Comparison of Ensemble Methods for Malaysian Medicinal Leaf Images Identification and Classification


  • Mohd Shamrie Sainin
  • Faudziah Ahmad
  • Rayner Alfred



Medicinal plant, ensemble, AdaboostM1, Random Forest


Malaysia has abundant natural resources especially plants which can be used for medicinal or herbal purposes. However, there is less research to preserve the knowledge of these resources to be utilized by the community in identifying useful medicinal plants using computing tools. In order to support this study, finding suitable method for identification and classification must be done in order to provide better classification performance. Ensemble methods are classification methods that combines several diverse classifiers which known to perform better than single classifiers. In this regard, the best ensemble method for this specific leaf image data need to be explored and Weka has been used as the platform to compare related ensemble methods. The study in this paper compares several ensemble classifiers where AdaboostM1 with Random Forest as base classifier provides the best technique to the nature of the shape-based Malaysian medicinal leaf images data. The ensemble classifier is also tested with other shape based dataset image domain and shows that the classifier is able to produce the best classification performance.




[1] Kulkarni, A. H., Rai, H. M., Jahagirdar, K. A., and Upparamani, P. S. 2013. A Leaf Recognition Technique for Plant Classification Using RBPNN and Zernike Moments. International Journal of Advanced Research in Computer and Communication Engineering. 2(1): 984–988.

[2] Chemburkar, A., Sartape, A., Gawade, A., and Somawanshi, P. 2014. Automated Tool for Plant Leaf Classification Using Morphological Features. International Journal Of Engineering And Computer Science. 3(11): 9098–9102.

[3] Krupnick, G. A. and Kress, W. J. 2005. Plant Conservation: A Natural History Approach. The Plant Press.

[4] Shakeel PM, Baskar S, Dhulipala VS, Mishra S, Jaber MM., “Maintaining security and privacy in health care system using learning based Deep-Q-Networksâ€, Journal of medical systems, 2018 Oct 1;42(10):186.

[5] Quinlan, M. B. and Quinlan, R. J. 2007. Modernization and Medicinal Plant Knowledge in a Caribbean Horticultural Village. International Journal for the Analysis of Health. 21(2): 169–192.

[6] Kadir, A. A. 1998. Biodiversity Prospecting Of Tropical Plants For Medicinal Uses. In Proceedings of the Third National Congress on Genetics.

[7] Sridhar KP, Baskar S, Shakeel PM, Dhulipala VS., “Developing brain abnormality recognize system using multi-objective pattern producing neural networkâ€, Journal of Ambient Intelligence and Humanized Computing, 2018:1-9.

[8] Ong, H. C., Zuki, R. M., and Milow, P. 2011. Traditional Knowledge of Medicinal Plants among the Malay Villagers in Kampung Mak Kemas, Terengganu, Malaysia. Ethno Med. 5(3): 175–185.

[9] Zakaria, M. and Mohd, M. A. 2010. Traditional Malay Medicinal Plants. Institut Terjemahan Negara Malaysia.

[10] Sainin, M. S., Ghazali, T. K., and Alfred, R. 2014. Malaysian Medicinal Plant Leaf Shape Identification and Classification. In Proceedings of the Knowledge Management International Conference and Exhibition. 578–583.

[11] Bong, M.-F., Sulong, G., Kumoi, R., and Rahim, M. S. M. 2015. Classify The Plant Species Based on Lobes, Sinuses and Margin. Jurnal Teknologi. 75(2): 27–31.

[12] Pornpanomchai, C., Rimdusit, S., Tanasap, P., and Chaiyod, C. 2011. Thai Herb Leaf Image Recognition System (THLIRS). Kasetsart Journal (Natural Science). 045(3): 551–562.

[13] Herdiyeni, Y. and Santoni, M. M. 2012. Combination of Morphological, Local Binary Pattern Variance and Color Moments Features for Indonesian Medicinal Plants Identification. In Proceedings of the International Conference on Advanced Computer Science and Informations. 255–259.

[14] Herdiyeni, Y. and Wahyuni, N. K. S. 2012. Mobile Application for Indonesian Medicinal Plants Identification using Fuzzy Local Binary Pattern and Fuzzy Color Histogram. In Proceedings of the International Conference on Advanced Computer Science and Information Systems (ICACSIS2012).

[15] Selvakumar S, Inbarani H, Shakeel PM. A Hybrid Personalized Tag Recommendations for Social E-Learning System. International Journal of Control Theory and Applications. 2016;9(2):1187-99.

