Identification of Green, Oolong and Black Teas in China via Wavelet Packet Entropy and Fuzzy Support Vector Machine

Entropy

Shuihua Wang¹  Xiaojun Yang³  Yudong Zhang¹  Preetha Phillips⁴  Jianfei Yang⁵  Ti-Fei Yuan² 

[1] School of Computer Science and Technology, Nanjing Normal University, 210023 Nanjing, China; E-Mail:;School of Psychology, Nanjing Normal University, 210008 Nanjing, China;Department of Mathematics and Mechanics, China University of Mining and Technology, 221008 Xuzhou, China; E-Mail:;School of Natural Sciences and Mathematics, Shepherd University, Shepherdstown, 25443 West Virginia, WV, USA; E-Mail:;Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing, 210042 Nanjing, China; E-Mail:

关键词: tea identification;    wavelet packet entropy;    Shannon entropy;    wavelet analysis;    support vector machine (SVM);    fuzzy SVM;    information theory;   

DOI  :  10.3390/e17106663

来源: mdpi

【 摘 要 】

To develop an automatic tea-category identification system with a high recall rate, we proposed a computer-vision and machine-learning based system, which did not require expensive signal acquiring devices and time-consuming procedures. We captured 300 tea images using a 3-CCD digital camera, and then extracted 64 color histogram features and 16 wavelet packet entropy (WPE) features to obtain color information and texture information, respectively. Principal component analysis was used to reduce features, which were fed into a fuzzy support vector machine (FSVM). Winner-take-all (WTA) was introduced to help the classifier deal with this 3-class problem. The 10 × 10-fold stratified cross-validation results show that the proposed FSVM + WTA method yields an overall recall rate of 97.77%, higher than 5 existing methods. In addition, the number of reduced features is only five, less than or equal to existing methods. The proposed method is effective for tea identification.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.