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.
Highlights
Automated snake image identification is important from different points of view, most importantly, snake bite management
For the first time, a series of state-of-the-art machine learning algorithms were compared in the classification of six snake species of Lar National Park
In holistic methods, performance of the classifiers over the raw images’ data were not satisfying and the test accuracy did not exceed 50%
Summary
Automated snake image identification is important from different points of view, most importantly, snake bite management. 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. 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. Efforts have been made for image-based snake classification using ML7–10 In these researches a range of machine learning methods we used, from traditional ML classifiers, including k-nearest neighbors (hereafter kNN) and support vector machine (hereafter SVM), to the state of the art neural
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
