Affiliation:
1. Tea Research Institute, Hangzhou Academy of Agricultural Sciences, Hangzhou 310024, China
2. National Center for Tea Plant Improvement, Tea Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310008, China
Abstract
Tea plant cultivar identification is normally achieved manually or by spectroscopic, chromatographic, and other methods that are time-consuming and often inaccurate. In this paper, a method for the identification of three tea cultivars with similar leaf morphology is proposed using transfer learning by five pre-trained models: EfficientNet-B0, MobileNetV2, MobileNetV3, MobileViT-S, and ShuffleNetV2. The results showed that the best test accuracy percentages for EfficientNet-B0, MobileNetV2, MobileNetV3, MobileViT-S, and ShuffleNetV2 were 98.33, 99.67, 99.33, 98.67, and 99.00%, respectively. The most lightweight model was ShuffleNetV2, and the fastest combination was ShuffleNetV2 with 112 × 112 image resolution. Considering accuracy, the number of parameters, and floating point operations (FLOPs), MobileNetV2 was not only the most accurate model, but also both lightweight and fast. The present research could benefit both farmers and consumers via identifying tea cultivars without destructive techniques, a factor that would reduce the adulteration of commodity tea.
Funder
Zhejiang Science and Technology Major Program on Agricultural New Varieties of Breeding Tea Plants
Science and Technology Innovation and Demonstration and Promotion Fund of Hangzhou Academy of Agricultural Sciences
Key Technology Research and Product Creation for the High Value Utilization of Tea in the Hangzhou Longjing Production Area
Key Techniques and Innovative Applications of the Inheritance and Protection of Xihu Longjing Tea