Mix histogram and gray level co-occurrence matrix to improve glaucoma prediction machine learning

Glaucoma is an eye disease that the second leading cause of blindness. Examination glaucoma by ophthalmologist usually done observing retinal image directly. Observations from one doctor to another may differ, depending on their educational background, experience, and psychological condition. Therefore, a detection system based digital processing needed. The or classification with strongly influenced feature extraction method, selection, type features used. Many researchers have carried out various kinds for systems whose accuracy needs be improved. In general, there are two groups features, namely morphological non-morphological (image-based features). this study, it proposed detect using texture GLCM histograms, combined GLCM-histogram method. method uses 5 Histogram 6 features. To distinguish between non-glaucoma eyes, multi-layer perceptron (MLP) artificial neural network model serves as classifier. data used in study consisted 136 fundus images (66 normal 70 affected glaucoma). performance obtained approach 93.4%, sensitivity 86.6%, specificity 100%.