Methods and systems for automated display verification

A computer-readable medium having computer-executable instructions stored thereon that, when executed by a processing system, cause the processing system to:

• analyze an unverified image using a first layer of a convolutional neural network to identify a first plurality of kernels associated with the first layer of the convolutional neural network for the unverified image;
• analyze a reference image using the first layer of the convolutional neural network to identify a second plurality of kernels associated with the first layer of the convolutional neural network for the reference image;
• create a shared set of kernels associated with the first layer based at least in part on the first plurality of kernels and the second plurality of kernels in accordance with one or more kernel shortlisting criteria;
• extract a first feature map for the first layer of the unverified image using the first layer of the convolutional neural network and the shared set of kernels;
• extract a second feature map for the first layer of the reference image using the first layer of the convolutional neural network and the shared set of kernels;
• calculate a similarity score for the unverified image based at least in part on differences between the first feature map and the second feature map and a weighting factor associated with the first layer;
• and
• automatically validate the unverified image based at least in part on the similarity score.

A computing device comprising:

• at least one computer-readable storage medium to store computer-executable instructions;
• and
• at least one processor, coupled to the at least one computer-readable storage medium, to execute the computer-executable instructions to:
• analyze an unverified image using a first layer of a convolutional neural network to identify a first plurality of kernels associated with the first layer of the convolutional neural network for the unverified image;
• analyze a reference image using the first layer of the convolutional neural network to identify a second plurality of kernels associated with the first layer of the convolutional neural network for the reference image;
• create a shared set of kernels associated with the first layer based at least in part on the first plurality of kernels and the second plurality of kernels in accordance with one or more kernel shortlisting criteria;
• extract a first feature map for the first layer of the unverified image using the first layer of the convolutional neural network and the shared set of kernels;
• extract a second feature map for the first layer of the reference image using the first layer of the convolutional neural network and the shared set of kernels;
• calculate a similarity score for the unverified image based at least in part on differences between the first feature map and the second feature map and a weighting factor associated with the first layer;
• and
• automatically validate the unverified image based at least in part on the similarity score.