Open AccessTea Verification Using Triplet Loss Convolutional Network
Author(s) -
Kun-Yi Chen,
Chi-Yu Chang,
Zhi-Ren Tsai,
Chun-Ting Lee,
Zon-Yin Shae
Publication year - 2021
Publication title -
advances in technology innovation
Language(s) - English
Resource type - Journals
eISSN - 2518-2994
pISSN - 2415-0436
DOI - 10.46604/aiti.2021.6939
Subject(s) - convolutional neural network , artificial intelligence , feature (linguistics) , computer science , pattern recognition (psychology) , majority rule , image (mathematics) , voting , deep learning , transfer of learning , contextual image classification , philosophy , linguistics , politics , political science , law
To solve tea image classification problems, this study focuses on triplet loss convolutional neural network to classify six high-mountain oolong tea classes. In the experiment, instead of using traditional deep learning training approach for local feature of tea images, an innovative image verification approach is proposed to learn the global feature of tea images by integrating the distributed tea leaves’ features of all tea sub-images and using a majority voting mechanism to do classification. The results show that the proposed approach can work for small sample size dataset and have higher accuracy than normal transfer learning approach. The average accuracy of the proposed approach achieves 99.54%.