Masoumeh Siar - Department of Computer Science Science and Research Branch, Islamic Azad University Tehran, Iran
Mohammad Teshnehlab - Department of Electrical Engineering K.N. Toosi University of Technology Tehran, Iran

In this paper, the convolutional neural network(CNN), used for two applications, age and gender classificationfrom brain magnetic resonance images (MRI). The images usedin this paper are from the imaging centers and collected by theauthor of the paper. In this paper, the Alexnet model is used inCNN architecture. In the structure of the CNN, four categorymethod are used such as the Support Vector Machine (SVM),classifier, Decision Tree (DT) classifier, Radial Basis Function(RBF) classifier and Softmax classifier, have been used. In thefirst application, the CNN is used to gender Classification frombrain MRI. The CNN that the last layer has been used tocategorize the images into two classes. The accuracy of the CNNis obtained by the SVM classifier 96.98%, Softmax classifier96.75%, RBF classifier 95.51% and the DT classifier 95.82%. Inthe second application, the CNN is used to age classification andfrom brain MRI. The CNN that the last layer has been used tocategorize the images into five age classes. The accuracy of theCNN is obtained by the Softmax classifier 79.40%, SVMclassifier 75.28%, RBF classifier 54.32% and the DT classifier48.61%.

component; Convolutional neural network, Gender classification, age classification, feature extraction, magneticresonance images