An Accurate HOG based Exemplar Pyramid Method for Image Classification of Astragalus L. Taxa

Abstract

As known from the literature, machine learning (ML) is one of the popular researches have been used variable areas. In this work, a novel exemplar pyramid method is presented to accurately classify Astragalus L. taxa by using their chromosome images. To implement ML to biological images, the proposed exemplar pyramid method is used. Histogram of Oriented Gradients (HOG) is utilized as feature generator. The proposed exemplar pyramid method consists of preprocessing, feature generation and concatenation, feature selection and classification phase. 10 classifiers are chosen to train and test the extracted features. According to results, the proposed exemplar pyramid generates discriminative features. because five of the used 10 classifiers achieved 100.0% classification rate.

Keywords

• Chromosome
• Astragalus
• Image processing
• HOG
• Plant classficaiton

References

1. Albayrak, S. and Kaya, O., 2019. Antioxidant, Antimicrobial And Cytotoxic Activities Of Endemic Astragalus argaeus Boiss. From Turkey. Hacettepe J. Biol. & Chem., 47 (1), 87–97.
2. Çeçen, Ö., Aytaç, Z., and Mısırdalı, H., 2016. Astragalus unalii (Fabaceae), A New Species From Turkey. Turkish Journal of Botany, 40, 81-86.
3. Ebrahimzadeh, R., and Jampour, M., 2014. Efficient Handwritten Digit Recognition Based On Histogram Of Oriented Gradients And SVM. International Journal of Computer Applications (0975 – 8887), 104(9), 10-13.
4. Elci, S., 1982. Observations and Reserarch Methods In Cytogenetics. Fırat University Press, Elazig.
5. Emre, İ., Şahin, A., Türkoğlu, İ., Yılmaz, Ö., Bahşi, M., and Kurşat, M., 2011. Compositions Of Seed Fatty Acids In Some Astragalus L. Taxa From Turkey, Acta Botanica Gallica, 158(4), 487-491.
6. Fernandes, F., Weigel, L., Jung, C., Navaux, P., Carro, L., and Rech, P., 2016. Evaluation of Histogram Of Oriented Gradients Soft Errors Criticality For Automotive Applications. ACM Transactions on Architecture and Code Optimization, 13 (4), 38:2-38:25.
7. Gedik, O., Kurşat, M., and Kiran, Y., 2019. Karyological Studies On Nine Astragalus L. taxa in Turkey. KSÜ Tarım ve Doğa Dergisi, 22(1), 35-44.
8. Liu, N., and Kan, J.M., 2016. Improved Deep Belief Networks And Multifeature Fusion For Leaf Identification. Neurocomputing, 216, 460–467.

9. Naresh, Y.G., and Nagendraswamy, H.S., 2016. Classification of Medicinal Plants: An Approach Using Modified Lbp With Symbolic Representation. Neurocomputing, 173,1789–1797.
10. Sheidai, M., Shahin, Z., and Jalal, I., 2009. New Chromosome Number Reports In Tragacanthic Astragalus Species. Caryologia, 62(1), 30-36.
11. Siraj, F., Salahuddin, M.A., and Yusof, S.A.M., 2010. Digital Image Classification For Malaysian Blooming Flower. Second International Conference on Computational Intelligence, Modelling and Simulation, 33-38.
12. Uchida, S., 2013. Image Processing And Recognition For Biological Images. Develop. Growth Differ., 55, 523–549.
13. Wang, Z., Li, H., Zhu, Y., and Xu, T.F., 2017. Review of Plant Identification Based On Image Processing. Arch Computat Methods Eng., 24, 637–654.
14. Yigit, E., Sabanci, K., Toktas, A., and Kayabası, A., 2019. A Study On Visual Features Of Leaves In Plant Identification Using Artificial Intelligence Techniques. Computers and Electronics in Agriculture, 156, 369–377.