Enhancing Convolutional Neural Network Accuracy for Herbal Leaf Classification Using Squeeze and Excitation Attention

Ragil Gigih Utomo; Rodhiyah Mardhiyyah

doi:10.58526/jsret.v4i4.938

Authors

Ragil Gigih Utomo University of Technology Yogyakarta
Rodhiyah Mardhiyyah University of Technology Yogyakarta, Yogyakarta, Indonesia

DOI:

https://doi.org/10.58526/jsret.v4i4.938

Keywords:

attention mechanism, Deep Learning, Image Classification, Convolutional Neural Network

Abstract

Accurate identification of herbal plant species is crucial for human health, but remains challenging, even for experts. This study addressed this need by developing a Convolutional Neural Network (CNN) model integrated with an attention mechanism for reliable herbal leaf classification. The research implemented the MobileNetV2 architecture, which was enhanced by incorporating the Squeeze-and-Excitation (SE) attention module. The dataset consisted of 1,500 images across 10 classes of herbal leaves, split into 80% for training, 10% for validation, and 10% for testing. Both the native CNN and the enhanced CNN (CNN-AM) models were trained using TensorFlow and evaluated using standard metrics like accuracy, precision, recall, and F1-score. The comparison results decisively demonstrated the effectiveness of the attention mechanism. Integrating Squeeze-and-Excitation significantly improved performance. The average accuracy of the model increased from 68% to 72%, while the average loss decreased from 1.03 to 1.02. The best-performing CNN-AM model achieved a strong 86% accuracy with a 0.53 loss. These findings confirm that the Squeeze-and-Excitation attention mechanism effectively enhances herbal leaf classification performance, offering a promising foundation for developing reliable and efficient identification systems.

Downloads

Download data is not yet available.

References

Al-Zoghby, A. M., Al-Awadly, E. M. K., Moawad, A., Yehia, N., & Ebada, A. I. (2023). Dual Deep CNN for Tumor Brain Classification. Diagnostics 2023, Vol. 13, Page 2050, 13(12), 2050. https://doi.org/10.3390/DIAGNOSTICS13122050

Atha, A. M., & Zuliarso, E. (2022). Herbal Plants Detection Specifically For Skin And Hair Diseases Using The Convolutional Neural Network (CNN) and Tensorflow. JUPITER: Jurnal Penelitian Ilmu Dan Teknologi Komputer, 14(2-a), 01–10. https://doi.org/10.5281./4736/5.jupiter.2022.10

Azlah, M. A. F., Chua, L. S., Rahmad, F. R., Abdullah, F. I., & Alwi, S. R. W. (2019). Review on Techniques for Plant Leaf Classification and Recognition. Computers 2019, Vol. 8, Page 77, 8(4), 77. https://doi.org/10.3390/COMPUTERS8040077

Azmi, K., Defit, S., & Putra Indonesia YPTK Padang Jl Raya Lubuk Begalung-Padang-Sumatera Barat, U. (2023). Implementasi Convolutional Neural Network (CNN) Untuk Klasifikasi Batik Tanah Liat Sumatera Barat. JURNAL UNITEK, 16(1), 28–40. https://doi.org/10.52072/unitek.v16i1.504

Basri, H., Purnawansyah, P., Darwis, H., & Umar, F. (2023). Klasifikasi Daun Herbal Menggunakan K-Nearest Neighbor dan Convolutional Neural Network dengan Ekstraksi Fourier Descriptor. Jurnal Teknologi Dan Manajemen Informatika, 9(2), 79–90. https://doi.org/10.26905/JTMI.V9I2.10350

Borman, R. I., Rossi, F., Jusman, Y., Rahni, A. A. A., Putra, S. D., & Herdiansah, A. (2021). Identification of Herbal Leaf Types Based on Their Image Using First Order Feature Extraction and Multiclass SVM Algorithm. 2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System, ICE3IS 2021, 12–17. https://doi.org/10.1109/ICE3IS54102.2021.9649677

