Optimizing Plant Disease Detection Using Convolutional Neural Networks and Docker Environment

Optimizing Plant Disease Detection Using Convolutional Neural Networks and Docker Environment

연구 분야: Software Development

학회: 2025 International Conference on Computing for Sustainability and Intelligent Future (COMP-SIF)

In numerous nations, agriculture serves as the primary and most significant source of income generated domestically. Plant illnesses caused by bacteria, viruses, and fungi are among the many, and they can be quite expensive for agricultural companies worldwide. Crop security both in terms of quantity and quality is crucial for monitoring plant disease. Therefore, it is essential to recognize plant diseases. There are certain plant parts where the disease state is clearly visible. However, usually, the infection is seen in specific plant leaves. Many researchers use computing techniques to automatically detect plant illness using photos of their leaves. Farmers might also profit fromthese strategies by obtaining quick and suitable measures to do in both agricultural yield and quality. Furthermore, some molecular methods have been developed to reduce and even eliminate the harm posed by pathogens. Thus, this evaluationaids the researcher to identify automatically the plant illness. Also enhancing the learning and provide specific methods for disease identification in order to prevent illness.