The capacity of a specially designed neural network for familiarity recognition and recollection has been compared. The recognition is based on calculating some quantity interpreted as the familiarity of a pattern. The familiarity is calculated using a modified Hopfield energy function in which the value of the inner sum is replaced by the sign of this value. This replacement makes the calculation of familiarity compatible with the basic dynamic equations of the Hopfield network and is reduced actually to the calculation of the scalar product of the neural network state vectors at two successive time steps.