Scopus Indexed Publications

Paper Details


Title
Recognition of mango leaf disease using convolutional neural network models: A transfer learning approach
Author
, Anik Pramanik, Narayan Ranjan Chakraborty , Shah Md. Tanvir Siddiquee,
Email
Abstract

The acknowledgment of plant diseases assumes an indispensable part in taking infectious prevention measures to improve the quality and amount of harvest yield. Mechanization of plant diseases is a lot advantageous as it decreases the checking work in an enormous cultivated area where mango is planted to a huge extend. Leaves being the food hotspot for plants, the early and precise recognition of leaf diseases is significant. This work focused on grouping and distinguishing the diseases of mango leaves through the process of CNN. DenseNet201, InceptionResNetV2, InceptionV3, ResNet50, ResNet152V2, and Xception all these models of CNN with transfer learning techniques are used here for getting better accuracy from the targeted data set. Image acquisition, image segmentation, and features extraction are the steps involved in disease detection. Different kinds of leaf diseases which are considered as the class for this work such as anthracnose, gall machi, powdery mildew, red rust are used in the dataset consisting of 1500 images of diseased and also healthy mango leaves image data another class is also added in the dataset. We have also evaluated the overall performance matrices and found that the DenseNet201 outperforms by obtaining the highest accuracy as 98.00% than other models.


Keywords
Classification; DenseNet201; Mango leaf; Neural network
Journal or Conference Name
Indonesian Journal of Electrical Engineering and Computer Science
Publication Year
2021
Indexing
scopus