Intelligent Identification Method of Geographic Origin for Chinese Wolfberries Based on Color Space Transformation and Texture Morphological Features
Jiawang He,
Tianshu Wang,
Hui Yan,
Sheng Guo,
Kongfa Hu,
Xichen Yang,
Chenlu Ma,
Jinao Duan
Affiliations
Jiawang He
College of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China
Tianshu Wang
College of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China
Hui Yan
National and Local Collaborative Engineering Center of Chinese Medicinal Resources Industrialization and Formulae Innovative Medicine, Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese Medicine, Nanjing 210023, China
Sheng Guo
National and Local Collaborative Engineering Center of Chinese Medicinal Resources Industrialization and Formulae Innovative Medicine, Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese Medicine, Nanjing 210023, China
Kongfa Hu
College of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China
Xichen Yang
School of Computer and Electronic Information and School of Artificial Intelligence, Nanjing Normal University, Nanjing 210023, China
Chenlu Ma
College of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China
Jinao Duan
National and Local Collaborative Engineering Center of Chinese Medicinal Resources Industrialization and Formulae Innovative Medicine, Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization, Nanjing University of Chinese Medicine, Nanjing 210023, China
Geographic origins play a vital role in traditional Chinese medicinal materials. Using the geo-authentic crude drug can improve the curative effect. The main producing areas of Chinese wolfberry are Ningxia, Gansu, Qinghai, and so on. The geographic origin of Chinese wolfberry can affect its texture, shape, color, smell, nutrients, etc. However, the traditional method for identifying the geographic origin of Chinese wolfberries is still based on human eyes. To efficiently identify Chinese wolfberries from different origins, this paper presents an intelligent identification method for Chinese wolfberries based on color space transformation and texture morphological features. The first step is to prepare the Chinese wolfberry samples and collect the image data. Then the images are preprocessed, and the texture and morphology features of single wolfberry images are extracted. Finally, the random forest algorithm is employed to establish a model of the geographic origin of Chinese wolfberries. The proposed method can accurately predict the origin information of a single wolfberry image and has the advantages of low cost, fast recognition speed, high recognition accuracy, and no damage to the sample.
