Xiaofeng Zhou, Zhe Tang, Fang Qi
Fermentation is a key processing technology in black tea production, and the quality of black tea largely depends on it. In order to reduce the dependence on artificial in fermentation process, a method of identifying black tea fermentation degree based on convolutional neural network is proposed in this paper. In this paper, the convolutional neural network is leveraged to identify the fermentation degree of black tea. The L-SVM function is used to replace softmax activation function to identify fermentation degree of black tea in the softmax layer of convolutional neural network structure, and achieved accuracy rate of 89.0% for 2000 images of black tea fermentation. Through experimental comparison, the identification accuracy of using convolutional neural network is higher than that of using multilayer perceptron to identify the fermentation degree of black tea. The method proposed in this paper promoted the automation and intellectualization of fermentation and production of black tea. © 2018 IEEE.
Department of Electrical Engineering, Faculty of Electrical Technology, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia; Department of Electrical Engineering, Universitas Negeri Surabaya, Surabaya, Indonesia; Department of Computer Engineering, Faculty of Electrical Technology, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock