Home / Current Issue / Paper 1705453
Jellyfish Recognition by Using Convolutional Neural Networks and Support Vector Machine
Subject area: Science,Engineering and Technology · Area of research: Machine Learning , Deep Learning
Abstract
This research presents a comprehensive approach to jellyfish recognition employing Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). The study utilizes a CNN for deep learning-based feature extraction from images, leveraging transfer learning with the MobileNetV2 architecture. The CNN is trained on a diverse dataset of jellyfish species, using an Image Data Generator for data augmentation. Simultaneously, a traditional machine learning model, SVM, is employed to evaluate image features extracted via resizing and flattening. The SVM model is trained on a dataset comprising three distinct jellyfish species. Experimental results demonstrate the effectiveness of both models, with the CNN achieving high accuracy on the training dataset and the SVM demonstrating robust performance on a separate test set. Furthermore, a comparative analysis between the CNN and SVM models underscores the strengths and limitations of each approach. This integrated methodology offers a versatile solution for jellyfish recognition, combining the interpretability of SVMs with the representational power of CNNs.
Keywords
Jellyfish Recognition, Convolutional Neural Networks, Support Vector Machines, Image Classification, Comparative Analysis
References
[1] Fagerlund S. Bird species recognition using support vector machines. EURASIP Journal on Advances in Signal Processing. 2007 Dec; 2007:1-8.
[2] Tattersall I. Species recognition in human paleontology. Journal of Human Evolution. 1986 Mar 1;15(3):165-75.
[3] Chen G, Han TX, He Z, Kays R, Forrester T. Deep convolutional neural network-based species recognition for wild animal monitoring. In2014 IEEE international conference on image processing (ICIP) 2014 Oct 27 (pp. 858-862). IEEE.
[4] Fujita K. Species recognition by five macaque monkeys. Primates. 1987 Jul; 28:353-66.
[5] Storbeck F, Daan B. Fish species recognition using computer vision and a neural network. Fisheries Research. 2001 Apr 1;51(1):11-5.
[6] Somervuo P, Harma A, Fagerlund S. Parametric representations of bird sounds for automatic species recognition. IEEE Transactions on Audio, Speech, and Language Processing. 2006 Oct 16;14(6):2252-63.
[7] Filho PL, Oliveira LS, Nisgoski S, Britto AS. Forest species recognition using macroscopic images. Machine Vision and Applications. 2014 May; 25:1019-31.
[8] Pu R. Broadleaf species recognition with in situ hyperspectral data. International Journal of Remote Sensing. 2009 Jun 10;30(11):2759-79.
How to cite this paper
@article{1705453,
author = {Aanchal Manikchandra Yadav, Mithilesh Vishwakarma, Riya Ganesh Sevekar},
title = {Jellyfish Recognition by Using Convolutional Neural Networks and Support Vector Machine},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {7},
number = {8},
pages = {10-16},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1705453.pdf},
abstract = {This research presents a comprehensive approach to jellyfish recognition employing Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). The study utilizes a CNN for deep learning-based feature extraction from images, leveraging transfer learning with the MobileNetV2 architecture. The CNN is trained on a diverse dataset of jellyfish species, using an Image Data Generator for data augmentation. Simultaneously, a traditional machine learning model, SVM, is employed to evaluate image features extracted via resizing and flattening. The SVM model is trained on a dataset comprising three distinct jellyfish species. Experimental results demonstrate the effectiveness of both models, with the CNN achieving high accuracy on the training dataset and the SVM demonstrating robust performance on a separate test set. Furthermore, a comparative analysis between the CNN and SVM models underscores the strengths and limitations of each approach. This integrated methodology offers a versatile solution for jellyfish recognition, combining the interpretability of SVMs with the representational power of CNNs.},
keywords = {Jellyfish Recognition, Convolutional Neural Networks, Support Vector Machines, Image Classification, Comparative Analysis},
month = {February},
}