NORMA eResearch @NCI Library

Classifying different sea species using Deep Learning techniques

Desai, Niranjan Pramod (2022) Classifying different sea species using Deep Learning techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (713kB) | Preview


Due to all the nutrients and delicious flavors that seafood contains, seaside nations use it as the major component of their diet. To satisfy their demand, the seafood industry must produce and offer high-quality seafood. Each year, the globe produces 200 million tonnes of seafood and fish. The current level of fish collection is unsustainable due to the overfishing of fish populations. Four times as many fish and marine foods are produced now as there were fifty years ago. We have developed an innovative method for preventing overfishing that makes use of deep learning and machine learning techniques. It allows us to keep the fish we want while not killing and returning undesired unwanted fish to the water. In this study, we will classify nine distinct fish species utilizing 430 photographs in total. Two models were used in this study: MOBILENET V2 and VGG16. MOBILENET V2 provided a test loss of 0.12303 and an accuracy of 96.51 percent, while vgg16 provided a test loss of 0.39825 and an accuracy of 88.37 percent. To improve the accuracy of both models, we have used data augmentation and model tuning strategies. The purpose of this research is to preserve natural habitat and solve the problem of identifying the fishes, which has been always a challenge because of the scarcity of data sources and the quality of available images. This study has also demonstrated that MOBILENET V2 can still provide good accuracy even with a less dataset.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
S Agriculture > SH Aquaculture. Fisheries. Angling
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 24 Jan 2023 11:21
Last Modified: 03 Mar 2023 16:47

Actions (login required)

View Item View Item