Generic visual classification with gradient components-based dimensionality enhancement
US7680341B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | May 5, 2006 |
| Grant date | Mar 16, 2010 |
| Priority date | — |
| Expiry date | Jan 14, 2029 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/274
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In an image classification system (70), a plurality of generative models (30) correspond to a plurality of image classes. Each generative model embodies a merger of a general visual vocabulary and an image class-specific visual vocabulary. A gradient-based class similarity modeler (40) includes (i) a model fitting data extractor (46) that generates model fitting data of an image (72) respective to each generative model and (ii) a dimensionality enhancer (50) that computes a gradient-based vector representation of the model fitting data with respect to each generative model in a vector space defined by the generative model. An image classifier (76) classifies the image respective to the plurality of image classes based on the gradient-based vector representations of class similarity.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.