SwinT-PGK: a lightweight and accurate framework for tea leaf age grading

Abstract As a globally important agricultural commodity, the quality of tea is closely linked to its economic and cultural value. Recent advances in artificial intelligence and sensing technologies have facilitated the development of automated tea harvesting systems. Among the various factors affecting tea quality and flavor, leaf age serves as an important indicator of plant health and growth status. Accurate classification of tea leaf age is therefore essential for improving product consistency and optimizing harvest timing. However, existing automated approaches have primarily focused on bud detection or disease diagnosis, while the classification of tea leaf age has received comparatively less attention. To address this gap, a novel framework named SwinT-PGK is proposed, which integrates a Swin Transformer for feature extraction with a hybrid Principal Component Analysis–Genetic Algorithm (PCA-GA) for feature optimization, followed by a k-Nearest Neighbors (KNN) classifier. Under real-world plantation conditions, the method achieves a tea leaf age classification accuracy of 97.52%, using only a 26-dimensional feature vector. This represents a 2.71% improvement over the baseline Swin Transformer model, which relies on a 768-dimensional feature space. These results suggest that SwinT-PGK can effectively reduce feature dimensionality while maintaining high classification performance, offering a practical tool to support informed decision-making in tea cultivation and improve the overall consistency and quality of tea production.