Plant disease detection using GLCM feature extractor and voting classification approach

Agriculture productivity has a large effect on the economy of the country. Agriculture productivity can be increased by the detect plant disease at an early stage. The automated techniques play an important role to detect diseases at an early stage and detection will be accurate. The automated techniques detect the disease when the symptoms start appearing on the leave of the plant. This paper presents an automated technique for plant disease detection which is based on the four operations which are pre-processing, segmentation, feature extraction, and classification. This paper also covers a literature survey of various techniques which are already proposed by the authors. The symptoms analysis of the plant leaf is done using the GLCM algorithm and classification of the disease is done using voting classification which are key aspects of this paper. The voting classification method is the combination of the decision trees, support vector machines, k nearest neighbour methods which will improvise the accuracy of the disease detection at an early stage. Copyright (c) 2022 Elsevier Ltd. All rights reserved.Selection and peer-review under responsibility of the scientific committee of the International Conference on Artificial Intelligence & Energy Systems.