0% found this document useful (0 votes)
2 views

Automatic_Fruit_Classification_Using_Deep_Learning

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
2 views

Automatic_Fruit_Classification_Using_Deep_Learning

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 1

The document you've provided is an extensive research paper titled "Automatic Fruit

Classification Using Deep Learning for Industrial Applications," published in the


IEEE Transactions on Industrial Informatics, Vol. 15, No. 2, February 2019. The
authors, M. Shamim Hossain, Muneer Al-Hammadi, and Ghulam Muhammad, delve into the
application of deep learning for classifying fruits, a critical task in various
industrial settings. They introduce an efficient framework utilizing two different
deep learning architectures for this purpose: a light model consisting of six
convolutional neural network (CNN) layers, and a more complex model based on a
fine-tuned Visual Geometry Group-16 (VGG-16) pretrained deep learning model.

The paper highlights the importance of fruit classification in supermarkets and


dietary management, noting the challenges posed by the similarity in appearance
among different fruit species and the variability within a single species. To
address these challenges, the authors used two color image datasets, achieving
classification accuracies of 99.49% and 99.75% on a simple dataset (dataset 1) with
the light and VGG-16 models, respectively. On a more complex dataset (dataset 2),
the models achieved accuracies of 85.43% and 96.75%, respectively.

The researchers also compare their framework's performance with existing methods,
demonstrating superior accuracy on the supermarket produce dataset. They conclude
by suggesting future research directions, including expanding the evaluation to
more fruit and vegetable species and exploring the impact of different parameters
on model performance.

This paper contributes significantly to the field of industrial informatics and


computer vision, particularly in the context of automating fruit classification in
industrial applications using deep learning techniques.

You might also like