Fisher vectors meet neural networks: a hybrid visual classification architecture
US9514391B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 20, 2015 |
| Grant date | Dec 6, 2016 |
| Priority date | — |
| Expiry date | Apr 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.