Rice grain classification

A comparative study of state-of-the-art deep learning architectures for rice grain classification
This study explores deep-learning models for automated rice grain classification, which is essential for quality control, cost optimization, and supply chain efficiency. Testing models like ResNet, VGG, EfficientNet, and MobileNet on a dataset of 75,000 images across five rice categories, results showed that EfficientNet achieved the highest accuracy (99.67%), while MobileNet excelled in speed. The study concludes that deep-learning models offer scalable, efficient handling of large, complex data, outperforming traditional machine-learning methods.
Farshad Farahnakian, Javad Sheikh, Fahimeh Farahnakian, Jukka Heikkonen
Cite DOI
A comparative study of state-of-the-art deep learning architectures for rice grain classification