Glaucomatous image Classification using Wavelet Transform

Abstract

Wavelet Transforms is a part of large community of mathematical function approximation method, they are being increasing and being deployed in image processing for segmentation, filtering, classification etc. This work is based on image classification with the use of single level Discrete Wavelet Transform (DWT). Wavelets have been employed in many applications of signal processing. The texture features within images are extracted for accurate and efficient Glaucoma Classification. Energy is distributed over the wavelet sub-bands to find these important texture features. The discriminatory potential of wavelet features obtained from the daubechies (db3), symlets (sym3), and reverse biorthogonal (rbio3.3, rbio3.5, and rbio3.7) wavelet filters. We propose a technique to extract energy features obtained using 2-D discrete wavelet transform. The energy features obtained from the detailed coefficients can be used to distinguish between normal and glaucomatous images with very high accuracy. The effectiveness is evaluated using K-NN classifier by taking 30 normal and glaucoma images, 15 images are used for training and 15 images for testing.