Bimonthly    Since 1986
ISSN 1004-9037
Publication Details
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
 
   
      09 May 2023, Volume 38 Issue 3
    Article

    FRUIT DISEASE CATEGORISATION BASED ON CONVOLUTIONAL NEURAL NETWORKS
    A S Lalitha1, K Nageswararao2
    Journal of Data Acquisition and Processing, 2023, 38 (3): 58-65 . 

    Abstract

    Applications of artificial intelligence have become very relevant in all sectors. This is especially true in agriculture, where it is used to protect crops from disease and to take appropriate measures to control the disease at an early stage. In this study, a model is used that employs deep learning techniques to classify fruits into different types: diseased and healthy. This involves the development of a Convolutional Neural Network (CNN) model to classify fruits into diseased and healthy in two different classes, considering each fruit individually for three different fruits. It was found that the deep learning model used in this research work has higher accuracy when compared with other existing models considering the same data set. The proposed deep learning model was compared with different pre-trained models LeNet5 and AlexNet trained on the same dataset. It was found that the proposed CNN model achieved over 95% accuracy for each of the fruits for different classes. Moreover, the developed CNN model achieved higher accuracy than other existing models, indicating the usefulness of CNNs for fruit disease classification with high accuracy.

    Keyword

    Agriculture, Convolutional Neural Network, Deep Learning, Fruit disease detection, AlexNet, LeNet5.


    PDF Download (click here)

SCImago Journal & Country Rank

ISSN 1004-9037

         

Home
Editorial Board
Author Guidelines
Subscription
Journal of Data Acquisition and Processing
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: info@sjcjycl.cn
 
  Copyright ©2015 JCST, All Rights Reserved