Automated Detection of Plant Diseases and Chlorophyl With Image Processing Using Mobile Application

Abstract

Green plants are capable of producing their own sustenance. They accomplish this through a process known as photosynthesis, which makes use of a chlorophyll-based green pigment. A pigment is a chemical that has a specific color and, depending on that color, may absorb light at various wavelengths. The chlorophyll of the leaf may be predicted from leaf color, which has the potential to be an excellent indicator of plant health. Chlorophyll a (Chl-a) and Chlorophyll b are the two main types of chlorophyll found in the photosystems of green plants (Chl-b). Each kind has a unique function as well as advantages and a unique chemical composition. So, it is crucial to anticipate the chlorophyll of the takes off as it provides valuable information regarding plant health and edit management. In the proposed work, a non-destructive image processing technique is employed to estimate the chlorophyll content of tomato plants using images of the leaves. The chlorophyll content of the acquired image is predicted using a deep learning (DL) algorithm. Using the camera of an Android smartphone, samples of tomato plant leaves were collected from the field, and the color vegetation indices for all three RGB channels were then abstracted. The Chlorophyll detector, which is aimed at both small- and large-scale farms, has finally been built. For easy deployment, the mobile app combines an image from a smartphone camera with cloud-hosted software.