Classification of Cassia Cinnamon and Ceylon Cinnamon using Deep Learning

Cinnamon, a widely utilized spice with diverse culinary and medicinal applications, consists of various variants, notably Cassia and Ceylon. Accurate classification of these variants is crucial for ensuring product authenticity and quality control in the spice industry. In this study, we propose a deep learning-based categorization system that specifically utilizes transfer learning and the VGG16 architecture. A dataset of 317 images of Ceylon cinnamon and 306 images of Cassia cinnamon, each derived from a single piece of cinnamon, served as the training and evaluation dataset for the classification model. The results indicate that the proposed approach is successful in discriminating between cinnamon cultivars from Cassia and Ceylon, with an encouraging 82.66% accuracy rate. This classification system is essential for enhancing quality assurance processes and ensuring consumer confidence in products containing cinnamon. The study found that deep learning-based categorization methods offer a trustworthy and efficient way to categorize and authenticate various spice kinds, which raises customer happiness and improves the quality of the industry's output.