Smart Disease Detection System for Citrus Fruits Using Deep Learning with Edge Computing

In recent decades, deep-learning dependent fruit disease detection and classification techniques have evinced outstanding results in technologically advanced horticulture investigation. Due to the comparatively limited image processing capabilities of edge computing devices, implementing deep learning methods actual field scenarios is currently difficult. The use intelligent machines contemporary being hampered by these restrictions, which are emerging as a new barrier. this research, we present an efficient model for citrus prediction. proposed utilizes fusion models CNN LSTM with computing. employs enhanced feature-extraction mechanism, down-sampling approach, then feature-fusion subsystem ensure significant recognition on devices retaining accuracy. This research online Kaggle plan village dataset contains 2950 images categories black spots, cankers, scabs, Melanosis, greening. existing tested two features pruning without compared based various performance measuring parameters, i.e., precision, recall, f-measure, support. first phase experimental analysis performed using Magnitude Based Pruning second Post Quantization. CNN-LSTM achieves accuracy rate 97.18% Magnitude-Based 98.25% Quantization, better method.