Fuzzy learning vector quantization, neural network and fuzzy systems for classification fundus eye images with wavelet transformation

The human eye is a complex organ that is essential for everyday life. The fundus is the inner surface of the eye, which lies contrary to the lens. The results of eye fundus shooting can be used to diagnose abnormalities that occur in the eye. Artificial neural networks and fuzzy systems are methods that can be used in the classification process. In this research used Levenberg-Marquardt (LM), adaptive neuro-fuzzy inference system (ANFIS), and fuzzy learning vector quantization (FLVQ) method in ANFIS clustering process for classification of retinal abdominal eye disease, Age-Related Macular Degeneration, and normal, with an input of energy coefficient, resulting from wavelet transformation process. From the results of the percentage of success of the system in the classification of disease in the eye fundus image, it appears that the system has been able to recognize the image pattern well, that is for ANFIS with lr = 0.4, mc = 0.9 is 100%, for ANFIS-FLVQ with lr = 0.9, mc = 0.1 is 100% and for LM with μ = 0.01 is 100%.