Glaucoma Detection based on Local Binary Patterns in Fundus Photographs

Maya Alsheh Ali, Thomas Hurtut , Timothée Faucon, Farida Cheriet

Accepted in SPIE Computer-Aided Diagnosis, 2014.


Glaucoma, a group of diseases that lead to optic neuropathy, is one of the most common reasons for blindness worldwide. In this paper, we propose an automatic method for glaucoma detection based on local texture features from fundus photographs. This method applies the completed modeling of Local Binary Patterns to capture representative texture features from the whole image. On a sample set of 13 glaucomatous and 28 non-glaucomatous images, our method achieves 95.1% success rate with 92.3% specificity and 96.4% sensitivity. This approach will allow an efficient and reproducible diagnosis of glaucoma from fundus photographs.