Thai Herb Identification with Medicinal Properties Using Convolutional Neural Network
Keywords:Herb Identification, Leaf Recognition, Convolutional Neural Network, VGGNet, Fast R-CNN
This paper builds an intelligent computer model to identify Thai herb from a single image using convolutional neural network. Since Thailand is one of the world herbal source. We used 2,700 herbal images with their medicinal properties to train the computer model that covered 11 well-known Thai herbs: Siamese Rough-bush, Cumin, Holy Basil, Sweet Basil, Cha Muang, Kaffir-lime Leaf, Siamese Morning-glory, Pandanus Leaf, Mint, Chinese Kale and Chaplu, respectively. The feature extraction framework and model architecture were done by Fast Region Convolution Neural Network (Fast R-CNN) and Visual Geometry Group Network (VGGNet) that produce the recall as higher than 0.75 and the precision as higher than 0.80.
Alom, M. Z., et al. (2018). The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches. arXiv, 1803.01164,
Arun, C. H., et al. (2013). Texture Feature Extraction for Identification of Medicinal Plants and Comparison of Different Classifiers. International Journal of ComputerApplications, 62(12), 1-9.
de Luna, R. G., et al. (2017). Identification of Philippine herbal medicine plant leaf using artificial neural network. The 9th International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management, pp. 1-8.
Girshick, R., et al. (2014). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. International Conference on
Computer Vision and Pattern Recognition,pp.580-587.
Girshick, R. (2015). Fast R-CNN. The 2015 International Conference on Computer Vision, pp.1440-1448.
Giuffrida, M.V., et al. (2017). ARIGAN: Synthetic Arabidopsis Plants Using Generative Adversarial Network. The 2017 IEEE
International Conference on Computer Vision, pp. 2064-2071.
Hodges, I. (1999). Time in Transition: King Narai and the Luang Prasoet Chronicle of Ayutthaya. Journal of the Siam Society,
Janani, R. & Gopal, A. (2013). Identification of Selected Medicinal Plant Leaves Using Image Features and ANN. IEEE Conference on
Advanced Electronic Systems, pp.238-242.
Krizhevsky, A., et al. (2012). ImageNet Classification with Deep Convolutional Neural Networks. The 25th International
Conference on Neural Information Processing Systems, pp. 1097-1105.
Liu, L., et al. (2018). Deep Learning for Generic Object Detection: A Survey. arXiv, 1809.02165, 1-37.
Love, R. S. (1994). Simon De La Loubere: French Views of Siam in the 1680s. Journal of the
Siam Society, 82(2), 155-164.
Masao, T. (1908). The New Penal Code of Siam.The Yale Law Journal, 18(2), 085-100.
Mookdarsanit, P., et al. (2018). Name and Recipe Estimation of Thai-desserts beyond Image Tagging. Kasembundit Engineering Journal,
(Special Issue), 293-303.
Mookdarsanit, S., et al. (2019). SiamFishNet: The Deep Investigation of Siamese Fighting Fishes. International Journal of Applied
Computer Technology and Information Systems, 8(2), 40-46.
Pornpanomchai, C. & Rimdusit, S. (2011). Thai Herb Leaf Image Recognition System(THLIRS). Kasetsart Journal, 45(3), 551-562.
Satti, V., et al. (2013). An Automatic Leaf Recognition System for Plant Identification Using Machine Vision Technology.
International Journal of Engineering Science and Technology, 5(4), 874-879.
Simonyan, K. & Zisserman A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. The 2014 European
Conference on Computer Vision, pp. 84-90.
Sun, X. & Qian, H. (2016). Chinese Herbal Medicine Image Recognition and Retrieval by Convolutional Neural Network. Public
Library of Science One, 11(6), 1-19.
Zhao, Z. Q., et al. (2018). Object Detection with Deep Learning: A Review. IEEE Transactions on Neural Networks and
Learning Systems, PP(99), 01-21.
Zheng, L., et al. (2018). SIFT Meets CNN: A Decade Survey of Instance Retrieval. IEEE Transactions on Pattern Analysis and
Machine Intelligence, 40(5), 1224-1244.
How to Cite
This work is licensed under a Creative Commons Attribution 4.0 International License.