Global ETD Search

A Study on Deepsea Fish Detection Using Convolutional Neural Networks

Madari, Poojitha Priyadarshini2026

… and deep-sea fish detection using the DeepFish dataset. A pretrained ResNet-50 model attained a validation accuracy of 82.8% for multi-class habitat classification, demonstrating robust performance in most habitats based on 6,517 images, although exhibiting lower recall for visually …

usm Repository record for A Study on Deepsea Fish Detection Using Convolutional Neural Networks (opens in a new tab)