Plant Identification Via Leaf Classification Using Color and Biometric Features

Authors

  • Çiğdem TURHAL Bilecik Şeyh Edebali University, Faculty of Engineering Department of Electrical and Electronics Engineering

DOI:

https://doi.org/10.46291/ISPECJASvol5iss2pp393-400

Keywords:

Plant identification, Plant venation, Image Processing, Leaf classification, Machine Learning

Abstract

Plants that are of great importance for humans and other living things are an integral part of our ecosystem. In today's world, where many plant species are at risk of disappearance, the identification of plants helps to protect and survive all natural life. There are many studies presented in the literature for plant identification. The most popular of these identification methods is leaf based classification. The reason for choosing leaves in this classification is that they are easier to obtain than other biometric components such as flowers available for a short period of time. Various biometric properties of the leaf must be determined for leaf classifications. In traditionally it is time consuming and expensive to perform this process visually by experts. In this article, various leaf biometric features obtained by digital image processing methods are used as the feature extraction step for automatic leaf classification. As the classification algorithms, Naive Bayes, Linear Regression, Multilayer Perceptron, Decision Tree and Random Forest are used. According to the experimental results using the training set as the test set, 100% recognition rate is obtained for Random Forest classification algorithm and 96% recognition rate is obtained in 30-fold cross validation for Linear Regression classification algorithm.

References

Bashish, D.A., Braik, M., Bani-Ahmad, S. 2010. A framework for detection and classification of plant leaf and stem diseases. In Signal and Image Processing (ICSIP), International Conference IEEE, 113–118.

Beghin, T., Cope, J.S., Remagnino, P., Barman, S. 2010. Shape and texture based plant leaf classification. In International Conference on Advanced Concepts for Intelligent Vision Systems, Springer, 345–353.

Chang, T., Kuo, C.C. 1993. Texture analysis and classification with tree-structured wavelet transform. IEEE Transactions on Image Processing, 2(4): 429–441.

Coşkun, M., Bengisu, G. 2021. Determine the effects of bacteria ınoculation on yield and yield components of some legume green fertilization crops under organic farming conditions. ISPEC Journal of Agricultural Sciences, 5(1): 10-20.

Kadir, A., Nugroho, L.E., Susanto, A., Santosa, P.I. 2013. Leaf classification using shape, color, and texture features. arXiv preprint arXiv:1401-4447.

Keten, M., Tanrıverdi, Ç. 2020. The effect of the leonardite dose applied at different rates on the water-yield relationship of amaranth (Amaranthus cruentus L.) plants. ISPEC Journal of Agricultural Sciences, 4(4): 823-833.

Kumar-Saroj, S., Oshiro, S., Yadav, P., Pratap-Singh, N. 2019. An efficient approach for plant leaves identification based on texture features. International Journal of Computational Intelligence & IoT 2(3).

Petr, T., Suk, T. 2013. Leaf recognition of woody species in Central Europe. Biosystems Engineering, 115(4): 444-452.

Pedro, F.B., Silva-Andre, R.S., Marcal-Rubim, M., Almeida da Silva. 2013. Evaluation of features for leaf discrimination. Springer Lecture Notes in Computer Science, 79(50): 197-204.

Weka-Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H. 2009. The WEKA Data Mining Software: An Update. SIGKDD Explorations, 11(1).

Published

2021-06-02

How to Cite

Çiğdem TURHAL. (2021). Plant Identification Via Leaf Classification Using Color and Biometric Features. ISPEC Journal of Agricultural Sciences, 5(2), 393-400. https://doi.org/10.46291/ISPECJASvol5iss2pp393-400

Issue

Section

Articles