Fruit Image Classification Using Convolutional Neural Networks

Fruit Image Classification Using Convolutional Neural Networks

Shawon Ashraf (North South University, Dhaka, Bangladesh), Ivan Kadery (North South University, Dhaka, Bangladesh), Md Abdul Ahad Chowdhury (North South University, Dhaka, Bangladesh), Tahsin Zahin Mahbub (North South University, Dhaka, Bangladesh) and Rashedur M. Rahman (Department of Electrical Engineering and Computer Science, North South University, Dhaka, Bangladesh)
Copyright: © 2019 |Pages: 20
DOI: 10.4018/IJSI.2019100103
OnDemand PDF Download:
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Convolutional neural networks (CNN) are the most popular class of models for image recognition and classification task nowadays. Most of the superstores and fruit vendors resort to human inspection to check the quality of the fruits stored in their inventory. However, this process can be automated. We propose a system that can be trained with a fruit image dataset and then detect whether a fruit is rotten or fresh from an input image. We built the initial model using the Inception V3 model and trained with our dataset applying transfer learning.
Article Preview
Top

CNN techniques are more successful than traditional machine learning techniques because of their superior predicting capabilities when it comes to image classification. Makantasis, Protopapadakis, Doulamis, Doulamis, and Loupos (2015) used a Convolutional Neural Network based system to inspect tunnels. They compared their proposed system with other established techniques and showed that Convolutional Neural Network outperformed all other techniques.

Affonso et al. (2017) used CNN and many machine learning (ML) techniques to predict the quality of wooden boards samples using their images. Here they compared the performances of ML techniques with CNN. In their work the dimensionality of the dataset was low (only 2 dimensions), that is why CNN performed worse compared to other ML techniques.

Wang, Yang, Mao, Huang, Huang and Xu (2016) used convolutional neural networks with recurrent neural networks to make a multi-label image classifier system. Their work took the route of employing convolutional neural network and recurrent neural network to model the label co-occurrence dependency in a joint image/label embedding space.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2021): 1 Released, 3 Forthcoming
Volume 8: 4 Issues (2020)
Volume 7: 4 Issues (2019)
Volume 6: 4 Issues (2018)
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing