Automated Glaucoma Detection based on LBP Representation and GLRLM Feature Extraction Method

Glaucoma is a chronic and degenerative disease that causes irreversible damage to the nerve system of an eye, due to an increase in the Intra-ocular pressure in the retina. It reduces the vision area and leads to blindness. Early detection is critical to prevent permanent vision loss. The automated analysis of medical images contributes to the increase in the performance of classifying retinal images to pathological and nonpathological. This paper presents an automated glaucoma diagnosis approach by analyzing the texture of fundus images. The analysis was performed using Local Binary Pattern descriptor to represent grayscale and channels of retinal images and applied Gray Level Run-Length Matrix to describe patterns of texture. The classification was performed using two classifiers. The proposed approach provided the best classification results with 98%, 91%, and 97% of the three versions of RIM-ONE databases using Support Vector Machine classifier. Findings showed that local binary pattern representations and concatenated gray level run length matrix features achieved high results. Consequently, proving this approach is reliable and promising.