Published Paper Details:

A plant's main component is water. In this way, changes in plant water content have a significant impact on how plants grow. Visual item identification is a straightforward skill for a human. Computer-based picture identification is still difficult, though. Recent developments in machine learning have led to the development of strong recognition and classification methods that can handle challenging settings. This research proposes a machine learning-based smart agricultural architecture based on plant detection and categorization. In order to improve plant development in a local water situation, this research seeks to organize and design an intelligent framework in light of Support Vector Machine (SVM) and machine vision. The strategy employs a powerful deep learning-based architecture for item identification in the context of Smart Agriculture. This architecture describes an approach for image recognition with a specific focus on the automated recognition of plants and flowers. It aims to automatically detect damages in leaves and fruits, locate them, classify their severity levels, and visualize them by contouring their exact locations. The mobile iOS (iPhone Operating System) application was described that was designed, and results can indicate a higher accuracy when the SVM was utilized as the classifier with high precision for plant conditions (Fresh and Wilted).