Pratondo Agus, Elfahmi Elfahmi, Novianty Astri
Department of Multimedia Engineering, School of Applied Sciences, Telkom University, Bandung, West Java, Indonesia.
Department of Pharmaceutical Biology, School of Pharmacy, Bandung Institute of Technology, Bandung, West Java, Indonesia.
PeerJ Comput Sci. 2022 Dec 15;8:e1168. doi: 10.7717/peerj-cs.1168. eCollection 2022.
(turmeric) and (temulawak) are members of the family that contain curcuminoids, essential oils, starch, protein, fat, cellulose, and minerals. The nutritional content proportion of turmeric is different from temulawak which implies differences in economic value. However, only a few people who understand herbal plants, can identify the difference between them. This study aims to build a model that can distinguish between the two species of based on the image captured from a mobile phone camera. A collection of images consisting of both types of rhizomes are used to build a model through a learning process using transfer learning, specifically pre-trained VGG-19 and Inception V3 with ImageNet weight. Experimental results show that the accuracy rates of the models to classify the rhizomes are 92.43% and 94.29%, consecutively. These achievements are quite promising to be used in various practical use.
姜黄和莪术是姜科植物的成员，含有姜黄素类、精油、淀粉、蛋白质、脂肪、纤维素和矿物质。姜黄的营养成分比例与莪术不同，这意味着它们在经济价值上存在差异。然而，只有少数了解草药植物的人能够识别它们之间的差异。本研究旨在构建一个模型，可以根据手机摄像头拍摄的图像区分这两种植物。通过使用迁移学习，特别是使用带有ImageNet权重的预训练VGG - 19和Inception V3，利用由两种根茎类型组成的图像集合来构建模型。实验结果表明，模型对根茎进行分类的准确率分别为92.43%和94.29%。这些成果在各种实际应用中具有很大的应用前景。
