Device and method for estimating if an image is blurred
US8068668B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Jul 17, 2008 |
| Grant date | Nov 29, 2011 |
| Priority date | — |
| Expiry date | Jul 17, 2028 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30168
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A method for estimating if an image (14) is either blurred or sharp includes the steps of (i) determining an image gradient histogram distribution (410) of at least a portion of the image (14), and (ii) comparing at least a portion of the image gradient histogram distribution (410) to a Gaussian model gradient histogram distribution (414) of at least a portion of the image (14) to estimate if the image (14) is either blurred or sharp. In most cases, a sharp image (14) has a relatively large tailed distribution when compared to the Gaussian model, while a blurred image has a relatively small tailed distribution when compared to the Gaussian model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.