A New Deep Learning Model for the Classification of Poisonous and Edible Mushrooms Based on Improved AlexNet Convolutional Neural Network

The difficulty involved in distinguishing between edible and poisonous mushrooms stems from their similar appearances. In this study, we attempted to classify five common species of found Thailand, Inocybe rimosa, Amanita phalloides, citrina, Russula delica, Phaeogyroporus portentosus, using the convolutional neural network (CNN) region (R-CNN). This study was motivated by yearly death toll eating Thailand. research, a method for classification proposed testing time accuracy three pretrained models, AlexNet, ResNet-50, GoogLeNet, were compared. model reduce duration required training while retaining high level accuracy. mushroom experiments CNN R-CNN, demonstrated levels 98.50% 95.50%, respectively.