Implementation Strategy of Tomato Plant Disease Detection using Optimized Feature Extraction Method

Abstract

Tomato plants normally have a single growing season, during which they develop, bear fruit, and then perish. The species first appeared in Western South America, Mexico, and Central America. In the sixteenth century, they were brought to various regions. They produce self-pollinating yellow blooms. After being pollinated, the blooms turn into fruits, which, depending on the type, might be red, yellow, green, or even purple. Tomatoes are a well-liked element in many recipes, including salads, sauces, and soups. They are high in vitamins A and C, potassium, and antioxidants. They are afflicted by several illnesses that can seriously harm the plant and lower crop output. These illnesses were brought on by a variety of minor inadequacies in the soil, air, and the major. These diseases are produced by a range of mineral deficiencies in the soil, and the air, and their primary causes include insects and fungi. We discovered that machine learning is a potential avenue for detecting these diseases before they spread to the plant. As a result, we thought about using Feature Extraction Methods to optimize the data