Comparative Analysis of CNN and YOLO for Aromatic Leaf Detection on Android-Based Deep Learning Applications
DOI:
https://doi.org/10.30871/jaic.v10i3.13015Keywords:
Deep Learning, Convolutional Neural Network, YOLOv11, Aromatic Leaf Detection, Image Classification, AndroidAbstract
Commonly used aromatic leaves in Indonesian cuisine include bay leaves (Syzygium polyanthum), pandan leaves (Pandanus amaryllifolius), lime leaves (Citrus hystrix), curry leaves (Murraya koenigii), and turmeric leaves (Curcuma longa). Their similar shapes, colors, and textures often make manual identification difficult. Therefore, deep learning technology can be utilized to automatically identify and detect aromatic leaf types through digital images. This study aims to analyze the performance of a Convolutional Neural Network (CNN) using the EfficientNet-B0 architecture and the YOLOv11 model with the AdamW optimizer in detecting and classifying aromatic leaves. The system is implemented using a Python Flask framework for the web based backend and Flutter for the mobile application interface on Android devices. The dataset used in this study consists of 671 digital images obtained through direct image collection and supporting datasets. The dataset is categorized into five classes: bay leaf, pandan leaf, lime leaf, curry leaf, and turmeric leaf. Furthermore, the dataset is divided into training data (89%), validation data (7%), and testing data (4%). The results show that the YOLOv11 model outperforms the CNN (EfficientNet-B0) model. YOLOv11 achieved a precision of 73.36%, recall of 84.35%, mAP50 of 83.93%, and mAP50-95 of 71.38%. Meanwhile, EfficientNet-B0 achieved a best validation accuracy of 81.40% and a test accuracy of 62.07%. Based on experimental results, YOLOv11 demonstrates higher detection confidence and more consistent performance compared to EfficientNet-B0. In addition, YOLOv11 is more suitable for mobile deployment due to its real-time object detection capability with faster inference speed, while the system is supported by a Flask based backend and a Flutter mobile application interface.
Downloads
References
[1] L. Hakim, Spices & Herbs In Community Home Gardens, no. 164. 2022.
[2] T. Muhandri, F. M. Taqi, Subarna, and D. D. Widiawati, “Drying Characteristics of Herb Leaves Using Fluidized Bed Drier and Tray Drier,” J. Teknol. dan Ind. Pangan, vol. 34, no. 2, pp. 187–199, 2023, doi: 10.6066/jtip.2023.34.2.187.
[3] A. I. Saputra, I. Weni, and U. Khaira, “Implementation of The Convolution Neural Network Method for Disease Detection in Arabica Coffe Plants Use Android Based Leaf Images,” Decod. J. Pendidik. Teknol. Inf., vol. 4, no. 1, pp. 41–51, 2023, doi: 10.51454/decode.v4i1.231.
[4] M. Ibrahim and U. Latifa, “Application of The Yolo-v8 Algorithm in Website-Based Detection of Harvest Time of Pakcoy Crops,” J. Mhs. Tek. Inform., vol. 7, no. 4, pp. 2489–2495, 2023.
[5] M. Mufid Bachri, E. D. Astuti, and H. Sibyan, “Clean Energy and Smart Technology Image Classification Recognition Of Gamelan Musical Instrument Types Using Cnn Method Android Based,” vol. 02, no. 02, pp. 56–70, 2024, [Online]. Available: https://doi.org/10.58641/
[6] M. A. A. Mosleh and A. H. Gumaei, “An Efficient Bidirectional Android Translation Prototype for Yemeni Sign Language Using Fuzzy Logic and CNN Transfer Learning Models,” IEEE Access, vol. 12, no. November, pp. 191030–191045, 2024, doi: 10.1109/ACCESS.2024.3512455.
[7] M. F. Golfantara, “Use of YOLO Algorithm for Spice Identification,” vol. 12, no. 3, pp. 3867–3873, 2024.
