1：Experimental Design and Method Selection:

The methodology includes preprocessing, Gabor filtering using different orientation and scale, textural feature extraction using Gray Level Co-occurrence Matrix (GLCM), classification using Support Vector Machine (SVM) and K Nearest Neighbor (KNN). Performance of the classifier is evaluated by applying data reduction using Principal Component Analysis (PCA) as well as data selection using Genetic Algorithm (GA).

2：Sample Selection and Data Sources:

Fundus images collected from Sushrutha Eye Hospital, Mysuru, Karnataka, India. The database consists of 70 images out of which 40 are normal and 30 have drusen.

3：List of Experimental Equipment and Materials:

Not explicitly mentioned.

4：Experimental Procedures and Operational Workflow:

Input images are RGB images. Green channel images are extracted and used for further processing. Images are resized to 160x160 pixels. Adaptive histogram equalization is applied for contrast enhancement. Gabor filtering is applied with different orientations and scales. Textural features are extracted using GLCM. Classification is performed using SVM and KNN. Performance is evaluated using 10-fold cross validation technique.

5：Data Analysis Methods:

Performance measures include sensitivity, specificity, accuracy, misclassification rate, Positive Predictive Value, Negative Predictive Value, and Youden’s Index.