Darmawati, A. R. R., Purnawansyah, Darwis, H., & Ilmawan, L. B. (2024). Digital Image Classification of Herbal Leaves Using Support Vector Machine and Convolutional Neural Network with Fourier Descriptor Features. CSRID (Computer Science Research and Its Development Journal), 16(1), 01–12. https://doi.org/10.22303/CSRID-.16.1.2024.01-12

Daun, K., Berdasarkan, H., Bentuk, F., Menggunakan, D. T., Meiriyama, K., Devella, S., & Adelfi, S. M. (2022). Klasifikasi Daun Herbal Berdasarkan Fitur Bentuk dan Tekstur Menggunakan KNN. JATISI (Jurnal Teknik Informatika Dan Sistem Informasi), 9(3), 2573–2584. https://doi.org/10.35957/JATISI.V9I3.2974

Goeau, H., Bonnet, P., & Joly, A. (2025). Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017). https://arxiv.org/pdf/2509.20856

Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2021). Attention Mechanisms in Computer Vision: A Survey. Computational Visual Media, 8(3), 331–368. https://doi.org/10.1007/s41095-022-0271-y

Hidayat, R., Toyib, R., Apridiansyah, Y., Reswan, Y., Bali, J., Bali, K., Segara, T., & Bengkulu, K. (2025). KLASIFIKASI CITRA DAUN HERBAL DENGAN KHASIATNYA UNTUK PENGOBATAN MENGGUNAKAN JARINGAN SYARAF TIRUAN (BACKPROPAGATION). JATI (Jurnal Mahasiswa Teknik Informatika), 9(4), 5571–5577. https://doi.org/10.36040/JATI.V9I4.13860

Kardakis, S., Perikos, I., Grivokostopoulou, F., & Hatzilygeroudis, I. (2021). Examining Attention Mechanisms in Deep Learning Models for Sentiment Analysis. Applied Sciences 2021, Vol. 11, Page 3883, 11(9), 3883. https://doi.org/10.3390/APP11093883

Khatib Sulaiman, J., Perbandingan Kombinasi GMI, S., CNN pada Klasifikasi Daun Herbal Alfitriana Riska, dan, Darwis, H., & Astuti, W. (2023). Studi Perbandingan Kombinasi GMI, HSV, KNN, dan CNN pada Klasifikasi Daun Herbal. The Indonesian Journal of Computer Science, 12(3). https://doi.org/10.33022/IJCS.V12I3.3210

Lu, J., Tan, L., & Jiang, H. (2021). Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification. Agriculture 2021, Vol. 11, Page 707, 11(8), 707. https://doi.org/10.3390/AGRICULTURE11080707

Marpaung, N. L., Butar, R. J. H. B., & Hutabarat, S. (2023). Implementasi Deep learning untuk Identifikasi Daun Tanaman Obat Menggunakan Metode Transfer learning. JEPIN (Jurnal Edukasi Dan Penelitian Informatika), 9(3), 348–354. https://jurnal.untan.ac.id/index.php/jepin/article/view/63895

Minarno, A. E., Wicaksono, G. W., Azhar, Y., & Hasanuddin, M. Y. (2022). Indonesian Herb Leaf Dataset 3500. 1. https://doi.org/10.17632/S82J8DH4RR.1

Mirtaheri, S. L., & Shahbazian, R. (2022). Machine Learning : Theory to Applications. Machine Learning Theory to Applications. https://doi.org/10.1201/9781003119258

Mujahid, P. E., Manik, R., Simbolon, J. S., Sinaga, M. R. R. S., Aisyah, S., Nababan, M., & Harmaja, O. J. (2024). Herbal Leaf Image Classification Using Convolutional Neural Network (CNN). Jurnal Sistem Informasi Dan Ilmu Komputer, 8(1), 52–68. https://doi.org/10.34012/JURNALSISTEMINFORMASIDANILMUKOMPUTER.V8I1.5145

Nguyen, H. T., Li, S., & Cheah, C. C. (2022). A Layer-Wise Theoretical Framework for Deep Learning of Convolutional Neural Networks. IEEE Access, 10, 14270–14287. https://doi.org/10.1109/ACCESS.2022.3147869

