Automatic Pill Detection Using Faster R-CNN with an AlexNet Backbone

Penulis

  • Dinial Utami Nurul Qomariah Politeknik Negeri Jember
  • Ade Irma Elvira Universitas Indonesia
  • Arvita Agus Kurniasar Universitas Indonesia
  • Bima Wahyu Maulana Universitas Indonesia

DOI:

https://doi.org/10.58812/jmws.v4i12.3068

Kata Kunci:

Object Detection, Pill Detection, Faster R-CNN, AlexNet, Deep Learning

Abstrak

Object detection is a crucial component in the development of automated systems in the healthcare domain, particularly in pharmaceutical applications such as pill identification and management. One of the main challenges in image-based pill detection systems is achieving high accuracy and robust generalization under variations in pill shape, color, and illumination conditions. This study applies the Faster R-CNN framework with an AlexNet backbone to detect and classify pill objects in digital images. The model is trained using multiple epoch configurations to analyze the effect of training duration on detection performance. Experimental results show that the proposed approach achieves an accuracy of up to 98%, demonstrating strong detection capability. Increasing the number of training epochs improves the stability and consistency of pill recognition. These results indicate that AlexNet-based Faster R-CNN is effective for pharmaceutical applications, particularly in drug distribution, packaging, and pill counting systems that require high precision and reliability.

Referensi

Abdullah, M., Qomariah, D., & Farosanti, L. (2018). AUTOMATIC DETERMINATION OF SEEDS FOR RANDOM WALKER BY SEEDED WATERSHED TRANSFORM FOR TUNA IMAGE SEGMENTATION. Jurnal Ilmu Komputer Dan Informasi, 11, 52. https://doi.org/10.21609/jiki.v11i1.468

Akyon, F. C., Onur Altinuc, S., & Temizel, A. (2022). Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection. 2022 IEEE International Conference on Image Processing (ICIP), 966–970. https://doi.org/10.1109/ICIP46576.2022.9897990

Al-Hussaeni, K., Karamitsos, I., Adewumi, E., & Amawi, R. M. (2023). CNN-Based Pill Image Recognition for Retrieval Systems. Applied Sciences, 13(8). https://doi.org/10.3390/app13085050

Babasaheb, K. D. (2023). A deep learning based drug pill recognition system. 7(6).

Bates, D. W., Spell, N., Cullen, D. J., Burdick, E., Laird, N., Petersen, L. A., Small, S. D., Sweitzer, B. J., & Leape, L. L. (1997). The costs of adverse drug events in hospitalized patients. Adverse Drug Events Prevention Study Group. JAMA, 277(4), 307–311.

Chiu, Y.-J. (2024). Automated medication verification system (AMVS): System based on edge detection and CNN classification drug on embedded systems. Heliyon, 10(9), e30486. https://doi.org/10.1016/j.heliyon.2024.e30486

Chughtai, M., Raja, G., Mir, J., & Shaukat, F. (2019). An Efficient Scheme for Automatic Pill Recognition Using Neural Networks. 56, 42–48.

Cohen, J. P., Boucher, G., Glastonbury, C. A., Lo, H. Z., & Bengio, Y. (2017). Count-ception: Counting by Fully Convolutional Redundant Counting. 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 18–26. https://doi.org/10.1109/ICCVW.2017.9

Guerrouj, F. Z., Rodriguez Florez, S., El Ouardi, A., Abouzahir, M., & Ramzi, M. (2025). Quantized Object Detection for Real-Time Inference on Embedded GPU Architectures. International Journal of Advanced Computer Science and Applications, 16. https://doi.org/10.14569/IJACSA.2025.0160503

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778.

Heo, J., Kang, Y., Lee, S., Jeong, D.-H., & Kim, K.-M. (2023). An Accurate Deep Learning-Based System for Automatic Pill Identification: Model Development and Validation. Journal of Medical Internet Research, 25, e41043. https://doi.org/10.2196/41043

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25 (NIPS 2012), 1–9.

Li, L., Li, B., & Zhou, H. (2022). Lightweight multi-scale network for small object detection. PeerJ. Computer Science, 8, e1145. https://doi.org/10.7717/peerj-cs.1145

Liang, Y., Han, Y., & Jiang, F. (2022). Deep Learning-based Small Object Detection: A Survey. 432–438. https://doi.org/10.1145/3532213.3532278

Liu, J., Gao, C., Meng, D., & Hauptmann, A. G. (2018). DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5197–5206. https://doi.org/10.1109/CVPR.2018.00545

M, S., G, E. R., D, A., Akshaya, S., Uthaman, A. C., & Sridhar, S. (2023). Detection and Identification of Pills using Machine Learning Models. 2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN), 1–6. https://doi.org/10.1109/ViTECoN58111.2023.10157873

Morimoto, T., Gandhi, T., Seger, A. C., Hsieh, T., & Bates, D. (2004). Adverse drug events and medication errors: Detection and classification methods. Quality & Safety in Health Care, 13, 306–314. https://doi.org/10.1136/qhc.13.4.306

Nikouei, M., Baroutian, B., Nabavi, S., Taraghi, F., Aghaei, A., Sajedi, A., & Ebrahimi Moghaddam, M. (2025). Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applications. https://doi.org/10.48550/arXiv.2503.20516

Pillbox. (2025). Pillbox - Archived Data. Open Data Portal.

Qomariah, D. U. N., Tjandrasa, H., & Alam, B. R. (2021). Hemorrhage Segmentation in Retinal Images Using Modified FCN-8. 2021 Fourth International Conference on Vocational Education and Electrical Engineering (ICVEE), 1–6. https://doi.org/10.1109/ICVEE54186.2021.9649686

Qomariah, D. U. N., Tjandrasa, H., & Elvira, A. I. (2025). Retinal Blood Vessel Segmentation Based on Encoder and Decoder Networks Using Weighted Cross Entropy Loss Function. ADALAH, 9(6).

Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031

S.MANIKANDAN, M., KUMAR, A., KUMAR, V., NITHISH, V., & KRISHNA, G. (2025). AUTOMATED PILL RECOGNITION AND CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS. International Journal of Engineering Research and Science & Technology, 21, 654–660. https://doi.org/10.62643/ijerst.2025.v21.n4.pp654-660

Tan, L., Huangfu, T., Wu, L., & Chen, W. (2021). Comparison of RetinaNet, SSD, and YOLO v3 for real-time pill identification. BMC Medical Informatics and Decision Making, 21(1), 324. https://doi.org/10.1186/s12911-021-01691-8

Yang, X., Yan, J., Liao, W., Yang, X., Tang, J., & He, T. (2023). SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), 2384–2399. https://doi.org/10.1109/TPAMI.2022.3166956

Unduhan

Dimensions

Diterbitkan

2025-12-30

Terbitan

Vol 4 No 12 (2025): Jurnal Multidisiplin West Science

Bagian

Artikel

Lisensi

Hak Cipta (c) 2025 Dinial Utami Nurul Qomariah, Ade Irma Elvira, Arvita Agus Kurniasar, Bima Wahyu Maulana

Creative Commons License

Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.

Cara Mengutip

Automatic Pill Detection Using Faster R-CNN with an AlexNet Backbone. (2025). Jurnal Multidisiplin West Science, 4(12), 2597-2604. https://doi.org/10.58812/jmws.v4i12.3068