CARDAMOM PLANT DISEASE DETECTION USING ROBOT

Abstract

The cardamom plant has various types of diseases. Among these diseases, leaf blight and leaf spot cause too much damage. Early detection and prevention of these diseases is done with the help of a robot. In this approach, we proceed in several steps. i.e. image collection, image processing, machine learning, image classification and fertilizer design. Cardamom is the queen of spices. It is indigenously grown in the evergreen forests of Karnataka, Kerala, Tamil Nadu and the north-eastern states of India. India is the third largest producer of cardamom. Plant diseases have a disastrous effect on the safety of food production; they reduce the eminence and quantity of agricultural products. Plant diseases can cause significantly high losses or no harvest in severe cases. Various diseases and pests affect the growth of cardamom plants at different stages and crop yields. This study focused on two cardamom plant diseases, Colletotrichum Blight and Phyllosticta Leaf Spot of cardamom and three grape diseases, Black Rot, ESCA and Isariopsis Leaf Spot. Various methods have been proposed to detect plant diseases and deep learning has become the preferred method due to its spectacular success. In this study, U2-Net was used to remove the unwanted background of the input image by selecting multi-scale features. This work proposes an approach for disease detection of cardamom plants using the EfficientNetV2 model. A comprehensive set of experiments was conducted to investigate the performance of the proposed approach and compare it with other models such as EfficientNet and Convolutional Neural Network (CNN).