This study explores modern techniques to enhance cataract detection accuracy, including ensemble learning, hybrid feature extraction, and a Modified Random Forest classifier. Traditional methods face limitations in feature extraction and classification, which are addressed through a hybrid approach combining LBP, GLCM, and CNN. LBP detects early-stage cataracts, GLCM captures spatial relationships, and CNN extracts deep structural features, improving image representation. The proposed Modified Random Forest (MRF) classifier integrates feature weighting and optimized decision thresholds, reducing noise and enhancing classification accuracy. Feature selection with Recursive Feature Elimination (RFE) and Principal Component Analysis (PCA) minimizes overfitting and computational cost. Ensemble learning methods such as Bagging, Boosting, and Stacking further improve model robustness, with Stacking achieving 93% accuracy and high ROC-AUC for early-stage detection. However, computational complexity remains a challenge, particularly for deployment in clinical settings. KNN and SVM models underperform without feature selection, highlighting the need for careful preprocessing. Despite these challenges, the proposed techniques significantly improve cataract detection, ensuring better generalization across datasets.

1.    Ismail WN, Alsalamah HA. A novel CatractNetDetect deep learning model for effective cataract classification through data fusion of fundus images. Discover Artificial Intelligence. 2024; 4(1): 54. doi: 10.1007/s44163-024-00155-y

2.    Jindal I, Gupta P, Goyal A. Cataract detection using digital image processing. 2019 global conference for advancement in technology (gcat). IEEE publishing; 2019. pp. 1–4. doi: 10.1109/gcat47503.2019.8978316

3.    Grammatikopoulou M, Evangello F, Abdolrahim K, et al. CaDIS: Cataract dataset for surgical RGB-image segmentation. Medical Image Analysis. 2021; 71 (2021): 102053. doi: 10.1016/j.media.2021.102053

4.    Giap BD, Srinivasan K, Mahmoud O, et al. Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery. IEEE Journal of Biomedical and Health Informatics. 2024; 28(3): 1599–1610. doi: 10.1109/jbhi.2023.3345837

5.    Zhang, L, Li J, Han H, et al. Automatic cataract detection and grading using deep convolutional neural network. In: Proceeding of 2017 IEEE 14th international conference on networking, sensing and control (ICNSC); 2017. pp. 60–65.

6.    Cruz-Vega I, Hans I, Juan M, et al. Nuclear cataract database for biomedical and machine learning applications. IEEE Access. 2023; 11(2023): 107754–107766. doi: 10.1109/ACCESS.2023.3312616

7.    Manuel FME, Saide SM, Ali FDMA, et al. Ocular Cataract Identification Using Deep Convolutional Neural Networks. In:Proceeding of 2023 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD); 2023. pp. 1–5.

8.    Zhang X, Xiao Z, Yang B, et al. Regional context-based recalibration network for cataract recognition in AS-OCT. Pattern Recognition. 2024; 147: 110069. doi: 10.1016/j.patcog.2023.110069

9.    Cheng J, Li Z, Gu Z, et al. Structure-preserving guided retinal image filtering and its application for optic disk analysis. IEEE Transactions on Medical Imaging. 2018; 37(11): 2536–2546. doi: 10.1109/tmi.2018.2838550

10.    Navatha N, Revanth A, Pramod C, et al. High-Accuracy Cataract Detection using Enhanced VGG-19 CNN and Adam Optimizer[C]//2024 IEEE 6th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA); 2024. pp. 117–122.

11.    Shi X, Zhang D, Liang S, et al. Real-time corneal image segmentation for cataract surgery based on detection framework. International Journal of Computer Assisted Radiology and Surgery. 2025; 1-10. doi: 10.1007/s11548-025-03506-x

12.    Vadduri M. DAUCD: Deep attention U-Net for cataract detection leveraging CNN frameworks. International Journal of Intelligent Engineering & Systems. 2025; 18(1): 184–197. doi: 10.22266/ijies2025.0229.15

13.    Xiong Y, He Z, Niu K, et al. Automatic cataract classification based on multi-feature fusion and SVM. In: Proceeding of 2018 IEEE 4th International Conference on Computer and Communications (ICCC); 2018. pp. 1557–1561.

14.    Zhang L, Li J, Han H, et al. Automatic cataract detection and grading using deep convolutional neural network. In: Proceeding of 2017 IEEE 14th international conference on networking, sensing and control (ICNSC); 2017. pp. 60–65.

15.    Imran A, Li J, Pei Y, et al. Cataract Detection and Grading with Retinal Images Using SOM-RBF Neural Network. In: Proceeding of 2019 IEEE Symposium Series on Computational Intelligence (SSCI); 2019. pp. 2626–2632.

16.    Manchalwar MD, Warhade KK. Histogram of Oriented Gradient based Automatic Detection of Eye Diseases. 2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA); 2017. pp. 1–5. 

17.    Faizal S, Rajput CA, Tripathi R, et al. Automated cataract disease detection on anterior segment eye images using adaptive thresholding and fine tuned inception-v3 model. Biomedical Signal Processing and Control. 2023; 82: 104550. doi: 10.1016/j.bspc.2022.104550

18.    Laia F H, Buulolo P. Application of svm and lda models in eye image-based cataract detection system. Jurnal ICT: Information and Communication Technologies, 2024, 15(2): 98–106.

19.    Sevani N, Tampubolon H, Wijaya J, et al. A Study of Convolution Neural Network Based Cataract Detection with Image Segmentation. In: Proceeding of 2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT); 2022. pp. 216–221. 

20.    Syarifah MA, Bustamam A, Tampubolon PP. Cataract classification based on fundus image using an optimized convolution neural network with lookahead optimizer. In: Proceeding of AIP Conference Proceedings; 2020.

21.    Cao L, Li H, Zhang Y, et al. Hierarchical method for cataract grading based on retinal images using improved Haar wavelet. Information Fusion. 2020; 53: 196–208. doi: 10.1016/j.inffus.2019.06.022

22.    Gu H, Guo Y, Gu L, et al. Deep learning for identifying corneal diseases from ocular surface slit-lamp photographs. Scientific Reports. 2020; 10(1): 17851. doi: 10.1038/s41598-020-75027-3