[16] Guo, X., Yin, Y., Dong, C., Yang, G., and Zhou, G. 2008. On the Class Imbalance Problem. In Proceedings of the Fourth International Conference on Natural Computation, ICNC’08. 4: 192–201.

[17] Witten, I. and Frank, E. 2000. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann.

[18] Dietterich, T. G. 2000. Ensemble methods in machine learning. In Proceedings of the IEEE Transactions on Multiple Classifier Systems, Man, and Cybernetics Part B: Cybernetics. 1857: 1–15.

[19] Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., and Herrera, F. 2012. A Review on Ensembles for the Class ImbalanceProblem: Bagging-, Boosting-, and Hybrid-Based Approaches. IEEE Transactions on Systems, Man, and Cybernetics - Part C: Applications and Reviews. 42(4): 463–484.

[20] Freund, Y. and Schapire, R. 1996. Experiments with a new boosting algorithm. In Proceedings of the International Conference on Machine Learning. 148–156.

[21] Breiman, L. 1996. Bagging Predictors. Machine Learning. 24(2): 123–140.

[22] Jerzy BÅ‚aszczyÅ„ski, Stefanowski, J., and Idkowiak, Å. 2013. Extending Bagging for Imbalanced Data. In Proceedings of the 8th International Conference on Computer Recognition Systems CORES. 269–278.

[23] P. Mohamed Shakeel; Tarek E. El. Tobely; Haytham Al-Feel; Gunasekaran Manogaran; S. Baskar., “Neural Network Based Brain Tumor Detection Using Wireless Infrared Imaging Sensorâ€, IEEE Access, 2019, Page(s): 1

[24] Gaikwad, D. P. and Thool, R. C. 2015. Intrusion Detection System Using Bagging Ensemble Method of Machine Learning. In Proceedings of the International Conference on Computing Communication Control and Automation (ICCUBEA). 291 – 295.

[25] Melville, P. and Mooney, R. J. 2004. Creating Diversity In Ensembles Using Artificial Data. Information Fusion. 6: 99–111.

[26] Gu, S. and Jin, Y. 2014. Generating diverse and accurate classifier ensembles using multi-objective optimization. In Proceedings of the IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making (MCDM). 9–15.

[27] Gu, S., Cheng, R., and Jin, Y. 2015. Multi-objective ensemble generation. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 5(5): 234–245.

[28] Ramisa, A. and Torras, C. 2013. Large-scale image classification using ensembles of nested dichotomies. Frontiers in Artificial Intelligence and Applications. 256: 87–90.

[29] Webb, G. I. 2000. MultiBoosting: A Technique for Combining Boosting and Wagging. Machine Learning. 40: 159–196.

[30] Sainin, M. S. and Alfred, R. 2012. A Direct Ensemble Classifier for Imbalanced Multiclass Learning. In Proceedings of the International conference on Data Mining Optimization (DMO2012). 59–66.

[31] Pedro F.B. S., Andre R.S. M., and Rubim M. A.d. S. 2013. Evaluation of Features for Leaf Discrimination. Springer Lecture Notes in Computer Science. 7950: 197-204.

[32] Siebert, J.P. 1987. Vehicle Recognition Using Rule Based Methods. Turing Institute Research Memorandum TIRM-87-018.

[33] N. Thakoor, J. Gao, S. Jung. 2007. Hidden Markov Model-Based Weighted Likelihood Discriminant for 2-D Shape Classification. IEEE Transactions on Image Processing. 16(11): 270723–2719.

[34] Shakeel PM. Neural Networks Based Prediction Of Wind Energy Using Pitch Angle Control. International Journal of Innovations in Scientific and Engineering Research (IJISER). 2014;1(1):33-7.

[35] HMRC. Introduction to Herbal Medicine Research Centre (HMRC). 2011. [Online]. Available:

[36] Jantan, I. 2004. Medicinal Plant Research in Malaysia: Scientific Interests and Advances. Jurnal Sains Kesihatan Malaysia. 2(2): 27–46.

[37] Prasvita, D. S. and Herdiyeni, Y. 2013. Medleaf Mobile Application for Medicinal Plant Identification Based on Leaf Image. Advanced Science Enginering Information Technology. 2(2): 5–8.

[38] Yao, B., Zhao, Z., Liu, K., and Cai, A. 2015. Bagging based metric learning for person re-identification. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME). 1–6.

View Full Article: