CSUniversity San Bernardino
CLASSIFICATION OF LARGE SCALE FISH DATASET BY DEEP NEURAL NETWORKS
Abstract
dc:description.abstractThe development of robust and efficient fish classification systems has become essential to preventing the rapid depletion of aquatic resources and building conservation strategies. A deep learning approach is proposed here for the automated classification of fish species from underwater images. The proposed methodology leverages state-of-the-art deep neural networks by applying the compact convolutional transformer (CCT) architecture, which is famous for faster training and lower computational cost. In CCT, data augmentation techniques are employed to enhance the variability of the training data, reducing overfitting and improving generalization. The preliminary outcomes of our proposed method demonstrate a promising accuracy level of 100% over the Large-scale fish dataset, with the potential for real-time deployment in aquatic monitoring systems. Furthermore, this work proposes avenues for future research in the domain of fish classification.
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Computer Science
- Level thesis:degree_level
- Project
- Discipline thesis:degree_discipline
- School of Computer Science and Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Adapa, Priyanka
- Contributors dc:contributor
-
- JIN JENNIFER
Subjects
dc:subject × 12- The development of robust and efficient fish classification systems has become essential to preventing the rapid depletion of aquatic resources and building conservation strategies. A deep learning approach is proposed here for the automated classification of fish species from underwater images. The proposed methodology leverages state-of-the-art deep neural networks by applying the compact convolutional transformer (CCT) architecture
- which is famous for faster training and lower computational cost. In CCT
- data augmentation techniques are employed to enhance the variability of the training data
- reducing overfitting and improving generalization. The preliminary outcomes of our proposed method demonstrate a promising accuracy level of 100% over the Large-scale fish dataset
- with the potential for real-time deployment in aquatic monitoring systems. Furthermore
- this work proposes avenues for future research in the domain of fish classification.
- Animal Studies
- Computer and Systems Architecture
- Food Studies
- Hardware Systems
- Other Computer Engineering
- Systems Science
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://scholarworks.lib.csusb.edu/etd/1820