Deep Learning–based Fruit Quality Assessment Using Comparative Cnn Architectures and Yolov8 Detection
Year: 2026
Type: article
Abstract: This study proposes a deep learning-based approach for automated fruit quality classification into Good and Bad categories using a labelled image dataset.A comparative evaluation of EfficientNet (EfficientNetB0), MobileNetV2, ResNet50, and a custom 2D CNN was conducted.Experimental results show that ResNet50 achieved the highest training and validation accuracy with stable convergence and minimal overfitting.In addition to these, YOLOv8 was applied for real-time fruit quality detection.
Source: Science and Culture
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W7225124604