# FSCA-EUNet: Lightweight Classification of Stacked Jasmine Bloom-Stages via Frequency–Spatial Cross-Attention for Industrial Scenting Automation

## TL;DR

This paper introduces a lightweight AI model to classify the bloom stages of stacked jasmine flowers in tea scenting processes, enabling real-time automation.

## Contribution

A novel U-Net model with frequency-spatial cross-attention is proposed for efficient and accurate classification of jasmine bloom stages.

## Key findings

- The model achieved 95.52% precision and 97.24% mean average precision on a custom dataset.
- It runs at 22.33 FPS on edge devices with only 878.851 K parameters and 15.445 G FLOPs.
- Ablation studies confirmed the effectiveness of each module in improving classification accuracy.

## Abstract

To address the challenge of monitoring the postharvest jasmine bloom stages during industrial tea scenting processes, this study proposes an efficient U-shaped Network (U-Net) model with frequency–spatial cross-attention (FSCA-EUNet) to resolve critical bottlenecks, including repetitive backgrounds and small interclass differences, caused by stacked jasmine flowers during factory production. High-resolution images of stacked jasmine flowers were first preprocessed and input into FSCA-EUNet, where the encoder extracted multi-scale spatial features and the FSCA module incorporated frequency-domain textures. The decoder then fused and refined these features, and the final classification layer output the predicted bloom stage for each image. The proposed model was designed as a “U-Net”-like structure to preserve multiscale details and employed a frequency–spatial cross-attention module to extract high-frequency texture features via a discrete cosine transform. Long-range dependencies were established by NonLocalBlook, located after the encoders in the model. Finally, a momentum-updated center loss function was introduced to constrain the feature space distribution and enhance intraclass compactness. According to the experimental results, the proposed model achieved the best metrics, including 95.52% precision, 95.42% recall, 95.40% F1-score, and 97.24% mean average precision, on our constructed dataset with only 878.851 K parameters and 15.445 G Floating Point Operations (FLOPs), and enabled real-time deployment at 22.33 FPS on Jetson Orin NX edge devices. The ablation experiments validated the improvements contributed by each module, which significantly improved the fine-grained classification capability of the proposed network. In conclusion, FSCA-EUNet effectively addresses the challenges of stacked flower backgrounds and subtle interclass differences, offering a lightweight yet accurate framework that enables real-time deployment for industrial jasmine tea scenting automation.