Information processing apparatus, information processing method, and program

摘要

An information processing apparatus includes a network learning portion that performs learning of an appearance/position recognition network by constraining first to third weights and using a learning image, wherein the appearance/position recognition network has a foreground layer including a position node, a background layer including a background node, and an image layer including a pixel node, and is a neural network in which the position node, the background node, and the pixel node are connected to each other, and wherein the first weight is a connection weight between the position node and the pixel node, the second weight is a connection weight between the position node and the background node, and the third weight is a connection weight between the background node and the pixel node.

主权项

1. An information processing apparatus comprising:
a network learning portion that performs learning of an appearance/position recognition network by constraining a first weight, a second weight and a third weight and using a learning image, wherein the appearance/position recognition network has a foreground layer including a position node which is a neuron corresponding to a position of a foreground of the learning image, a background layer including a background node which is a neuron corresponding to a background of the learning image, and an image layer including a pixel node which is a neuron corresponding to a pixel of the learning image in which the foreground is superimposed on the background, and is a neural network in which: the position node is connected to the background node, the position node is connected to the pixel node, and the background node is connected to the pixel node, wherein the first weight is a connection weight between the position node and the pixel node, the second weight is a connection weight between the position node and the background node, and the third weight is a connection weight between the background node and the pixel node, wherein the position node outputs a value corresponding to position information which is input as an input value and indicates a position of the foreground on the learning image, wherein the background node outputs a value including weighted sum of outputs of the position node, and wherein the pixel node outputs a value including weighted sum of outputs of the position node and weighted sum of outputs of the background node.