Track: High School STEM Poster Competition

Abstract

This study proposes a method for determining the freshness of fruits using a Convolutional Neural Network (CNN) model. Spoiled fruits often exhibit minimal visual changes, making them difficult to distinguish with the naked eye. To address this, an algorithm was developed that utilizes a CNN model to automatically learn features such as color, texture, and shape of the fruits, and determine their freshness.

The experiment utilized image datasets of both fresh and spoiled fruits, including various types such as apples and oranges. The structure of the CNN model consists of convolutional layers, pooling layers, and fully connected layers, designed to determine the freshness of the fruits in the final output.

The experimental results demonstrated that the CNN model could identify spoiled fruits with an accuracy of over 92%. This indicates that the proposed method provides an objective and accurate way to determine fruit freshness compared to traditional visual inspection methods. The suggested technology is expected to be applicable in various fields such as fruit quality control and distribution process monitoring.

Keywords

CNN, Convolutional Neural Network, Classifying Spoiled Fruits, fruits and AI