Comparison of MobilenetV2 and NASNetMobile for  Lavender Flower Analysis  using Convolutional Neural Network

Tito Sugiharto; Iwan Lesmana; Rio Priantama; Munya Saleh Ba Matraf

doi:10.15575/join.v11i1.1654

Authors

Tito Sugiharto Department of Informatics, Universitas Kuningan, Indonesia
Iwan Lesmana Department of Informatics, Universitas Kuningan, Indonesia
Rio Priantama Department of Informatics, Universitas Kuningan, Indonesia
Munya Saleh Ba Matraf Human-Centered Computing Research Lab, School of Computing, Universiti Utara Malaysia, Malaysia

DOI:

https://doi.org/10.15575/join.v11i1.1654

Keywords:

Comparison , CNN, Lavender Flower, MobileNetV2, NASNetMobile

Abstract

The identification of lavender flower varieties is a critical challenge in botany and agriculture, primarily due to the high morphological similarity among different varieties and the influence of environmental conditions on their appearance. Traditional methods of identifying lavender varieties, which often rely on manual observation, face significant limitations. These methods are time-consuming, prone to subjective error, and may not account for subtle environmental variations that affect flower morphology. The specific goal of this research is to develop an automated classification model using Deep Learning techniques, specifically Convolutional Neural Networks (CNN), to improve the accuracy and efficiency of lavender variety identification. The study leverages a dataset from Kaggle, which contains images of three lavender varieties—Lavandula angustifolia, Lavandula viridis, and Lavandula multifida. By applying data augmentation techniques to address dataset variability, the research compares two advanced CNN architectures, MobileNetV2 and NASNetMobile, for their classification performance. The key contribution of this work is demonstrating that NASNetMobile achieves superior performance, with 91.87% accuracy and a lower loss value, compared to MobileNetV2, which reaches 81.67% accuracy. This study highlights the novelty of using CNN models for lavender classification, offering a significant advancement over traditional methods by enhancing the identification process's accuracy and reducing reliance on manual and inefficient approaches. The findings have broad implications for botanical research, agricultural practices, and plant conservation efforts, showing that CNNs can significantly improve the efficiency of plant species identification.

References

[1] R. Chandra, T. Arifin Prasetyo, H. E. Lumbangaol, V. Siahaan, and J. I. Sianipar, “Development of a Mobile-Based Application for Classifying Caladium Plants Using the CNN Algorithm,” Jurnal Online Informatika, vol. 9, no. 1, pp. 111–118, May 2024, doi: 10.15575/join.v9i1.1296.

[2] N. Nurafiya and A. Y. Chandra, “Analisis Performa Akurasi Klasifikasi Citra Jenis Sayur Salada Menggunakan Arsitektur VGG16, Xception dan NasNetMobile,” Jurnal Media Informatika Budidarma, vol. 8, no. 3, p. 1240, Jul. 2024, doi: 10.30865/mib.v8i3.7661.

[3] J. Thomkaew and S. Intakosum, “Plant Species Classification Using Leaf Edge Feature Combination with Morphological Transformations and SIFT Key Point,” Journal of Image and Graphics(United Kingdom), vol. 11, no. 1, pp. 91–97, Mar. 2023, doi: 10.18178/joig.11.1.91-97.

[4] D. Akash et al., “Deep Learning for Plant Species Classification,” Power System Technology, vol. 49, 2024, [Online]. Available: https://powertechjournal.com

[5] D. Djenane, M. Aïder, J. Yangüela, L. Idir, D. Gómez, and P. Roncalés, “Antioxidant and antibacterial effects of Lavandula and Mentha essential oils in minced beef inoculated with E. coli O157:H7 and S. aureus during storage at abuse refrigeration temperature,” Meat Sci., vol. 92, no. 4, pp. 667–674, Dec. 2012, doi: 10.1016/j.meatsci.2012.06.019.

[6] M. D. Sanna, F. Les, V. Lopez, and N. Galeotti, “Lavender (Lavandula angustifolia Mill.) essential oil alleviates neuropathic pain in mice with spared nerve injury,” Front. Pharmacol., vol. 10, no. MAY, 2019, doi: 10.3389/fphar.2019.00472.

[7] M. Lis-Balchin, Lavender: The Genus Lavandula. CRC Press, 2002.

