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850194838156214272 |
|---|---|
| author | Subhrangshu Adhikary Saikat Banerjee Rajani Singh Ashutosh Dhar Dwivedi |
| author_facet | Subhrangshu Adhikary Saikat Banerjee Rajani Singh Ashutosh Dhar Dwivedi |
| author_sort | Subhrangshu Adhikary |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-34010fbd08544b0c9bcb6f2fc636fe69 |
| institution | OA Journals |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-34010fbd08544b0c9bcb6f2fc636fe692025-08-20T02:13:54ZengPeerJ Inc.PeerJ Computer Science2376-59922025-04-0111e286010.7717/peerj-cs.2860Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16Subhrangshu Adhikary0Saikat Banerjee1Rajani Singh2Ashutosh Dhar Dwivedi3Research and Development, Spiraldevs Automation Industries Pvt. Ltd., Raiganj, West Bengal, IndiaRemote Sensing, Aerosys Defence and Aerospace Pvt. Ltd., Pune, Maharashtra, IndiaDepartment of Digitalization, Copenhagen Business School, Copenhagen, DenmarkCyber Security Group, Department of Electronic Systems, Aalborg University, Copenhagen, DenmarkAn 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.https://peerj.com/articles/cs-2860.pdfDeep learningSuper resolutionObject detection |
| spellingShingle | Subhrangshu Adhikary Saikat Banerjee Rajani Singh Ashutosh Dhar Dwivedi Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16 PeerJ Computer Science Deep learning Super resolution Object detection |
| title | Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16 |
| title_full | Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16 |
| title_fullStr | Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16 |
| title_full_unstemmed | Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16 |
| title_short | Fish species identification on low resolution—a study with enhanced super-resolution generative adversarial network (ESRGAN), YOLO and VGG-16 |
| title_sort | fish species identification on low resolution a study with enhanced super resolution generative adversarial network esrgan yolo and vgg 16 |
| topic | Deep learning Super resolution Object detection |
| url | https://peerj.com/articles/cs-2860.pdf |
| work_keys_str_mv | AT subhrangshuadhikary fishspeciesidentificationonlowresolutionastudywithenhancedsuperresolutiongenerativeadversarialnetworkesrganyoloandvgg16 AT saikatbanerjee fishspeciesidentificationonlowresolutionastudywithenhancedsuperresolutiongenerativeadversarialnetworkesrganyoloandvgg16 AT rajanisingh fishspeciesidentificationonlowresolutionastudywithenhancedsuperresolutiongenerativeadversarialnetworkesrganyoloandvgg16 AT ashutoshdhardwivedi fishspeciesidentificationonlowresolutionastudywithenhancedsuperresolutiongenerativeadversarialnetworkesrganyoloandvgg16 |