1：Experimental Design and Method Selection:

The proposed method uses third level 2D DWT and histogram features for glaucoma diagnosis. The green channel images are extracted from the input fundus images and are decomposed by third level 2D DWT. Various histogram features namely mean, variance, skewness, kurtosis, energy and entropy have been extracted from the decomposed sub band images. The LS-SVM with RBF kernel used the normalized features for the classification.

2：Sample Selection and Data Sources:

The Rim1 image data set is used, which is publically available from the Medical Image Analysis Group (MIAG). In this paper 15 glaucoma and 15 healthy digital fundus images have been used.

3：List of Experimental Equipment and Materials:

The proposed methodology is implemented using MATLAB at 2.10 GHz with 2 GB RAM.

4：10 GHz with 2 GB RAM. Experimental Procedures and Operational Workflow:

4. Experimental Procedures and Operational Workflow: The input images are pre-processed and fed to the third level 2D DWT. 2D DWT decomposes input images in to sub band images. Histogram features are extracted from 2D DWT decomposed sub band images. These extracted features are given as input to the least square support vector machine (LS-SVM) classifier with radial basis function (RBF) kernel.

5：Data Analysis Methods:

Accuracy, sensitivity and specificity have been calculated as the performance parameters for glaucoma diagnosis.