A Comparison Study of Deep Convolutional Neural Networks for the Classification of Brazilian Savannah Pollen Grains: Preliminary Results
Keyword(s):
The classification of pollen grains images are currently done manually and visually, being a weariful task and predisposed to mistakes due to human exhaustion. In this paper, the authors introduce an automatic classification of 55 different pollen grain classes, using convolutional neural networks. Different architectures and hyperparameters were used to improve the classification result. Using the networks VGG16, VGG19, and InceptionV3, were obtained accuracy rates over 93.58%.
2020 ◽
Vol 2020
(10)
◽
pp. 28-1-28-7
◽
2020 ◽
Vol 16
(9)
◽
pp. 1332
Training Deep Convolutional Neural Networks for Land–Cover Classification of High-Resolution Imagery
2017 ◽
Vol 14
(4)
◽
pp. 549-553
◽
2018 ◽
Vol 17
(2)
◽
pp. e1232
◽
2020 ◽
pp. 154-165
2021 ◽