[8] N. Lysbetti Marpaung, R. Juan Hendri Butar-Butar, and S. Hutabarat, “(Journal of Informatics Education and Research) Implementation of Deep learning for Identification Using Transfer learning Method,” vol. 9, no. 3, pp. 348–354, 2023.
[9] A. K. Putri, S. Suroso, and A. S. Handayani, “Application of EfficiencyNet for Creating CNN Models in Sign Language Classification,” Build. Informatics, Technol. Sci., vol. 6, no. 2, pp. 758–766, 2024, doi: 10.47065/bits.v6i2.5592.
[10] F. Marpaung, F. Aulia, and R. C. Nabila, Computer Vision and Digital Image Processing. 2022. [Online]. Available: www.pustakaaksara.co.id
[11] S. Poonkuntran, R. K. Dhanraj, and B. Balusamy, Object Detection with Deep Learning Models: Principles and Applications. 2022. doi: 10.1201/9781003206736.
[12] F. Jupiter, E. S. Negara, Y. N. Kunang, and M. I. Herdiansyah, “Implementation of CNN and YOLO Algorithms to Detect Vehicle Types on Highways,” Explor. J. Sist. Inf. dan Telemat., vol. 14, no. 2, p. 110, 2023, doi: 10.36448/jsit.v14i2.3259.
[13] B. Erwanto, A. I. Pradana, and D. Hartanti, “Develoment of a Tomato Plant Disease Detection System Through Leaf Images With the You Only Look Once (YOLO) Method Based on Android,” G-Tech J. Teknol. Terap., vol. 8, no. 3, pp. 1453–1463, 2024, doi: 10.33379/gtech.v8i3.4327.
[14] N. Khairunisa, . C., and A. Jamaludin, “Comparative Analysis of CNN and YOLO Algorithms in Identifying Road Damage,” J. Inform. dan Tek. Elektro Terap., vol. 12, no. 3, 2024, doi: 10.23960/jitet.v12i3.4434.
[15] I. C. Sari, “Integration of EfficientNet-B0 Deep Learning Model for Tomato Leaf Disease Detection in Flutter Based Mobile Application,” Djtechno J. Teknol. Inf., vol. 5, no. 2, pp. 332–346, 2024, doi: 10.46576/djtechno.v5i2.4651.
[16] M. A. K. Majid and D. Ariatmanto, “Comparative Performance Analysis of YOLO11 and YOLOv8 Models in Tomato Leaf Disease Identification,” J. Bangkit Indones., vol. 14, no. 2, pp. 63–72, 2025, doi: 10.52771/bangkitindonesia.v14i2.459.
[17] B. Raharjo, Deep Learning dengan Python. 2022.
[18] S. Cong and Y. Zhou, A review of convolutional neural network architectures and their optimizations, vol. 56, no. 3. Springer Netherlands, 2023. doi: 10.1007/s10462-022-10213-5.
[19] R. Patel and S. Patel, “A comprehensive study of applying convolutional neural network for computer vision,” Int. J. Adv. Sci. Technol., vol. 29, no. 6 Special Issue, pp. 2161–2174, 2020.
[20] W. M. Ardana, “Optimization of Convolutional Neural Network Algorithm with Efficientnet-B0 and Resnet-50 Architecture for Waste Type Classification Optimasi Algoritma Convolutional Neural Network dengan Arsitektur Efficientnet-B0 dan Resnet-50 untuk Klasifikasi Jenis Sa,” vol. 5, no. October, pp. 1274–1286, 2025.
[21] “Home - Ultralytics YOLO Docs.” Accessed: Apr. 03, 2026. [Online]. Available: https://docs.ultralytics.com/
[22] D. Ardianto, J. Jasril, S. Sanjaya, L. Handayani, and F. Syafria, “Beef and Pork Image Classification Using Convolutional Neural Network (CNN) With EfficientNet-B2 Architecture and Data Augmentation,” J. Inform. Univ. Pamulang, vol. 8, no. 2, pp. 153–164, 2023, doi: 10.32493/informatika.v8i2.30587.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Yuli Safrina, Muhammad Fikry, Mukhlis Abd Muthalib
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
