Methods and apparatus for model-based visual descriptors compression
US10021395B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 27, 2015 |
| Grant date | Jul 10, 2018 |
| Priority date | — |
| Expiry date | Sep 8, 2036 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N19/94
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A particular implementation determines parameters of a generative probabilistic model from visual descriptors extracted from at least one image. The extracted visual descriptors are quantized and encoded using the model-based arithmetic encoding to be stored or for transmission to a decoder. The model parameters are also stored to be available to a decoder, or transmitted directly to a decoder. A decoder uses the stored, or received, model parameters to reconstruct the generative probabilistic model and then to decode the visual descriptors. The visual descriptors are used for image analysis tasks, such as image retrieval or object detection. A particular implementation uses a Gaussian mixture model as a generative probabilistic model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.