Automated Fruit Classification Using Deep Convolutional Neural Network

John Jowil D. Orquia; El Jireh  Bibangco

doi:10.52006/main.v3i2.188

John Jowil D. Orquia University of Antique, Antique, Philippines https://orcid.org/0000-0001-8729-0247
El Jireh Bibangco University of Negros Occidental-Recoletos, Bacolod City, Philippines https://orcid.org/0000-0002-2298-7665

DOI: https://doi.org/10.52006/main.v3i2.188

Keywords: Artificial Intelligence, Deep Learning, Deep Convolutional Neural Network, Fruit Classification, Experimental-Comparative, Philippines

Abstract

Manual Fruit classification is the traditional way of classifying fruits. It is manual contact-labor that is time-consuming and often results in lesser productivity, inconsistency, and sometimes damaging the fruits (Prabha & Kumar, 2012). Thus, new technologies such as deep learning paved the way for a faster and more efficient method of fruit classification (Faridi & Aboonajmi, 2017). A deep convolutional neural network, or deep learning, is a machine learning algorithm that contains several layers of neural networks stacked together to create a more complex model capable of solving complex problems. The utilization of state-of-the-art pre-trained deep learning models such as AlexNet, GoogLeNet, and ResNet-50 was widely used. However, such models were not explicitly trained for fruit classification (Dyrmann, Karstoft, & Midtiby, 2016). The study aimed to create a new deep convolutional neural network and compared its performance to fine-tuned models based on accuracy, precision, sensitivity, and specificity.