Detection and Measurement System for Button Mushrooms using Convolutional Neural Network

Abstract

In Malaysia, the button mushroom is recognized as a vegetable with high nutritional value and is easy to grow. To observe the mushrooms' growth, farmers are frequently required to check the crops, which are time-consuming and waste of human resources. Therefore, a detection and measurement system for button mushrooms has been developed based on image processing techniques using the convolutional neural network (CNN) algorithm model known as YOLOv4. Based on the results obtained from the preliminary experiments, the detection and measurement system demonstrate high accuracy in locating position of each button mushroom with only 5% deviation error in predicting the size of each button mushroom.