A Hybrid Application of Quantum Computing Methodologies to AI Techniques for Paddy Crop Leaf Disease Identification

Abstract

Disease is a common term used for ailments in all species, from humans to animals and plants. This research work helps to identify the diseases of plants. There are many methods to identify the plant’s disease using various techniques and algorithms; in this work, leaf disease is identified focusing on the ailment identification using quantum computing techniques to get a vivid result for better crop production. As there are many diseases in a paddy crop, they have been categorized into two types: nursery diseases and main field diseases. Both types cause a great loss in crop yield. In this research work, main field diseases are studied; though there are various main field diseases, research work targets leaf color changing, and colored spots. The existing methods use hybrid algorithms using AI techniques, but the result is not favorable, therefore, to get a precise result, the methodology is focused on techniques based on quantum computing. The technique to identify disease in a plant varies from leaf to leaf, but the base disease remains the same. Defects like yellow, black, and white spots are common problems. The fungi disease takes the energy from the plants in which they live, this leads to conditions like wilting, scabs, moldy coatings, rusts, blotches, and rotted tissues. All these problems have different existing solutions, through this research work, a minimal fault detection method is identified to reduce the flaws in the paddy crop. As the initial step, paddy crops are taken for research work; later, this can be extended to wheat and maize. The focus is on a hybrid approach of quantum computing and AI as quantum computing techniques help to spot patterns in large data sets. The concept of quantum image processing will help to elaborate the images of a leaf to identify its defect. QIP uses high varied quantum lattice methods to identify clear leaf images by reducing noise and paving the way to identify the discolored leaf at a minimal time. quantum computing possibly paves way for new opportunities in the techniques of Artificial Intelligence, for better predictions and decision-making involving a combination of large data collected from various resources, to produce very clear results. This research work aims to solve the problem of proper identification of paddy crops by studying the image carefully with the designed algorithms to achieve better results that lead to better productivity. The image detection helps to trigger the crop production by routine test work on the image captured thus optimizing the consistency and accuracy. This work also helps to detect the related issues during image computation using image classification techniques.