Recognition of Down syndromes using image analysis

Abstract

In the present study, image processing algorithms have been applied to face photos of the patients diagnosed by down syndrome for development of a pre-diagnostic tool. The data sets evaluated in this study are collected from children whose ages range from 5 to 6. In each of normal syndrome groups; 18 photos of the children are analyzed. The critical points on faces are obtained by using elastic face bunch graph method for all photos. 10 feature vectors are applied to artificial neural network for both training and classification. In results Down syndrome can be pre-diagnosed with the accuracy of 68,7 percent by using neural network.