Eliptik Fourier Serilerinde Yaprak Sınıflandırma İçin Parametre Seçimi

Abstract

Eliptik Fourier serileri metodu kontur analizinde göreceli olarak eski ancak güçlü bir yöntemdir. Bu metodu daha önce “BioMorp” isimli bir bilgisayar programı için bir modül olarak hazırlamıştık. Bu modülün iki önemli parametresi mevcuttur; birincisi konturu temsil edecek fonksiyonu meydana getiren harmoniklerin sayısıdır (sinüs-kosinüs terimleri). İkinci parametre, sinüs ve kosinüs terimlerinin sürekli toplamı olan fonksiyonun örneklenmesi ile elde edilen örneklerin sayısıdır. Bu çalışmada, bu iki parametrenin yaprak sınıflandırma üzerindeki etkileri incelenmiştir. Ayrıca koordinatların yeniden yapılandırılmasıyla elde edilen sonuçlar ile Fourier katsayılarının genlikleri kullanılarak elde edilen sonuçlar karşılaştırılmıştır. Koordinatların yeniden yapılandırılması ile minimum 15 sinüs-kosinüs terimi ve kontur başına 20 örnek kullanıldığında elde edilen en yüksek başarım değeri 75,197% iken, Fourier katsayılarının genlikleri kullanıldığında minimum 29 terim ile 69,953% olarak ölçülmüştür.

Keywords

• fourier serileri
• kontur analizi
• kontur sınıflandırma

Parameter Selection in Elliptical Fourier Series for Leaf Classification

Abstract

Elliptical Fourier series method is a relatively old but powerful method in contour analysis. We have previously implemented this method as a module for a computer program called “BioMorph”. There are two significant parameters in this module; the first one is the number of harmonics (sine-cosine terms) that are calculated to form a function which represents the contour. The second parameter is the number of samples that are collected by sampling the function which is a continuous function of sums of sine and cosine terms. In this study, the effects of those two parameters to leaf classification are investigated. Also classification results obtained using reconstructed coordinates and using magnitudes of Fourier coefficients are compared. While the highest classification accuracy is obtained as 75,197% with minimum 15 sine-cosine terms and 20 samples per contour using reconstructed coordinates, it is obtained as 69,953% using magnitudes of Fourier coefficients with minimum 29 terms.

Keywords

• fourier series
• contour analysis
• contour classification

References

1. Feng, S. (2021). Kernel pooling feature representation of pre-trained convolutional neural networks for leaf recognition. Multimedia Tools and Applications, 1-28.
2. Qin, X., Shi, Y., Huang, X., Li, H., Huang, J., Yuan, C., & Liu, C. (2021, August). Attention-Based Deep Multi-scale Network for Plant Leaf Recognition. In International Conference on Intelligent Computing (pp. 302-313).
3. Zheng, Y., Yuan, C. A., Shang, L., & Huang, Z. K. (2019, August). Leaf Recognition Based on Capsule Network. In International Conference on Intelligent Computing (pp. 320-325).
4. Sugata, T. L. I., & Yang, C. K. (2017, November). Leaf App: Leaf recognition with deep convolutional neural networks. In IOP Conf. Ser. Mater. Sci. Eng (Vol. 273, p. 012004).
5. Jeon, W. S., & Rhee, S. Y. (2017). Plant leaf recognition using a convolution neural network. International Journal of Fuzzy Logic and Intelligent Systems, 17(1), 26-34.
6. Ghazi, M. M., Yanikoglu, B., & Aptoula, E. (2017). Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing, 235, 228-235.
7. Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D., & Stefanovic, D. (2016). Deep neural networks based recognition of plant diseases by leaf image classification. Computational intelligence and neuroscience, 2016.
8. Yang, C. (2021). Plant leaf recognition by integrating shape and texture features. Pattern Recognition, 112, 107809.

9. Zhang, Q., Zeng, S., & Zhang, B. (2019, August). Initial investigation of different classifiers for plant leaf classification using multiple features. In Eleventh International Conference on Digital Image Processing (ICDIP 2019) (Vol. 11179, p. 1117922). International Society for Optics and Photonics.
10. Turkoglu, M., & Hanbay, D. (2019). Leaf-based plant species recognition based on improved local binary pattern and extreme learning machine. Physica A: Statistical Mechanics and its Applications, 527, 121297.
11. Zhang, X., Zhao, W., Luo, H., Chen, L., Peng, J., & Fan, J. (2019). Plant recognition via leaf shape and margin features. Multimedia Tools and Applications, 78(19), 27463-27489.
12. Kadir, A., Nugroho, L. E., Susanto, A., & Santosa, P. I. (2011). Leaf classification using shape, color, and texture features. Int. J. Comput. Trends Technol., 2 (1), 225-230.
13. Kalyoncu, C., & Toygar, Ö. (2015). Geometric leaf classification. Computer Vision and Image Understanding, 133, 102-109.
14. Zheng, Y., Guo, B., Li, C., & Yan, Y. (2019). A weighted Fourier and wavelet-like shape descriptor based on IDSC for object recognition. Symmetry, 11(5), 693.
15. Zare, A. A., & Zahiri, S. H. (2018). Recognition of a real-time signer-independent static Farsi sign language based on fourier coefficients amplitude. International Journal of Machine Learning and Cybernetics, 9(5), 727-741.
16. Wu, S. G., Bao, F. S., Xu, E. Y., Wang, Y. X., Chang, Y. F., & Xiang, Q. L. (2007, December). A leaf recognition algorithm for plant classification using probabilistic neural network. In 2007 IEEE international symposium on signal processing and information technology (pp. 11-16). IEEE.
17. Weisstein, Eric W. (2004). Fourier Series. https://mathworld.wolfram.com/FourierSeries.html (Accessed: 20.06.2020)