Hybrid Algorithm Developmental Strategies For Eye Disease Detection in Human Beings Using MLT Using Local Binary Pattern For The Extraction Of Features From Image Texture For Obtaining of Cup & Disc Ratio (CDR) For Moderate Case
DOI:
https://doi.org/10.51483/IJAIML.2882Keywords:
Hybrid Algorithm, Chronic Disease Detection, Machine Learning Techniques (MLT), Local Binary Pattern (LBP), Feature Extraction, Image Texture Analysis, Cup and Disc Segmentation, Cup-to-Disc Ratio (CDR), Ophthalmology, Medical Image Processing, Automated Screening, Diagnostic Accuracy, Early Disease Detection, Computer-Aided Diagnosis, Biomedical Engineering.Abstract
In this research paper, we present the hybrid algorithm developmental strategies for eye disease detection in human beings using MLT using local multi-level binary pattern (LMBP) for the detection of disease using cup and disc ratio (CDR) for moderate disease along with its simulation results. This work explores hybrid algorithm development strategies aimed at improving the detection of chronic diseases in humans by leveraging machine learning techniques (MLT) and advanced image processing. Specifically, the approach utilizes the Local Binary Pattern (LBP) method for extracting detailed texture features from medical images, with a focus on identifying the cup and disc regions—crucial for assessing the Cup-to-Disc Ratio (CDR), an important biomarker in ophthalmology. By integrating LBP-based texture extraction with robust machine learning models, the proposed framework enhances the accuracy and reliability of chronic disease diagnostics, paving the way for more effective, automated screening processes in clinical settings. This fusion of feature extraction and data-driven analysis demonstrates significant promise in advancing early detection and management of various chronic conditions.
