Classification of Some Iranian Vicia Species Using SEM Image Analysis Coupled with Conventional Texture Analysis and Deep Learning

Document Type : Original Research

Authors
M. Jafari 1
S. A. M. Mirmohammady Maibody 2
M. H. Ehtemam 2
1 Department of Biosystems Engineering, College of Agriculture, Isfahan University of Technology Isfahan 84156-83111, Islamic Republic of Iran.
2 Department of Agronomy and Plant Breeding, College of Agriculture, Isfahan University of Technology, Isfahan 84156-83111, Islamic Republic of Iran.
10.22034/JAST.27.2.343
Abstract
Micromorphological characteristics of seed sculpturing might be effective in circumscribing the infra-specific taxa in the genus Vicia. The present study was conducted to determine whether microstructural and seed coat texture data obtained from SEM images can serve as sufficient tools for delimiting Vicia genus. Other than visual inspections, a variety of texture-based methods, including the four conventional approaches of GLCM, LBP, LBGLCM, and SFTA, and the four pre-trained convolutional neural networks, namely, ResNet50, VGG16, VGG19, and Xception models were employed to extract features and to classify the species of Vicia genus using SEM images. In a subsequent step, the four unsupervised k-means, Mean-shift, agglomerative, and Gaussian mixture classification methods were used to group the identified Vicia spices based on the underlying features thus extracted. Moreover, the three supervised classifiers of Multilayer Perceptron Network (MLP), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN) were compared in terms of capability in discriminating the different visually-identified classes. SEM results showed that three classes might be identified based on the micromorphological character-species connections and that the differences among the species in the Vicia genus and the validity of Vicia sativa could be confirmed. Regarding the performance of the classifiers, SFTA textural descriptor outperformed the GLCM, LBP, and LBGLCM algorithms, but yielded a decreased accuracy compared with deep learning models. The combined Xception model and a MLP classifier was successful to discriminate the species in the Vicia genus with the best classification performances of 99 and 96% in training and testing, respectively.

