AI system fuses CNN and GLCM features for 95% accurate cataract grading

Researchers have developed a novel system for classifying cataract severity using a fusion of deep learning and traditional image processing techniques. This hybrid approach combines features from a Convolutional Neural Network (CNN) with handcrafted Grey-Level Co-occurrence Matrix (GLCM) descriptors. The system achieved a high accuracy of 95.0% on a test set of 300 images, outperforming both CNN-only and texture-only baselines. This method offers a cost-effective solution for cataract grading, suitable for deployment in primary care and telemedicine settings without requiring specialized hardware or GPU acceleration. AI

IMPACT Enables low-cost, accessible AI-powered diagnostic tools for eye conditions in resource-limited settings.

RANK_REASON The cluster contains an academic paper detailing a new methodology for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• BGM-109G Ground Launched Cruise Missile
• CNN
• convolutional neural network
• DagsHub
• graphics processing unit
• Hugging Face
• radial basis function
• support vector machine

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →