Leafy AI: Integrating MobileNetV2 and TensorFlow Lite into a Flutter-Based Application for Real-Time Ornamental Plant Recognition

Haris Setyawan; Nur Zareen Zulkarnain; Abian Ayatullah Fikri

doi:10.30595/juita.v14i1.28141

Authors

Haris Setyawan Universitas Muhammadiyah Yogyakarta
Nur Zareen Zulkarnain Universiti Teknikal Malaysia Melaka
Abian Ayatullah Fikri Universitas Muhammadiyah Yogyakarta

DOI:

https://doi.org/10.30595/juita.v14i1.28141

Keywords:

MobileNetV2; ornamental plant recognition; TensorFlow Lite.

Abstract

Operating artificial intelligence on smartphones attracted interest in various applications, but in practice, device capacity limited AI capabilities. Limited processing power, restricted memory capacity, and unstable network connectivity could make AI models difficult to use outside lab environments. In this work, we describe Leafy AI, a mobile application that identifies ornamental plants designed to work fully on the device. The classifier is based on MobileNetV2 and trained with transfer learning using 67,200 images from 112 plant categories. Images were resized to 224 × 224 pixels and normalized before training. After training, the model was converted into TensorFlow Lite format and integrated within a Flutter application. A lightweight service layer manages preprocessing and inference so that the interface remains simple for the user. Evaluation using 13,440 test images achieved a top-one accuracy of 0.89. A smaller field experiment involving 226 photos captured under real-world conditions resulted in lower accuracy, primarily due to variations in lighting and background. Nevertheless, the system remained reliable in offline mode. The findings show that recognition of ornamental plants can be carried out on ordinary smartphones and that further improvements are possible through augmentation, domain adaptation, quantization, and hardware acceleration.

Author Biographies

Haris Setyawan, Universitas Muhammadiyah Yogyakarta

Information Technology

Nur Zareen Zulkarnain, Universiti Teknikal Malaysia Melaka

Fakulti Kecerdasan Buatan dan Keselamatan Siber

Abian Ayatullah Fikri, Universitas Muhammadiyah Yogyakarta

Information Technology

References

[1] L. N. Huynh, R. K. Balan, and Y. Lee, “DEMO: GPU-based image recognition and object detection on commodity mobile devices,” in MobiSys 2016 Companion - Companion Publication of the 14th Annual International Conference on Mobile Systems, Applications, and Services, Association for Computing Machinery, Inc, Jun. 2016, p. 111. doi: 10.1145/2938559.2938577.

[2] I. Martinez-Alpiste, G. Golcarenarenji, Q. Wang, and J. M. Alcaraz-Calero, “Smartphone-based real-time object recognition architecture for portable and constrained systems,” J. Real. Time. Image Process., vol. 19, no. 1, pp. 103–115, Feb. 2022, doi: 10.1007/s11554-021-01164-1.

[3] V. Kimie Isuyama and B. De Carvalho Albertini, “Comparison of Convolutional Neural Network Models for Mobile Devices,” 2021.

[4] J. Wu, Y. Zhang, J. Hou, W. Liu, W. Huang, and H. Bai, “PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural Networks,” 2018.

[5] R. Han, Q. Zhang, C. H. Liu, G. Wang, J. Tang, and L. Y. Chen, “LegoDNN: Block-grained scaling of deep neural networks for mobile vision,” in Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM, Association for Computing Machinery, 2021, pp. 406–419. doi: 10.1145/3447993.3483249.

[6] J. Choi, M. Kim, D. Ahn, T. Kim, Y. Kim, and D. Jo, “Squeezing Large-Scale Diffusion Models for Mobile,” Jul. 2023, [Online]. Available: http://arxiv.org/abs/2307.01193

[7] J. Wang, B. Cao, P. S. Yu, L. Sun, W. Bao, and X. Zhu, “Deep Learning Towards Mobile Applications,” Sep. 2018, [Online]. Available: http://arxiv.org/abs/1809.03559

[8] M. F. Supriadi, E. Rachmawati, and A. Arifianto, “Tampilan Pembangunan Aplikasi Mobile Pengenalan Objek Untuk Pendidikan Anak Usia Dini,” Jurnal Teknologi Informasi dan Ilmu Komputer, no. 8, 2020.

[9] N. Luh, P. Ning, S. P. Astawa, P. Trisna, and H. Permana, “Astwana & Permana, ‘AIClopedia’: How Does It Facilitate Gen-Z Students in Learning English? ‘AIClopedia’: How Does It Facilitate Gen-Z Students in Learning English?,” 2020. [Online]. Available: https://www.elitejournal.org/index.php/ELITE

[10] N. Yuniar, T. Triyaswati, P. Rizki, and A. Saputri, “Integrasi Kecerdasan Buatan (AI), Deep Learning, dan Kurikulum Berbasis Sustainable Development Goals untuk Generasi Global,” Jun. 2022. [Online]. Available: https://journal.staida-sumsel.ac.id/index.php/alhaytham

[11] A. M. Atha and E. Zuliarso, “Deteksi Tanaman Herbal Khusus Untuk Penyakit Kulit Dan Penyakit Rambut Menggunakan Convolutional Neural Network (CNN) Dan Tensorflow,” Jurnal JUPITER, no. 14, Oct. 2022.