[8] A. S. Abade, P. A. Ferreira, and F. de B. Vidal, “Plant Diseases recognition on images using Convolutional Neural Networks: A Systematic Review,” Sep. 2020, [Online]. Available: http://arxiv.org/abs/2009.04365

[9] P. Srivastava, K. Mishra, V. Awasthi, V. Kumar Sahu, and P. Kumar Pal, “Plant Disease Detection Using Convolutional Neural Network,” Int. J. Adv. Res. (Indore)., vol. 9, no. 01, pp. 691–698, Jan. 2021, doi: 10.21474/IJAR01/12346.

[10] M. Yogeshwari and G. Thailambal, “Automatic feature extraction and detection of plant leaf disease using GLCM features and convolutional neural networks,” in Materials Today: Proceedings, Elsevier Ltd, 2021, pp. 530–536. doi: 10.1016/j.matpr.2021.03.700.

[11] T. Sugiharto et al., PENGOLAHAN CITRA DIGITAL DAN DETEKSI OBJEK. Malang: PT Literasi Nusantara Abadi Grup, 2025. [Online]. Available: www.penerbitlitnus.co.id

[12] R. Hadiyansah and R. Andamira, “Convolutional Neural Network (CNN) for Detecting Al-Qur’an Reciting and Memorizing,” Khazanah Journal of Religion and Technology, vol. 1, no. 2, pp. 44–48, Dec. 2023, doi: 10.15575/kjrt.v1i2.235.

[13] A. M. Roofiad, A. Sabillah, A. N. Rohman, and E. W. Triyani, “Classifying Hijaiyah Letters Handwritten Detection of Children Using CNN Algorithm,” Khazanah Journal of Religion and Technology, vol. 2, no. 1, pp. 18–22, Aug. 2024, doi: 10.15575/kjrt.v2i1.812.

[14] T. Sugiharto, Saparudin, and W. Fawwaz Al Maki, “Indonesian Cued Speech Transliterate System Using Convolutional Neural Network MobileNet,” in 2024 Ninth International Conference on Informatics and Computing (ICIC), Medan, Indonesia: IEEE, 2024, pp. 1–7. doi: 10.1109/ICIC64337.2024.10957117.

[15] B. Balaji, T. Satyanarayana Murthy, and R. Kuchipudi, “A Comparative Study on Plant Disease Detection and Classification Using Deep Learning Approaches,” International Journal of Image, Graphics and Signal Processing, vol. 15, no. 3, pp. 48–59, Jun. 2023, doi: 10.5815/ijigsp.2023.03.04.

[16] C. Karam, M. Awad, Y. Abou Jawdah, N. Ezzeddine, and A. Fardoun, “GAN-based semi-automated augmentation online tool for agricultural pest detection: A case study on whiteflies,” Front. Plant Sci., 2021, doi: 10.3389/fpls.2022.813050.

[17] M. Shoaib et al., “An advanced deep learning models-based plant disease detection: A review of recent research,” 2023, Frontiers Media SA. doi: 10.3389/fpls.2023.1158933.

[18] J. V. Anchitaalagammai, S. L. J. S. Revathy, S. Kavitha, and S. Murali, “Factors influencing the use of Deep Learning for Medicinal Plants Recognition,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Nov. 2021. doi: 10.1088/1742-6596/2089/1/012055.

[19] H. Rehana, M. Ibrahim, and Md. H. Ali, “Plant Disease Detection using Region-Based Convolutional Neural Network,” Mar. 2023, [Online]. Available: http://arxiv.org/abs/2303.09063

[20] İ. Aslan and N. Polat, “Deep learning-based classification of mature and immature lavender plants using UAV orthophotos and a hybrid CNN approach,” Earth Sci. Inform., vol. 17, no. 2, pp. 1713–1727, Apr. 2024, doi: 10.1007/s12145-023-01200-7.

[21] B. Khasoggi, Ermatita, and Samsuryadi, “Efficient mobilenet architecture as image recognition on mobile and embedded devices,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 16, no. 1, pp. 389–394, Oct. 2019, doi: 10.11591/ijeecs.v16.i1.pp389-394.

[22] S. Salsabila and A. Suharso, “Comparison of Deep Learning Architectures in Identifying Types of Medicinal Plant Leaf Images,” 2024. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC