how can i generate input and target data set to train neural network for face recognition, i have 400, images and i want to use 80% for training and 20% for testing

i'm working on the local binary pattern (LBP) and local ternary pattern (LTP) for face recognition using feed forward neural network (multi layer perceptron) please i need your help. i'm confuse, how can i create the input data set and the target data set from this images

[Greg Heath]

I cannot help with feature extraction. However, use PATTERNNET and a validation set via the default trn/val/tst data division to prevent overtraining.

Hope this helps.

Greg