US 10,872,230 B2 · Low-cost face recognition using Gaussian receptive field features

Abstract

Methods and systems may provide for facial recognition of at least one input image utilizing hierarchical feature learning and pair-wise classification. Receptive field theory may be used on the input image to generate a pre-processed multi-channel image. Channels in the pre-processed image may be activated based on the amount of feature rich details within the channels. Similarly, local patches may be activated based on the discriminant features within the local patches. Features may be extracted from the local patches and the most discriminant features may be selected in order to perform feature matching on pair sets. The system may utilize patch feature pooling, pair-wise matching, and large-scale training in order to quickly and accurately perform facial recognition at a low cost for both system memory and computation.

Claims25

Dependent claims

A system comprising:

a memory device to store an input image;
a processor including,
an image input interface to receive the input image,
a pre-processor to model the input image to yield a multi-channel image,
a feature extractor to extract a set of features based on the multi-channel image,
a feature selector to select one or more features from the set of features of the multi-channel image, wherein the one or more features are selected based on an ability to differentiate features,
a feature matcher to match the one or more features to a learned feature set, and
a similarity detector to determine whether the one or more features meet a pre-defined similarity threshold.

5 more elements

Dependencies are inferred from the claim text.

Low-cost face recognition using Gaussian receptive field features

Life of this patent

Low-cost face recognition using Gaussian receptive field features

Life of this patent

Abstract

Claims25