Home / Current Issue / Paper 1705428
Eco-Smart Elephant Recognition: A Dual Strategy with CNN Classification and SVM Feature Extraction
Subject area: Science,Engineering and Technology · Area of research: Machine Learning , Deep Learning
Abstract
Our research delves into the multifaceted realm of elephant recognition, employing diverse methodologies to address the challenges posed by image classification and feature extraction. We explore Convolutional Neural Networks (CNNs) for image classification, achieving an impressive 87.50% accuracy in discerning elephant subtypes. Furthermore, we investigate Support Vector Machines (SVMs) in conjunction with the VGG16 model for feature extraction, providing an alternative approach with a commendable 76% accuracy. Our project leverages these techniques to distinguish between African, Asian, and Indian elephants, contributing to wildlife conservation efforts. Through extensive experimentation, we showcase the strengths and limitations of each approach, offering valuable insights for researchers and practitioners in the field.
Keywords
Elephant Recognition, CNN, SVM, Wildlife Conservation, Image Classification
How to cite this paper
@article{1705428,
author = {Aman Mishra, Mithilesh Vishwakarma, Nihal Baranwal},
title = {Eco-Smart Elephant Recognition: A Dual Strategy with CNN Classification and SVM Feature Extraction},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {7},
number = {7},
pages = {351-357},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1705428.pdf},
abstract = {Our research delves into the multifaceted realm of elephant recognition, employing diverse methodologies to address the challenges posed by image classification and feature extraction. We explore Convolutional Neural Networks (CNNs) for image classification, achieving an impressive 87.50% accuracy in discerning elephant subtypes. Furthermore, we investigate Support Vector Machines (SVMs) in conjunction with the VGG16 model for feature extraction, providing an alternative approach with a commendable 76% accuracy. Our project leverages these techniques to distinguish between African, Asian, and Indian elephants, contributing to wildlife conservation efforts. Through extensive experimentation, we showcase the strengths and limitations of each approach, offering valuable insights for researchers and practitioners in the field.},
keywords = {Elephant Recognition, CNN, SVM, Wildlife Conservation, Image Classification},
month = {January},
}