[12] I. Y. Wulandari, N. Indroasyoko, R. Mudia Alti, Y. N. Asri, and R. Hidayat, “Pengenalan Sistem Deteksi Objek untuk Anak Usia Dini Menggunakan Pemrograman Python,” remik, vol. 6, no. 4, pp. 664–673, Oct. 2022, doi: 10.33395/remik.v6i4.11772.

[13] M. N. Arifin, M. Umar Mansyur, A. Rahman, N. P. Dewi, F. Prasetyo, and E. Putra, “Enhanced OCR Recognition for Madurese Text Documents: A Genetic Algorithm Approach with Tesseract 5.5,” https://jurnalnasional.ump.ac.id/index.php/JUITA/, vol. 13, pp. 109–118, 2025, Accessed: Oct. 27, 2025. [Online]. Available: https://jurnalnasional.ump.ac.id/index.php/JUITA/article/view/25794/9038

[14] H. Setyawan and D. Purbohadi, “Experimenting with AI-based mobile applications to improve student engagement in ornamental plant learning in rural Indonesian schools,” Edelweiss Applied Science and Technology, vol. 9, no. 3, pp. 2333–2343, 2025, doi: 10.55214/25768484.v9i3.5787.

[15] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” 2018.

[16] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, and T. Weyand, “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” Apr. 2017, [Online]. Available: http://arxiv.org/abs/1704.04861

[17] M. Tan and Q. V Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” 2019.

[18] Y. Cheng, D. Wang, P. Zhou, and T. Zhang, “Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges,” IEEE Signal Process. Mag., vol. 35, no. 1, pp. 126–136, Jan. 2018, doi: 10.1109/MSP.2017.2765695.

[19] Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, “Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing,” May 2019, [Online]. Available: http://arxiv.org/abs/1905.10083

[20] B. Jacob, S. Kligys, B. Chen, M. Zhu, M. Tang, and A. Howard, “Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference,” 2018.

[21] S. K. Esser, J. L. McKinstry, D. Bablani, R. Appuswamy, and D. S. Modha, “Learned Step Size Quantization,” May 2020, [Online]. Available: http://arxiv.org/abs/1902.08153

[22] Z. Dong, Z. Yao, A. Gholami, M. W. Mahoney, and K. Keutzer, “HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision.”

[23] G. Wilson and D. J. Cook, “A Survey of Unsupervised Deep Domain Adaptation,” ACM Trans. Intell. Syst. Technol., vol. 11, no. 5, Sep. 2020, doi: 10.1145/3400066.

[24] A. G. Khoee, Y. Yu, and R. Feldt, “Domain generalization through meta-learning: a survey,” Artif. Intell. Rev., vol. 57, no. 10, Oct. 2024, doi: 10.1007/s10462-024-10922-z.

[25] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, Dec. 2019, doi: 10.1186/s40537-019-0197-0.

[26] J. Nixon, G. Brain, M. W. Dusenberry, L. Zhang Google, G. Jerfel, and D. T. Google Brain, “Measuring Calibration in Deep Learning,” 2019.

[27] A. Mehrtash, W. M. Wells, C. M. Tempany, P. Abolmaesumi, and T. Kapur, “Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation,” IEEE Trans. Med. Imaging, vol. 39, no. 12, pp. 3868–3878, Dec. 2020, doi: 10.1109/TMI.2020.3006437.

[28] Z. Ding, X. Han, P. Liu, and M. Niethammer, “Local Temperature Scaling for Probability Calibration,” 2021.

[29] R. David, J. Duke, A. Jain, V. J. Reddi, N. Jeffries, and J. Li, “Tensor Flow Lite Micro: Embedded Machine Learning on TinyML System.,” 2021.

[30] A. Ignatov, R. Timofte, W. Chou, K. Wang, M. Wu, and T. Hartley, “AI Benchmark: Running Deep Neural Networks on Android Smartphones,” 2018. doi: https://doi.org/10.30595/juita.v13i2.25794.

[31] V. J. Reddi, D. Kanter, P. Mattson, J. Duke, T. Nguyen, and R. Chukka, “MLPerf Mobile Inference Benchmark,” 2022.

[32] D. Sculley, D. Golovin, E. Davydov, T. Phillips, D. Ebner, and V. Chaudhary, “Hidden Technical Debt in Machine Learning Systems,” 2015.