Survey of retinal image analysis for glaucomatous classification and exudates detection

This paper proposes an empirical study on glaucomatous image classification using texture features within images based on feature ranking and neural network. In addition, an efficient detection of exudates for retinal vasculature disorder analysis is performed. The classification plays an important role in detection of some diseases in early stages, such as diabetes, which can be performed by comparison of the states of retinal blood vessels. The Energy distributions over wavelet subbands are applied to find these important texture features. This system investigates the discriminatory potential of wavelet features obtained from the daubechies (db3), symlets (sym3), and bi-orthogonal (bio3.3, bio3.5, and bio3.7) wavelet filters. The energy obtained from the detailed coefficients can be used to distinguish between normal and glaucomatous images with very high accuracy. This performance will be done by artificial neural network model. The exudates are also detected effectively from the retina fundus image using segmentation algorithms. Finally the segmented defect region will be post processed by morphological processing technique for smoothing operation.