Abstract
Medicinal plants can provide immense contribution towards the growth of modern medicine and pharmaceutical industries to protect people from current deadly diseases like cancer and cardiovascular diseases. However, presence of thousands of plant species globally and similarity in their features like color, texture and shape makes their identification critical and immensely challenging. Moreover, utilization of traditional methods to classify plant leaf under expert’s guidance is costly, challenging and time taking process. Therefore, in this article, a Weighted KNN Classification (WKNNC) Model is adopted for the accurate identification of plant leaf images based on machine learning techniques.High quality morphological and discriminative features are obtained by using Region of Interest (ROI) images which is extracted from segmentation process. The proposed WKNNC model works upon Local Intensity Relation (LIR) and directional group encoding method to obtain high quality features. Further, the obtained feature weights provide high classification accuracy. Folio Leaf dataset is utilized to evaluate performance of proposed WKNNC model. The obtained classification accuracy is compared against several state-of-art-techniques and proposed EKNNC model outperforms all of them.
Similar content being viewed by others
References
Ahmed A, Hussein SE (2020) Leaf identification using radial basis function neural networks and SSA based support vector machine. PLoS One 15(8):e0237645. https://doi.org/10.1371/journal.pone.0237645
Anami BS, Nandyal SS, Govardhan A (2010) A combined color, texture and edge features based approach for identi_cation and classification of Indian medicinal plants. Int J Comput Appl 6(12):45–51
Azlah MAF, Chua LS, Rahmad FR, Abdullah FI, Alwi W, Sharifah R (2019) Review on techniques for plant leaf classification and recognition. Computers 8(4):77. https://doi.org/10.3390/computers8040077
Botany JO (2014) Retracted: Phytoliths as emerging taxonomic tools for identification of plants: an overview. J Bot https://doi.org/10.1155/2014/231914
Chaudhury A, Barron JL (2020) Plant species identification from occluded leaf images. IEEE/ACM Transactions on Computational Biology and Bioinformatics 17(3):1042–1055. https://doi.org/10.1109/TCBB.2018.2873611
Durairajah V, Gobee S, Muneer A (2018) Automatic vision based classification system using DNN and SVM classifiers, in Proc. 3rd Int. Conf.Control, Robot. Cybern. (CRC), 6–14
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for imagerecognition, in Proc. IEEE Conf Comput Vis Pattern Recognit (CVPR), pp. 770–778, https://doi.org/10.1109/cvpr.2016.90
Huixian J (2020) The analysis of plants image recognition based on deep learning and artificial neural network. IEEE Access 8:68828–68841. https://doi.org/10.1109/ACCESS.2020.2986946
Karami N, Javid A, Haghirosadat B (2017) A review of medicinal plants effective in the treatment or apoptosis of cancer cells. Cancer Press 3(1):22. https://doi.org/10.15562/tcp.41
Kumar M, Gupta S, Gao X, Singh A (2019) Plant species recognition using morphological features and adaptive boosting methodology. IEEE Access 7:163912–163918. https://doi.org/10.1109/ACCESS.2019.2952176
Larese MG, Namías R, Craviotto RM, Arango MR, Gallo C, Granitto PM (2014) Automatic classification of legumes using leaf vein image features. Pattern Recogn 47(1):158–168
Lulekal E, Kelbessa E, Bekele T, Yineger H (2008) An ethnobotanical study of medicinal plants in Mana Angetu District, southeastern Ethiopia. J Ethnobiol Ethnomed. https://doi.org/10.1186/1746-4269-4-10
Muneer A, Fati SM (2020) Efficient and automated herbs classification approach based on shape and texture features using deep learning. IEEE Access 8:196747–196764. https://doi.org/10.1109/ACCESS.2020.3034033
Patil AA, Bhagat KS (2016) Plant identification by leaf shape recognition. A review. Int J Eng Trends Technol 8(35):359–361
Pushpanathan K, Hanafi M, Mashohor S, Ilahi W (2021). Machine learning in medicinal plants recognition: a review. Artif Intell Rev 54. https://doi.org/10.1007/s10462-020-09847-0
Tan JW, Chang SW, Abdul-Kareem S, Yap HJ, Yong KT (2020) Deep learning for plant species classification using leaf vein morphometric. IEEE/ACM Transactions on Computational Biology and Bioinformatics 17(1):82–90. https://doi.org/10.1109/TCBB.2018.2848653
Thanikkal JG, Dubey AK, Thomas MT (2020) Unique shape descriptor algorithm for medicinal plant identification (SDAMPI) with abridged image database. IEEE Sensors J 20(21):13103–13109. https://doi.org/10.1109/JSEN.2020.3002909
Wang L, Huai Y, Peng Y-C (2015) Identification of foliage plant speciesbased on multi-feature fusion of leaf images. J Beijing Forestry Univ 37(01):55–61. https://doi.org/10.13332/j.cnki.jbfu.2015.01.006
Wang Z, Sun X, Zhang Y, Ying Z, Ma Y (2016) Leaf recognition basedon PCNN. Neural Comput Appl 27(4):899–908. https://doi.org/10.1007/s00521-015-1904-1
Wang X, Du W, Guo F, Hu S (2020) Leaf recognition based on elliptical half Gabor and maximum gap local line direction pattern. IEEE Access 8:39175–39183. https://doi.org/10.1109/ACCESS.2020.2976117
WHO (1999) WHO monographs on selected medicinal plants, 1st edn. World Health Organization, Geneva
Yang X et al (2020) Instance segmentation and classification method for plant leaf images based on ISC-MRCNN and APS-DCCNN. IEEE Access 8:151555–151573. https://doi.org/10.1109/ACCESS.2020.3017560
Zhang C, Zhou P, Li C, Liu L (2015) A convolutional neuralnetwork for leaves recognition using data augmentation, in Proc. IEEE Int Conf Comput Inf Technol, 2143–2150, doi: https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.318
Zhang S, Huang W, Huang Y-a, Zhang C (2020) Plant species recognition methods using leaf image: overview. Neurocomputing 408:246–272
Zheng Y (2017) Method of leaf identification based on multi-feature dimensionreduction. Trans Chin Soc Agricult Mach 48(03):30–37. https://doi.org/10.6041/j.issn.1000-1298.2017.03.004
Zheng Y, Zhang L (2018) Plant leaf image recognition methodbased on transfer learning with convolutional neural networks. TransChin Soc Agricult Machinery 49(1):354–359. https://doi.org/10.6041/j.issn.1000-1298.2018.S0.047
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Patil, S., Sasikala, M. Segmentation and identification of medicinal plant through weighted KNN. Multimed Tools Appl 82, 2805–2819 (2023). https://doi.org/10.1007/s11042-022-13201-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13201-7