Image recognition method
In an image recognition method executed by a computer of an image recognizer using a convolutional neural network, the convolutional neural network is a first convolutional neural network in which a fully connected layer is changed to a convolutional layer, and the method includes controlling a first convolutional neural network to acquire an input image, controlling the first convolutional neural network to estimate a center area of a recognition target in the acquired input image and to output a value indicating the estimated center area as a location of the recognition target in the input image.
1. An image recognition method executed by a computer of an image recognizer using a convolutional neural network, the convolutional neural network being a first convolutional neural network in which a fully connected layer is changed to a convolutional layer, the method comprising:
controlling the first convolutional neural network to acquire an input image including a recognition target; and
controlling the first convolutional neural network to perform a recognition process on the input image and as a result of the recognition process to
output only coordinates of two vertices on a diagonal of a rectangle surrounding the recognition target in the acquired input image,
the first convolutional neural network outputting the coordinates as a result of estimating the coordinates of two vertices on the diagonal of the rectangle surrounding the recognition target in the acquired input image, the outputted coordinates being the estimated coordinates of the two vertices on the diagonal of the rectangle as a location of the recognition target in the input image.
2. The image recognition method according to claim 1 , further comprising:
before performing the acquisition of the input image by the first convolutional neural network, controlling the first convolutional neural network to learn a weight of the first convolutional neural network by using learning data including a plurality of sets of a training image and a correct answer image, the training image including a recognition target, the correct answer image including the training image and coordinates of two vertices on a diagonal of a rectangle surrounding the recognition target in the training image and a value indicating a location of a center line indicating a center of the recognition target in the training image.
3. The image recognition method according to claim 2 , wherein the learning includes:
controlling a second convolutional neural network to output a value indicating a location of the recognition target in the training image included in the learning data, the second convolutional neural network having the same structure as that of the first convolutional neural network,
calculating an error, according to an error function, between the output value indicating the location of the recognition target and coordinates of two vertices on a diagonal of a rectangle surrounding the recognition target indicated by the correct answer image corresponding to the training image included in the learning data,
updating a weight of the second convolutional neural network based on the calculated error,
recursively performing the calculation by controlling the second convolutional neural network with the updated weight of the second convolutional neural network to again perform the outputting in the learning, and
in a case where the calculated error achieves a minimum value in the recursive calculation, ending the recursive calculation and determining the weight of the second convolutional neural network assigned when the error achieves the minimum value as the weight of the first convolutional neural network.
4. The image recognition method according to claim 3 , wherein the error function is an error function using a Euclidean distance.
5. The image recognition method according to claim 1 , wherein the recognition target is a person in the input image.