Classification of Indian Herbal Leaf with Random Forest Classifier
Abstract
Herbal Leaf is normally used for preparing medicines. This includes images taken from the locality of West Bengal mainly Kolkata, with white background. By taking into account this problem of image classification, this research tries to identify herbal leaves based on the images taken on white background. Therefore, this research includes an image processing algorithm and Otsu segmentation. Then, the leaf image features are identified, based on the characteristics of the shape and texture. Herbal leaf shape and color features produce high accuracy only when both are applied at the same time. In this research, morphological features were used for shape feature extraction. The contribution of this study is using the proposed image enhancement and segmentation algorithm so that the features of the image can be extracted based on shape and color descriptors. The classification accuracy in this study has reached 97.8% with Random Forest Classifier.
Downloads
References
Chaki, J., Parekh, R., & Bhattacharya, S. (2015). Plant leaf recognition using texture and shape features with neural classifiers. Pattern Recognition Letters, 58, 61-68.
Chithra, P. L., & Janes, P. S. (2018). A Survey on Various Leaf Classification Techniques for Medicinal Plants. In Proceedings of the International Conference on Advancements in Computing Technologies (pp. 38-42).
Herdiyeni, Y., & Santoni, M. M. (2012, December). Combination of morphological, local binary pattern variance and color moments features for indonesian medicinal plants identification. In 2012 International Conference on Advanced Computer Science and Information Systems (ICACSIS) (pp. 255-259). IEEE.
Jin, T., Hou, X., Li, P., & Zhou, F. (2015). A novel method of automatic plant species classification using sparse representation of leaf tooth features. PloS one, 10(10), e0139482.
Kebapci, H., Yanikoglu, B., & Unal, G. (2011). Plant image retrieval using color, shape and texture features. The Computer Journal, 54(9), 1475-1490.
Mareta, A., Soesanti, I., & Wahyunggoro, O. (2018, March). Herbal leaf classification using images in natural background. In 2018 International Conference on Information and Communications Technology (ICOIACT) (pp. 612-616). IEEE.
Teng, C. H., Kuo, Y. T., & Chen, Y. S. (2009, July). Leaf segmentation, its 3d position estimation and leaf classification from a few images with very close viewpoints. In International Conference Image Analysis and Recognition (pp. 937-946). Springer, Berlin, Heidelberg.
Wang, Z., Sun, X., Ma, Y., Zhang, H., Ma, Y., Xie, W., & Zhang, Y. (2014, July). Plant recognition based on intersecting cortical model. In 2014 International joint conference on neural networks (IJCNN) (pp. 975-980). IEEE.
Zhao, C., Chan, S. S., Cham, W. K., & Chu, L. M. (2015). Plant classification using leaf shapes—A pattern counting approach. Pattern Recognition, 48(10), 3203-3215.
