A study on image processing techniques and deep learning techniques for insect identification

Automatic identification of insects and diseases has attracted researchers for the last few years. Researchers have suggested several algorithms to get around problems manually identifying pests. Image processing techniques deep convolution neural networks can overcome challenges manual insect classification. This work focused on optimizing assessing convolutional identification. AlexNet, MobileNetv2, ResNet-50, ResNet-101, GoogleNet, InceptionV3, SqueezeNet, ShuffleNet, DenseNet201, VGG-16 VGG-19 are architectures evaluated three different datasets. In our experiments, DenseNet 201 performed well with highest test accuracy. Regarding training time, AlexNet well, but MobileNet better alternatives small architecture.