Ningbo Traditional Chinese Medicine Chinese Herb Medicine (NB - TCM - CHM) Dataset

We have established two datasets containing 20 types of Chinese herbal medicine fruits intended for the automatic recognition research of herbal medicines. The first dataset (Dataset 1) was obtained through Google search and contains 3,384 images. The second dataset (Dataset 2) was obtained from photographs of Chinese herbal medicine taken with a smartphone in a traditional Chinese medicine pharmacy, comprising 400 images. In Dataset 1 and Dataset 2, each type of Chinese medicine herb is stored in a separate folder, with the folder named after its name. The 20 classes of images are (1) Psoralea Corylifolia, (2) Alpinia Katsumadai Hayata, (3) Toosendan Fructus, (4) Kochiae Fructus, (5) Amomi Fructus Rotundus, (6) Rubi Fructus, (7) Lycii Fructus, (8) Trichosanhes Kirilowii, (9) Rosae Laevigatae Frucyus, (10) Semen Armeniacae Amarum, (11) Forsythiae Fructus, (12) Chaenomelis Fructus, (13) Amomi Fructus, (14) Crataegi Fructus, (15) Cornifructus, (16) Persicae Semen, (17) Mume Fructus, (18) Schisandrae Chinensis Fructus, (19) Foeniculi Fructus, (20) Gardeniae Fructus. The two datasets form a Ningbo Traditional Chinese Medicine Chinese Herb Medicine (NB - TCM - CHM) Dataset.

我们构建了两套适用于中药材自动识别研究的数据集，涵盖20种药用果实类中药材。第一套数据集（数据集1）通过谷歌搜索（Google）获取，共包含3384张图像。第二套数据集（数据集2）采集自中药房内使用智能手机（smartphone）拍摄的中药材照片，共计400张图像。在数据集1与数据集2中，每一类中药材均存储于独立文件夹，文件夹以该药材的名称命名。20个类别依次为：(1) 补骨脂（Psoralea Corylifolia），(2) 草豆蔻（Alpinia Katsumadai Hayata），(3) 川楝子（Toosendan Fructus），(4) 地肤子（Kochiae Fructus），(5) 益智仁（Amomi Fructus Rotundus），(6) 覆盆子（Rubi Fructus），(7) 枸杞子（Lycii Fructus），(8) 栝楼（Trichosanhes Kirilowii），(9) 金樱子（Rosae Laevigatae Fructus），(10) 苦杏仁（Semen Armeniacae Amarum），(11) 连翘（Forsythiae Fructus），(12) 木瓜（Chaenomelis Fructus），(13) 砂仁（Amomi Fructus），(14) 山楂（Crataegi Fructus），(15) 山茱萸（Cornifructus），(16) 桃仁（Persicae Semen），(17) 乌梅（Mume Fructus），(18) 五味子（Schisandrae Chinensis Fructus），(19) 小茴香（Foeniculi Fructus），(20) 栀子（Gardeniae Fructus）。上述两套数据集共同组成宁波中医药材数据集（Ningbo Traditional Chinese Medicine Herb Dataset，缩写为NB-TCM-CHM）。