Comparative Study on Reliability of Transfer Learning to Classify Plant-Based Diseases
N Rohan Sai1, T Sudarshan Rao2, G. L. Aruna Kumari3

1N Rohan Sai*, Computer Science and Engineering, GITAM (Deemed to University), Visakhapatnam, India.
2T Sudarshan Rao, Computer Science and Engineering, GITAM (Deemed to University), Hyderabad, India.
3G. L. Aruna Kumari, Assistant Professor, Computer Science and Engineering, GITAM (Deemed to University), Visakhapatnam, India. 
Manuscript received on August 19, 2021. | Revised Manuscript received on August 23, 2021. | Manuscript published on August 30, 2021. | PP: 154-160 | Volume-10 Issue-6, August 2021. | Retrieval Number: 100.1/ijeat.F30800810621 | DOI: 10.35940/ijeat.F3080.0810621
Open Access | Ethics and  Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: One of the essential factors contributing to a plant’s growth is identifying and preventing diseases in the early stages. Healthy plants are essential for a rich production. Recent advances in Deep learning – a subset of Artificial Intelligence and Machine Learning are playing a pivotal role in solving image classification problems and can be applied to the agricultural sector for crop surveillance and early anomaly identification. For this research, we used an open-source dataset of leaf images divided into three classes, two of which are the most common disease types found on many crops; the graphical characterizations for the three classes are images of leaves with Powdery Residue, images of leaves with Rusty Spots, and images of Healthy leaves. The primary objective of this research is to present a pre-trained ImageNet network architecture that is well suited for dealing with plant-based data, even when sample sizes collected are limited. We used different convolutional neural network-based architectures such as InceptionV3, MobileNetV2, Xception, VGG16, and VGG19 to classify plant leaf images with visually different representations of each disease. Xception, MobileNetV2, and DenseNet had a considerable advantage over all the performance metrics recorded among the other networks trained.
Keywords: Artificial Intelligence, Deep Learning, Neural Networks, Transfer Learning
Scope of the Article: Deep Learning