Authors :
Prabhat Kumar Singh; Pawan Kumar; Abshar Imam
Volume/Issue :
Volume 7 - 2022, Issue 3 - March
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3IBwJVG
DOI :
https://doi.org/10.5281/zenodo.6386609
Abstract :
Insect numbers are dwindling over the world,
and some species have gone extinct in the past.
Exploration of seldom seen Insect species has therefore
become a difficult endeavor for Entomologists and Insect
Watchers. We created an Android application based on
deep learning to assist users in recognizing 280 different
insect species, making insect categorization much more
user-friendly. We employ Convolutional Neural
Networks (CNN) pre-trained on ImageNet Dataset as
freeze layers of the network in this article, then train the
final output layer, which has 280 separate classes. The
accuracy of CNN models such as EfficientNet-lite0,
InceptionV3, Xception, ResNet-50, MobilenetV2, and
InceptionResNetV2 has been evaluated, and the mobile
app's operation has been discussed. Maximum train data
accuracy of 99.81 percent and test data accuracy of 98.62
percent is accomplished.
Keywords :
Transfer Learning, Classification of Bird Species, Deep Learning, Recognition of Image, CNN, Android Application
Insect numbers are dwindling over the world,
and some species have gone extinct in the past.
Exploration of seldom seen Insect species has therefore
become a difficult endeavor for Entomologists and Insect
Watchers. We created an Android application based on
deep learning to assist users in recognizing 280 different
insect species, making insect categorization much more
user-friendly. We employ Convolutional Neural
Networks (CNN) pre-trained on ImageNet Dataset as
freeze layers of the network in this article, then train the
final output layer, which has 280 separate classes. The
accuracy of CNN models such as EfficientNet-lite0,
InceptionV3, Xception, ResNet-50, MobilenetV2, and
InceptionResNetV2 has been evaluated, and the mobile
app's operation has been discussed. Maximum train data
accuracy of 99.81 percent and test data accuracy of 98.62
percent is accomplished.
Keywords :
Transfer Learning, Classification of Bird Species, Deep Learning, Recognition of Image, CNN, Android Application