Title: Deep learning for apple diseases: classification and identification

Authors: Asif Iqbal Khan; S.M.K. Quadri; Saba Banday

Addresses: Department of Computer Science, Jamia Millia Islamia University, New Delhi, India ' Department of Computer Science, Jamia Millia Islamia University, New Delhi, India ' Department of Pathology, Sher-i-Kashmir University of Agricultural Sciences, Shalimar, Srinagar, J&K, India

Abstract: Diseases cause huge economic loss to the apple industry every year. Timely identification of these diseases is challenging for the farmers as the symptoms produced by different diseases may be similar and sometimes present simultaneously. This paper is an attempt to provide the timely and accurate identification of apple diseases from plant leaves. In this study, we propose a deep learning approach for identification and classification of apple diseases. First part of this study is dataset creation which includes data collection and labelling. Next, we train a convolutional neural network (CNN) model on the prepared dataset for automatic classification of apple diseases. CNNs are end-to-end learning algorithms which perform automatic feature extraction and learn complex features directly from raw images, making them suitable for a wide variety of computer vision tasks. The model parameters were initialised using transfer learning enabling the proposed model to achieve 97.18% accuracy on the prepared dataset.

Keywords: deep learning; apple disease classification; convolutional neural network; CNN.

DOI: 10.1504/IJCISTUDIES.2021.113831

International Journal of Computational Intelligence Studies, 2021 Vol.10 No.1, pp.1 - 12

Received: 06 Apr 2020
Accepted: 06 Jun 2020
Published online: 31 Mar 2021 *