UNCONVENTIONAL TECHNIQUE FOR IMPROVING FARMER YIELDS BY EXPOSING AND MITIGATING FOLIAGE DISEASES IN AN EXTENSIVELY ADAPTABLE DEEP LEARNING AND COMPUTATIONAL MODEL THROUGH MICROBIOLOGICAL VEGETATION ASSESSMENT

The consistency of yield for many agriculture sectors is indicated by leaf-based diseases. These sector include banana farming, mango growing and many others. The identification and prevention of these diseases is extremely necessary to improve the quality of yield. Thus, over the years many image processing methods for efficiently detecting leaf-based diseases have been suggested. The present work proposes a new architecture based on a deep neural network which takes a variety of imagery aspects into account when identifying leaf imaging diseases. The proposed architecture improves precision by evaluating the structure, colour, form and border information. This article further contrasts the current scheme with other state-of-the-art systems, and it is observed that by retaining a mild algorithmic complexity, the proposed system increases the accuracy, precision and recall.