Convolution Neural Network for Face Similarity Estimation

We present a convolution neural network used to determine face similarity given two images as input, i.e. a face identification task. The main focus is on the shape of the input data. We propose schemes where two pictures are connected in four different ways. The input sample is concatenated horizontally and vertically, giving the first two schemes. The other two input shapes include the intertwining by column and by row. Analysis of precision versus recall has been provided for each input schema. Some of the traditional approaches focus on deriving the feature vectors of an individual and then comparing the obtained vectors with each other. Our paper offers a new approach to face identification problems where two images of an individual are directly fed to the neural network. Then, it is the task of the neural network to determine the similarity score.