Klasifikasi Mata Katarak dan Mata Normal Menggunakan Algoritma Dasar Convolutional Neural Network (CNN)
DOI:
https://doi.org/10.47747/jpsii.v6i3.2758Keywords:
Classification, CNN, Deep Learning, Cataract, Normal EyesAbstract
Eye diseases encompass a wide range of conditions, from mild visual impairments to complete blindness, with cataracts being one of the leading causes. Despite advances in medical imaging, automated classification of cataract versus normal eye images remains a challenging task. This study proposes a classification method using a Convolutional Neural Network (CNN) to distinguish between cataract-affected eyes and normal eyes accurately. The approach involves collecting and preprocessing a labeled dataset, extracting features such as color and vein patterns (including average RGB values), and training the CNN model with optimized parameters. Experimental results demonstrate that the proposed model achieves a high classification accuracy of 95.1%. These findings indicate that CNN-based image classification is a promising tool for supporting automated cataract detection and early diagnosis
References
O. Bernabe, E. Acevedo, A. Acevedo, R. Carreno, and S. Gomez, “Classification of eye diseases in fundus images,” IEEE Access, vol. 9, pp. 123456–123470, 2021.
A. K. Akan, M. A. Genc, and F. T. Yarman Vural, “Just noticeable difference for machines to generate adversarial images,” in Proc. International Conference on Image Processing (ICIP), 2020.
S. K. Venu and S. Ravula, "Evaluation of deep convolutional generative adversarial networks for data augmentation of chest X-ray images," [Online].
S. Niu, B. Li, X. Wang, and H. Lin, "Defect image sample generation with GAN for improving defect recognition," [Online].
S. Menon et al., "Generating realistic COVID-19 x-rays with a mean teacher + transfer learning GAN," in Proc. 2020 IEEE International Conference on Big Data (Big Data), 2020.
X. Zeng, L. W. Xu, and C. Ji, "Generating diagnostic report for medical image by high-middle-level visual information incorporation on double deep learning models," Computer Methods and Programs in Biomedicine, 2020.
G. J. Horng, M. X. Liu, and C. C. Hsu, "The anomaly detection mechanism using deep learning in a limited amount of data for fog networking," Computer Communications, 2021.
T. Shen, C. Gou, F. Y. Wang, Z. He, and W. Chen, "Learning from adversarial medical images for X-ray breast mass segmentation," Computer Methods and Programs in Biomedicine, 2019.
L. Bargsten and A. Schlaefer, "SpeckleGAN: a generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing," International Journal of Computer Assisted Radiology and Surgery, 2020.
S. Wang et al., "Diabetic retinopathy diagnosis using multichannel generative adversarial network with semisupervision," IEEE Transactions on Automation Science and Engineering, 2021.
T. D. Pham, "Geostatistical simulation of medical images for data augmentation in deep learning," IEEE Access, 2019.
L. Wang, D. Guo, G. Wang, and S. Zhang, “Annotation-efficient learning for medical image segmentation based on noisy pseudo labels and adversarial learning,” IEEE Transactions on Medical Imaging, vol. 40, no. 8, pp. 2104–2115, 2021.
L. Li, C. Wang, H. Zhang, and B. Zhang, “SAR image ship object generation and classification with improved residual conditional generative adversarial network,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022.
M. M. Islam, A. K. M. S. A. Rabby, H. R. M. Arfin, and S. A. Hossain, “Majedul Md Islam A. K. M. Shahahriar Azad Rabby Hafizur Rahman Md Arfin Syed Akhter Hossain,” in Proc. 10th Int. Conf. Computing, Communication and Networking Technologies (ICCCNT), 2019.
Satria, R. L., & Wathan, M. H. (2023). ConFruit: Effective Fruit Classification Using CNN Algorithm. International Journal of Informatics and Computation, 5(1), 10–18. https://doi.org/10.35842/ijicom.v5i1.44
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jurnal Pengembangan Sistem Informasi dan Informatika
This work is licensed under a Creative Commons Attribution 4.0 International License.
