Eye diseases classification using back propagation artificial neural network

Abstract EN

A human eye is a vital organ responsible for a person's vision.

So, theearly detection of eye diseases is essential.

The objective of this paperdeals with diagnosing of seven different external eye diseases that canbe recognized by a human eye.

These diseases cause problems either ineye pupil, in sclera of eye or in both or in eyelid.

Color histogram andtexture features extraction techniques with classification technique areused to achieve the goal of diagnosing external eye diseases.

Hue MinMax Diff (HMMD) color space is used to extract color histogram andtexture features which were fed to Back Propagation Artificial NeuralNetwork (BPANN) for classification.

The comparative study states thatthe features extracted from HMMD color space is better than otherfeatures like Histogram of Oriented Gradient (HOG) features and givethe same accuracy as features extracted directly from medical expertrecorded symptoms.

The proposed method is applied on external eyediseases data set consisting of 416 images with an accuracy rate of85.26315% , which is the major result that was achieved in this study