Mushroom Recognition Using Neural Network

Johaira U. Lidasan, Martina P. Tagacay
2018 Zenodo  
An application would be beneficial if it is real time and could give its users enough information. This would be of greater advantage for mobile applications. Mushroom Recognition using Neural Network is a mobile-based application that combined the power of neural network with image processing to recognize mushroom image based on its order and family and if it is edible or inedible/poisonous. It is a multi-class classification program that recognizes mushroom image from 3 orders and 8 families
more » ... ers and 8 families defined in this research. The application used the GrabCut algorithm for image segmentation and Probabilistic Neural Network (PNN) as its classifier that trains and classifies the mushroom image. This application used 133 mushroom images as its training data and obtained an accuracy rate of 92%. This could be used as an educational tool both for Biology students and people in IT fields. It could also help mycologists identify wild mushrooms.
doi:10.5281/zenodo.1467659 fatcat:rcaklmmkbncybp4yyv4dpr7wby