# Green-Making Stage Recognition of Tieguanyin Tea Based on Improved MobileNet V3

## TL;DR

This paper introduces a lightweight AI model to automatically recognize the green-making stages of Tieguanyin tea, improving accuracy and efficiency over traditional methods.

## Contribution

A novel lightweight model, T-GSR, is proposed with improvements to MobileNet V3 for accurate and efficient tea stage recognition.

## Key findings

- The T-GSR model achieved 93.38% recognition accuracy for green-making stages.
- The model outperformed MobileNet V3 with 3.025 M parameters and 0.242 G FLOPs.
- The model supports intelligent and automated tea production through online monitoring.

## Abstract

The green-making stage is crucial for forming the distinctive aroma and flavor of Tieguanyin tea. Current green-making stage recognition relies on tea makers’ sensory experience, which is labor-intensive and time-consuming. To address these issues, this paper proposes a lightweight automatic recognition model named T-GSR for the accurate and objective identification of Tieguanyin tea green-making stages. First, an extensive set of Tieguanyin tea images at different green-making stages was collected. Subsequently, preprocessing techniques, i.e., multi-color-space fusion and morphological filtering, were applied to enhance the representation of target tea features. Furthermore, three targeted improvements were implemented based on the MobileNet V3 backbone network: (1) an adaptive residual branch was introduced to strengthen feature propagation; (2) the Rectified Linear Unit (ReLU) activation function was replaced with the Gaussian Error Linear Unit (GELU) to improve gradient propagation efficiency; and (3) an Improved Coordinate Attention (ICA) mechanism was adopted to replace the original Squeeze-and-Excitation (SE) module, enabling more accurate capture of complex tea features. Experimental results demonstrate that the T-GSR model outperforms the original MobileNet V3 in both classification performance and model complexity, achieving a recognition accuracy of 93.38%, an F1-score of 93.33%, with only 3.025 M parameters and 0.242 G FLOPs. The proposed model offers an effective solution for the intelligent recognition of Tieguanyin tea green-making stages, facilitating online monitoring and supporting automated tea production.