QoE-driven unsupervised image categorization for optimized web delivery
US10013625B1 · kind B1 · utility
9Cited by
8References
27Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 16, 2015 |
| Grant date | Jul 3, 2018 |
| Priority date | — |
| Expiry date | Apr 16, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30168
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of delivering an image is disclosed. The method includes receiving a request for an image. A variation of quality signature (VoQS) of the image is determined. A VoQS of a particular image is determined based on a plurality of different levels of distortion applied to the particular image. The image is categorized into one of a plurality of clusters of images, wherein the categorization is based on a similarity between the VoQS of the image and one or more other VoQSs of one or more other images within the plurality of clusters of images. A distorted version of the image based on the categorization is delivered.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.