Premium
Improving feature extraction in fingerprint of medicinal herbs via wavelet transform and fractal technique
Author(s) -
Du Jianwei,
Tang Yuan Yan,
Wang Jingrong,
Jiang Zhihong
Publication year - 2006
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/cem.1028
Subject(s) - pattern recognition (psychology) , artificial intelligence , fingerprint (computing) , wavelet transform , medicinal herbs , wavelet , fractal , computer science , combing , feature extraction , fractal dimension , mathematics , discrete wavelet transform , feature (linguistics) , traditional medicine , materials science , medicine , mathematical analysis , linguistics , philosophy , composite material
In this paper, hybrid features combing both high‐frequency and low‐frequency components of wavelet transform are applied to fingerprint of medicinal herbs. Through the fingerprints of medicinal herbs by wavelet transform and the fractal dimensions, 13 features are obtained, which are called fractal‐wavelet features. In this new approach, the information of each sample can be acquired to the maximum degree. These novel hybrid features have been applied to recognition of the different types of ginseng. Experiments have been conducted, and the result of recognition can match the real situation. Experiments indicate this method is better than the traditional ones. Copyright © 2007 John Wiley & Sons, Ltd.