A Streamlined Method for Detecting Strawberry Leaf Diseases Utilizing Deep Learning Techniques

Strawberry leaf scorch presents major risks to fruit yields through its harmful effects on plant health so early detection methods are vital for growers. This research analyzes how different Convolutional Neural Networks classify strawberry leaf diseases while fixing problems found in earlier studies about speed and diagnosis precision. The proposed research evaluated five CNN models namely AlexNet, DenseNet, ResNet, MobileNet, and EfficientNet through implementation on a total of 6146 images that showcased both healthy and scorch-affected strawberry leaves. The proposed research optimized feature extraction techniques and added model comparison to find the most effective configuration. EfficientNet achieved higher accuracy and precision than all test models when detecting diseases in samples. The strong disease identification abilities of DenseNet and MobileNet show promise for developing better ways to manage agricultural health problems. This study expands precision agriculture methods while helping farmers sustain their operations through modern machine learning tools.