A comparative study on image-based snake identification using machine learning

Abstract Automated snake image identification is important from different points of view, most importantly, snake bite management. Auto-identification of snake images might help the avoidance of venomous snakes and also providing better treatment for patients. In this study, for the first time, it’s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mahdi Rajabizadeh, Mansoor Rezghi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7341c93c3cce4e6db0be564de287740a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7341c93c3cce4e6db0be564de287740a
record_format	dspace
spelling	oai:doaj.org-article:7341c93c3cce4e6db0be564de287740a2021-12-02T19:17:05ZA comparative study on image-based snake identification using machine learning10.1038/s41598-021-96031-12045-2322https://doaj.org/article/7341c93c3cce4e6db0be564de287740a2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96031-1https://doaj.org/toc/2045-2322Abstract Automated snake image identification is important from different points of view, most importantly, snake bite management. Auto-identification of snake images might help the avoidance of venomous snakes and also providing better treatment for patients. In this study, for the first time, it’s been attempted to compare the accuracy of a series of state-of-the-art machine learning methods, ranging from the holistic to neural network algorithms. The study is performed on six snake species in Lar National Park, Tehran Province, Iran. In this research, the holistic methods [k-nearest neighbors (kNN), support vector machine (SVM) and logistic regression (LR)] are used in combination with a dimension reduction approach [principle component analysis (PCA) and linear discriminant analysis (LDA)] as the feature extractor. In holistic methods (kNN, SVM, LR), the classifier in combination with PCA does not yield an accuracy of more than 50%, But the use of LDA to extract the important features significantly improves the performance of the classifier. A combination of LDA and SVM (kernel = 'rbf') is achieved to a test accuracy of 84%. Compared to holistic methods, convolutional neural networks show similar to better performance, and accuracy reaches 93.16% using MobileNetV2. Visualizing intermediate activation layers in VGG model reveals that just in deep activation layers, the color pattern and the shape of the snake contribute to the discrimination of snake species. This study presents MobileNetV2 as a powerful deep convolutional neural network algorithm for snake image classification that could be used even on mobile devices. This finding pave the road for generating mobile applications for snake image identification.Mahdi RajabizadehMansoor RezghiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Mahdi Rajabizadeh Mansoor Rezghi A comparative study on image-based snake identification using machine learning
description	Abstract Automated snake image identification is important from different points of view, most importantly, snake bite management. Auto-identification of snake images might help the avoidance of venomous snakes and also providing better treatment for patients. In this study, for the first time, it’s been attempted to compare the accuracy of a series of state-of-the-art machine learning methods, ranging from the holistic to neural network algorithms. The study is performed on six snake species in Lar National Park, Tehran Province, Iran. In this research, the holistic methods [k-nearest neighbors (kNN), support vector machine (SVM) and logistic regression (LR)] are used in combination with a dimension reduction approach [principle component analysis (PCA) and linear discriminant analysis (LDA)] as the feature extractor. In holistic methods (kNN, SVM, LR), the classifier in combination with PCA does not yield an accuracy of more than 50%, But the use of LDA to extract the important features significantly improves the performance of the classifier. A combination of LDA and SVM (kernel = 'rbf') is achieved to a test accuracy of 84%. Compared to holistic methods, convolutional neural networks show similar to better performance, and accuracy reaches 93.16% using MobileNetV2. Visualizing intermediate activation layers in VGG model reveals that just in deep activation layers, the color pattern and the shape of the snake contribute to the discrimination of snake species. This study presents MobileNetV2 as a powerful deep convolutional neural network algorithm for snake image classification that could be used even on mobile devices. This finding pave the road for generating mobile applications for snake image identification.
format	article
author	Mahdi Rajabizadeh Mansoor Rezghi
author_facet	Mahdi Rajabizadeh Mansoor Rezghi
author_sort	Mahdi Rajabizadeh
title	A comparative study on image-based snake identification using machine learning
title_short	A comparative study on image-based snake identification using machine learning
title_full	A comparative study on image-based snake identification using machine learning
title_fullStr	A comparative study on image-based snake identification using machine learning
title_full_unstemmed	A comparative study on image-based snake identification using machine learning
title_sort	comparative study on image-based snake identification using machine learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7341c93c3cce4e6db0be564de287740a
work_keys_str_mv	AT mahdirajabizadeh acomparativestudyonimagebasedsnakeidentificationusingmachinelearning AT mansoorrezghi acomparativestudyonimagebasedsnakeidentificationusingmachinelearning AT mahdirajabizadeh comparativestudyonimagebasedsnakeidentificationusingmachinelearning AT mansoorrezghi comparativestudyonimagebasedsnakeidentificationusingmachinelearning
_version_	1718376918786506752

A comparative study on image-based snake identification using machine learning

Ejemplares similares