Patent · US Active

Fisher vectors meet neural networks: a hybrid visual classification architecture

US9514391B2 · kind B2 · utility

23Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 20, 2015
Grant dateDec 6, 2016
Priority date
Expiry dateApr 20, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/082
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In an image classification method, a feature vector representing an input image is generated by unsupervised operations including extracting local descriptors from patches distributed over the input image, and a classification value for the input image is generated by applying a neural network (NN) to the feature vector. Extracting the feature vector may include encoding the local descriptors extracted from each patch using a generative model, such as Fisher vector encoding, aggregating the encoded local descriptors to form a vector, projecting the vector into a space of lower dimensionality, for example using Principal Component Analysis (PCA), and normalizing the feature vector of lower dimensionality to produce the feature vector representing the input image. A set of mid-level features representing the input image may be generated as the output of an intermediate layer of the NN.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.