Recognition of objects in images with equivariance or invariance in relation to the object size

A non-transitory machine-readable data medium on which is stored a computer program configured to recognize at least one object in at least one input image, the computer program, when executed by at least one computer, causing the at least one computer to perform the following steps:

• processing a template image of the object by a first convolutional neural network to form at least one template feature map;
• processing the input image by a second convolutional neural network to form at least one input feature map;
• comparing the at least one template feature map to the at least one input feature map;
• and
• evaluating, from a result of the comparison whether the object is contained in the input image;
• wherein the first and second convolutional neural networks each contain multiple convolutional layers, and at least one of the convolutional layers is at least partially formed from at least two filters, which are convertible into one another by a scaling operation, and
• the first and second convolutional neural networks each output multiple feature maps for the template image and the input image, respectively, and in the creation of each of the multiple feature maps a different one of the filters convertible into one another predominantly participates.

A computer configured to recognize at least one object in at least one input image, the computer configured to:

• process a template image of the object by a first convolutional neural network to form at least one template feature map;
• process the input image by a second convolutional neural network to form at least one input feature map;
• compare the at least one template feature map to the at least one input feature map;
• and
• evaluate, from a result of the comparison whether the object is contained in the input image;
• wherein the first and second convolutional neural networks each contain multiple convolutional layers, and at least one of the convolutional layers is at least partially formed from at least two filters, which are convertible into one another by a scaling operation, and
• the first and second convolutional neural networks each output multiple feature maps for the template image and the input image, respectively, and in the creation of each of the multiple feature maps a different one of the filters convertible into one another predominantly participates.