Noviana, L. P. R., & Nugraha, I. N. B. S. (2023). Perbandingan Klasifikasi Citra Daun Herbal Menggunakan Metode Logistic Regression dan Decision Tree Classifier Berdasarkan Fitur (Warna, GLCM, Bentuk). JITU : Journal Informatic Technology And Communication, 7(2), 126–133. https://doi.org/10.36596/JITU.V7I2.1241

Perbandingan Klasifikasi Citra Daun Herbal Menggunakan Metode Logistic Regression dan Decision Tree Classifier Berdasarkan Fitur (Warna, GLCM, Bentuk) | JITU : Journal Informatic Technology And Communication. (n.d.). Retrieved September 6, 2025, from https://ejournal.uby.ac.id/index.php/jitu/article/view/1241

Pratama, A., Sugiharto, T., & Novantara, P. (2025). Classification of Avocado Plant Varieties Based on Leaf Shape Using CNN Algorithm. Jurnal CoSciTech (Computer Science and Information Technology), 6(2), 120–128. https://doi.org/10.37859/COSCITECH.V6I2.9474

Pujiati, R., & Rochmawati, N. (2022). Identifikasi Citra Daun Tanaman Herbal Menggunakan Metode Convolutional Neural Network (CNN). Journal of Informatics and Computer Science (JINACS), 3(03), 351–357. https://doi.org/10.26740/JINACS.V3N03.P351-357

Purnama, I. N. (2020). HERBAL PLANT DETECTION BASED ON LEAVES IMAGE USING CONVOLUTIONAL NEURAL NETWORK WITH MOBILE NET ARCHITECTURE. JITK (Jurnal Ilmu Pengetahuan Dan Teknologi Komputer), 6(1), 27–32. https://doi.org/10.33480/JITK.V6I1.1400

Rathore, S., Niazi, T., Iftikhar, M. A., & Chaddad, A. (2020). Glioma Grading via Analysis of Digital Pathology Images Using Machine Learning. Cancers 2020, Vol. 12, Page 578, 12(3), 578. https://doi.org/10.3390/CANCERS12030578

Ruan, T., & Zhang, S. (2024). Towards understanding how attention mechanism works in deep learning. https://arxiv.org/pdf/2412.18288

Saifullah, S., Suryotomo, A. P., & Yuwono, B. (2021). Fish Detection Using Morphological Approach Based-on K-Means Segmentation. Compiler, 10(1). https://doi.org/10.28989/compiler.v10i1.946

Suhardin, I., Patombongi, A., Muhammad Islah, A., & Catur Sakti Kendari Jl Abdullah, S. H. (2021). MENGIDENTIFIKASI JENIS TANAMAN BERDASARKAN CITRA DAUN MENGGUNAKAN AlGORITMA CONVOLUTIONAL NEURAL NETWORK. Simtek : Jurnal Sistem Informasi Dan Teknik Komputer, 6(2), 100–108. https://doi.org/10.51876/SIMTEK.V6I2.101

SWATHI, N., HARI, DR. N. S., & VEDANTAM, DR. R. (2025). SATELLITE IMAGE CLASSIFICATION: A DEEP LEARNING APPROACH USING MOBILENETV2. International Journal of Innovative Research in Technology, 12(2), 3856–3862. https://ijirt.org/article?manuscript=182947

Taye, M. M. (2023). Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions. Computation 2023, Vol. 11, Page 52, 11(3), 52. https://doi.org/10.3390/COMPUTATION11030052

Wang, Z., Wang, P., Liu, K., Wang, P., Fu, Y., Lu, C.-T., Aggarwal, C. C., Pei, J., & Zhou, Y. (2024). A Comprehensive Survey on Data Augmentation. https://arxiv.org/pdf/2405.09591

Zhu, H., Xie, C., Fei, Y., & Tao, H. (2021). Attention Mechanisms in CNN-Based Single Image Super-Resolution: A Brief Review and a New Perspective. Electronics 2021, Vol. 10, Page 1187, 10(10), 1187. https://doi.org/10.3390/ELECTRONICS10101187