Home / Current Issue / Paper 1705315
Integrated Approach for Crab Species Classification: Comparative Analysis of SVM and CNN for Accuracy Assessment
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Deep Learning
Abstract
Crab species classification is a crucial task in marine biology and ecological studies. This research presents an integrated approach using Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) for the accurate classification of crab species. The study leverages SVM, a classical machine learning algorithm, and CNN, a state-of-the-art deep learning model, to explore their effectiveness in distinguishing between different crab species based on image data. The research employs pre-trained models such as MobileNetV2 and VGG16 for feature extraction and investigates their performance in predicting crab species from images. Additionally, a custom CNN model is developed and trained on a dataset comprising three crab species: Callinectes sapidus, king crab, and sally lightfoot crab. The models are evaluated and compared based on their accuracy in classifying images from a real-world crab dataset.
Keywords
Crab species classification, SVM vs CNN, Image-based identification, Marine ecology, Deep learning for biodiversity, Comparative accuracy 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] 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.
[3] Storbeck F, Daan B. Fish species recognition using computer vision and a neural network. Fisheries Research. 2001 Apr 1;51(1):11-5.
[4] Hafemann LG, Oliveira LS, Cavalin P. Forest species recognition using deep convolutional neural networks. In2014 22Nd international conference on pattern recognition 2014 Aug 24 (pp. 1103-1107). IEEE.
[5] Fujita K. Species recognition by five macaque monkeys. Primates. 1987 Jul; 28:353-66.
[6] Gogul I, Kumar VS. Flower species recognition system using convolution neural networks and transfer learning. In2017 fourth international conference on signal processing, communication and networking (ICSCN) 2017 Mar 16 (pp. 1-6). IEEE.
[7] Zhang S, Huang W, Huang YA, Zhang C. Plant species recognition methods using leaf image: Overview. Neurocomputing. 2020 Sep 30; 408:246-72.
[8] Deep BV, Dash R. Underwater fish species recognition using deep learning techniques. In2019 6th International Conference on Signal Processing and Integrated Networks (SPIN) 2019 Mar 7 (pp. 665-669). IEEE.
How to cite this paper
@article{1705315,
author = {Amit Kumar Pandey, Dr. Santosh Singh, Kalash Seetharam Shetty, Ashwani Kumar Mishra, Bipin Yadav},
title = {Integrated Approach for Crab Species Classification: Comparative Analysis of SVM and CNN for Accuracy Assessment},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {7},
number = {6},
pages = {228-234},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/17053151.pdf},
abstract = {Crab species classification is a crucial task in marine biology and ecological studies. This research presents an integrated approach using Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) for the accurate classification of crab species. The study leverages SVM, a classical machine learning algorithm, and CNN, a state-of-the-art deep learning model, to explore their effectiveness in distinguishing between different crab species based on image data. The research employs pre-trained models such as MobileNetV2 and VGG16 for feature extraction and investigates their performance in predicting crab species from images. Additionally, a custom CNN model is developed and trained on a dataset comprising three crab species: Callinectes sapidus, king crab, and sally lightfoot crab. The models are evaluated and compared based on their accuracy in classifying images from a real-world crab dataset.},
keywords = {Crab species classification, SVM vs CNN, Image-based identification, Marine ecology, Deep learning for biodiversity, Comparative accuracy analysis.},
month = {December},
}