Tomato Crop Disease Classification Using Semantic Segmentation Algorithm in Deep Learning

Abstract

Agriculture is critical to human survival. Almost 70% of the population is involved in agriculture, either directly or indirectly. There are no technologies in the old system to identify diseases in diverse crops in an agricultural environment, which is why farmers are not interested in expanding their agricultural productivity all days. Crop diseases control the growth and production of their particular species; hence early detection is also essential. There have been many attempts to use Machine Learning (ML) methods for disease detection and classification in agriculture, but recent advances in a subset of ML called Deep Learning (DL) have given this field of study renewed hope for improved accuracy. The widespread spread of diseases in the tomato crop has an impact on both the quality and quantity of the crop. A rapid, dependable, and non-destructive way of diagnosing Tomato diseases early on may be useful for farmers. The approach employs two deep learning based algorithms, the AlexNet and the SegNet Model, with input including seven different color images of tomato leaves, six of which are afflicted and one of which is healthy. This algorithm is applicable for other plants like potato, corn diseases of bacterial, fungul infection leaves. Some examples of hyperparameters that have been investigated for their effect on classification accuracy and execution time are mini-batch size, weights, and bias learning rate.