Keywords

Subjects

Aedo, C. 2016. Taxonomic Revision of Geranium sect. Polyantha (Geraniaceae) 1. Ann. Missouri Bot. Gard., 101(4):611-635.
2. Ariunzaya, G., Kavalan, J. C. and Chung, S. 2023. Identification of seed coat sculptures using deep learning. J. Asia-Pac. Biodivers., 16(2):234-245.
3. Asadova, K. and Asgarov, A. 2018. Distribution and Ecobiological Research of Vetch (Vicia L.) Species in Azerbaijan. Int. J. Curr. Res. Biosci. Plant Biol., 5(7):27-36.
4. Boissier, E. and Buser, R. 1888. Flora orientalis; sive, Enumeratio plantarum in oriente a Graecia et Aegypto ad Indiae fines hucusque observatarum: Supplementum editore R. Buser. apud H. Georg.
5. Buyukarikan, B. and Ulker, E. 2022. Classification of physiological disorders in apples fruit using a hybrid model based on convolutional neural network and machine learning methods. Neural Comput. Appl. 34(19):16973-16988.
6. Cai, J., Liu, M., Zhang, Q., Shao, Z., Zhou, J., Guo, Y., Liu, J., Wang, X., Zhang, B. and Li, X. 2022. Renal cancer detection: fusing deep and texture features from histopathology images. Biomed Res. Int. 2022.
7. Chrtková-Žertová, A. 1979. Vicia. Flora Iranica. 140:16-56.
8. Chuang, K. S., Tzeng, H. L., Chen, S., Wu, J. and Chen, T. J. 2006. Fuzzy c-means clustering with spatial information for image segmentation. Comput. Med. Imaging Graph. 30(1):9-15.
9. Cronquist, A. 1988. The evolution and classification of flowering plants. New York Botanical Garden.
10. Engler, A. 1892. Syllabus der pflanzenfamilien. Vol. 2. Gebrüder Borntraeger Verlag.
11. Fedchko, B. A. 1948. Flora of the USSR (Flora SSSR). Vol. 13. Koeltz Scientific Books, Koenigsteine.
12. Gabr, D. G. 2018. Significance of fruit and seed coat morphology in taxonomy and identification for some species of Brassicaceae. Am. J. Plant Sci., 9(03):380.
13. Genze, N., Bharti, R., Grieb, M., Schultheiss, S. J. and Grimm, D. G. 2020. Accurate machine learning-based germination detection, prediction and quality assessment of three grain crops. Plant methods, 16(1):1-11.
14. Gunn, C. R. 1971. Seeds of native and naturalized vetches of North America. US Agricultural Research Service, 392.
15. Ilakiya, J. and Ramamoorthy, D. 2021. SEM and light microscopic studies in seeds of Hibiscus surattensis L. and phylogenetic attributes in Puducherry region, India. Geol. Ecol. Landsc. 5(4):269-279.
16. Jalal, M., Shaheen, S., Saddiqe, Z., Harun, N., Abbas, M. and Khan, F. 2021. Scanning electron microscopic screening; Can it be a taxonomic tool for identification of traditional therapeutic plants. Microsc. Res. Tech. 84(4):730-745.
17. Kaus, M. R., Warfield, S. K., Nabavi, A., Black, P. M., Jolesz, F. A. and Kikinis, R. 2001. Automated segmentation of MR images of brain tumors. Radiology, 218(2):586-591.
18. Kozłowski, M., Górecki, P. and Szczypiński, P. M. 2019. Varietal classification of barley by convolutional neural networks. Biosyst. Eng. 184:155-165.
19. Liu, L., Fieguth, P., Wang, X., Pietikainen, M. and Hu, D. 2016. Evaluation of LBP and deep texture descriptors with a new robustness benchmark. Computer Vision–ECCV: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Springer.
20. Liu, X. and Aldrich, C. 2022. Deep learning approaches to image texture analysis in material processing. Metals, 12(2):355.
21. Luo, T., Zhao, J., Gu, Y., Zhang, S., Qiao, X., Tian, W. and Han, Y. 2021. Classification of weed seeds based on visual images and deep learning. Inf, Process. Agric., 10(1): 40-51.
22. Narmadha, R., Sengottaiyan, N. and Kavitha, R. 2022. Deep transfer learning based rice plant disease detection model. Intell. Autom. Soft Comput. 31(2): 1257-1271.
23. Pakravan, M., Hayel Moghaddam, K. and Ghahreman, A. 2001. Use of micromorphological data for classification in the genus Alcea (Malvaceae). In Proceeding of deep morphology; 18-21 October; University of Vienna, Austria.
24. Pieniazek, F. and Messina, V. 2016. Scanning electron microscopy combined with image processing technique: Microstructure and texture analysis of legumes and vegetables for instant meal. Microsc. Res. Tech., 79(4):267-275.
25. Prasad, R., Mukherjee, K. and Gangopadhyay, G. 2014. Image-analysis based on seed phenomics in sesame. Plant Breed. Seed Sci. 68(1):119.
26. Przybyło, J. and Jabłoński, M. 2019. Using Deep Convolutional Neural Network for oak acorn viability recognition based on color images of their sections. Comput. Electron. Agric. 156:490-499.
27. Rashid, N., Zafar, M., Ahmad, M., Malik, K., Haq, I., Shah, S. N., Mateen, A. and Ahmed, T. 2018. Intraspecific variation in seed morphology of tribe vicieae (Papilionoidae) using scanning electron microscopy techniques. Microsc. Res. Tech. 81(3):298-307.
28. Rashid, N., Zafar, M., Ahmad, M., Memon, R. A., Akhter, M. S., Malik, K., Malik, N. Z., Sultana, S. and Shah, S. N. 2021. Seed morphology: An addition to the taxonomy of Astragaleae and Trifolieae (Leguminosae: Papilionoidae) from Pakistan. Microsc. Res. Tech., 84(5):1053-1062.
29. Ribas, L. C., Junior, J. J. dM. S, Scabini, L. F. and Bruno, O. M. 2020. Fusion of complex networks and randomized neural networks for texture analysis. Pattern Recognit., 103:107189.
30. Shrivastava, V. K., Pradhan, M. K., Minz, S. and Thakur, M. P. 2019. Rice plant disease classification using transfer learning of deep convolution neural network. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., 42:631-635.
31. Stern, W. T. 1983. Botanical Latin. 3 ed. London: Thomas Nelson.
32. Szkudlarz, P. and Celka, Z. 2016. Morphological characters of the seed coat in selected species of the genus Hypericum L. and their taxonomic value. Biodivers. Res. Conserv., 44(1):1-9.
33. Taheri-Garavand, A., Nasiri, A., Fanourakis, D., Fatahi, S., Omid, M. and Nikoloudakis, N. 2021. Automated in situ seed variety identification via deep learning: a case study in chickpea. Plants, 10(7):1406.
34. Verma, S., Chug, A. and Singh, A. P. 2020. Application of convolutional neural networks for evaluation of disease severity in tomato plant. J. Discret. Math. Sci. Cryptogr. 23(1):273-282.
35. Voronchikhin, V. 1981. Identification of certain species of the genus Vicia L. from their fruits and seeds.
36. Wei Tan, J., Chang, S. W., Abdul-Kareem, S., Yap, H. J. and Yong, K. T. 2018. Deep learning for plant species classification using leaf vein morphometric. IEEE/ACM Trans. Comput. Biol. Bioinform., 17(1):82-90.
37. Yang, S., Zheng, L., He, P., Wu, T., Sun, S. and Wang, M. 2021. High-throughput soybean seeds phenotyping with convolutional neural networks and transfer learning. Plant Methods, 17(1):50.
Journal of Agricultural Science and Technology
Volume 27, Issue 2
March and April 2025
Pages 343-357