US 11,107,189 B2 · Methods and systems using improved convolutional neural networks for image processing

Abstract

Methods and systems are disclosed using improved Convolutional Neural Networks (CNN) for image processing. In one example, an input image is down-sampled into smaller images with a smaller resolution than the input image. The down-sampled smaller images are processed by a CNN having a last layer with a reduced number of nodes than a last layer of a full CNN used to process the input image at a full resolution. A result is outputted based on the processed down-sampled smaller images by the CNN having a last layer with a reduced number of nodes. In another example, shallow CNN networks are built randomly. The randomly built shallow CNN networks are combined to imitate a trained deep neural network (DNN).

Claims19

Dependent claims

At least one non-transitory machine-readable medium including a plurality of instructions, which when executed by one or more computing devices, cause performance of a method comprising:

down-sampling an input image into smaller images with a smaller resolution than the input image;
processing the down-sampled smaller images by a convolutional neural network (CNN) including:
inputting the smaller images to a plurality of pooling layers of the CNN,
randomly selecting a subset of nodes of a last pooling layer of the plurality of pooling layers, and
inputting outputs from the subset of nodes of the last pooling layer to fully-connected layers of the CNN;
and
outputting a result of the processed down-sampled smaller images by the CNN.

4 more elements

Dependencies are inferred from the claim text.

Methods and systems using improved convolutional neural networks for image processing

Life of this patent

Methods and systems using improved convolutional neural networks for image processing

Life of this patent

Abstract

Claims19