US5771318A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Adaptive edge-preserving smoothing filter
Assignee: Siemens AG
•
Filing: 1996-06-27
•
Granted: 1998-06-23
•
Expires: 2016-06-27
Abstract
Abstract An adaptive edge-preserving smoothing filter effectively reduces noise levels while preserving fine structures in data. The behavior of the filter is controlled easily by two control parameters. To adaptively control the behavior of the filter, the control parameter, α, can be set as a function of the local directional variances. The control parameter, β, can be set as a function of all of the directional variances and directional means. The filter includes; a compute means which receives the filter window size, the number of filter directions and input data, adaptive weighting parameter map means which receives the control parameter, α, adaptive weighting process means, adaptive combination parameter map means which receives the control parameter, β, and final compute means which provides the filtered output data.
Inventors
- 👤 Ming Fang
- 👤 Jianzhong Qian
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 18:39
CPC Classifications
G; G06; G06T; G06T5/00; G06T5/20
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
62 words
An adaptive edge-preserving smoothing filter comprising: compute means for receiving filter window size, number of filter directions and input data; adaptive weighting parameter map means connected to said compute means; adaptive weighting process means connected to said compute means and said adaptive weighting parameter map means; and, final compute means connected to said adaptive weighting process means for providing filtered output data.
Claim 2
Dependent Claim
62 words
An adaptive edge-preserving smoothing filter comprising: compute means for receiving filter window size, number of filter directions and input data; adaptive weighting parameter map means connected to said compute means; adaptive weighting process means connected to said compute means and said adaptive weighting parameter map means; and, final compute means connected to said adaptive weighting process means for providing filtered output data.
Claim 3
Dependent Claim
27 words
An adaptive edge-preserving smoothing filter as claimed in claim 1 further comprising: adaptive combination parameter map means connected between said compute means and said final compute means.
Claim 4
Dependent Claim
25 words
An adaptive edge-preserving smoothing filter as claimed in claim 1 wherein: said compute means computes the directional mean values and corresponding variances for all directions.
Claim 5
Dependent Claim
45 words
An adaptive edge-preserving smoothing filter as claimed in claim 1 wherein: said adaptive weighting parameter map means receives a constant weighting parameter, α, which ensures that directional mean with smallest directional variance will always contribute a greatest amount of signal to said filtered output data.
Claim 6
Dependent Claim
37 words
An adaptive edge-preserving smoothing filter as claimed in claim 1 wherein: said adaptive weighting parameter map means computes an adaptive weighting parameter map, α -- map, from local directional means and variances obtained from said compute means.
Claim 7
Dependent Claim
42 words
An adaptive edge-preserving smoothing filter as claimed in claim 1 wherein: adaptive weighting process means combines all directional means with their variances as weighting factors to form filtered data in which local directional means with smaller variances always have a greater contribution.
Claim 8
Dependent Claim
28 words
An adaptive edge-preserving smoothing filter as claimed in claim 1 wherein: said final compute means adaptively combines input data and filtered data from said adaptive weighting process means.
Claim 9
Dependent Claim
39 words
An adaptive edge-preserving smoothing filter as claimed in claim 1 wherein: for every small alpha, α, said filter acts like an isotropic smoothing filter and for every large alpha, α, said filter acts like an isotropic nonlinear smoothing filter.
Claim 10
Dependent Claim
23 words
An adaptive edge-preserving smoothing filter as claimed in claim 2 wherein: said adaptive combination parameter map means receives a constant weighting parameter, β.
Claim 11
Dependent Claim
37 words
An adaptive edge-preserving smoothing filter as claimed in claim 2 wherein: said adaptive combination parameter map means computes an adaptive combination parameter map, β -- map, from local directional means and variances obtained from said compute means.
Claim 12
Dependent Claim
42 words
An adaptive edge-preserving smoothing filter as claimed in claim 2 wherein: adaptive weighting process means combines all directional means with their variances as weighting factors to form filtered data in which local directional means with smaller variances always have a greater contribution.
Claim 13
Dependent Claim
50 words
An adaptive edge-preserving smoothing filter as claimed in claim 2 wherein: said final compute means adaptively combines input data and filtered data from adaptive weighting process means depending on value of combination parameter, α, or adaptive combination parameter map, β -- map, obtained from said adaptive combination parameter map means.
Claim 14
Dependent Claim
62 words
An adaptive edge-preserving smoothing filter comprising: compute means for receiving filter window size, number of filter directions and input data; adaptive weighting process means connected to said compute means; adaptive combination parameter map means connected to said compute means; and, final compute means connected to said adaptive weighting process means and said adaptive combination parameter map means for providing filtered output data.
Claim 15
Dependent Claim
62 words
An adaptive edge-preserving smoothing filter comprising: compute means for receiving filter window size, number of filter directions and input data; adaptive weighting process means connected to said compute means; adaptive combination parameter map means connected to said compute means; and, final compute means connected to said adaptive weighting process means and said adaptive combination parameter map means for providing filtered output data.
Claim 16
Dependent Claim
28 words
An adaptive edge-preserving smoothing filter as claimed in claim 13 further comprising: adaptive weighting parameter map means connected between said compute means and said adaptive weighting process means.
Claim 17
Dependent Claim
25 words
An adaptive edge-preserving smoothing filter as claimed in claim 13 wherein: said compute means computes the directional mean values and corresponding variances for all directions.
Claim 18
Dependent Claim
23 words
An adaptive edge-preserving smoothing filter as claimed in claim 13 wherein: said adaptive combination parameter map means receives a constant weighting parameter, β.
Claim 19
Dependent Claim
37 words
An adaptive edge-preserving smoothing filter as claimed in claim 13 wherein: said adaptive combination parameter map means computes an adaptive combination parameter map, β -- map, from local directional means and variances obtained from said compute means.
Claim 20
Dependent Claim
42 words
An adaptive edge-preserving smoothing filter as claimed in claim 13 wherein: adaptive weighting process means combines all directional means with their variances as weighting factors to form filtered data in which local directional means with smaller variances always have a greater contribution.
Claim 21
Dependent Claim
50 words
An adaptive edge-preserving smoothing filter as claimed in claim 13 wherein: said final compute means adaptively combines input data and filtered data from adaptive weighting process means depending on value of combination parameter, β, or adaptive combination parameter map, β -- map, obtained from said adaptive combination parameter map means.
Claim 22
Independent Claim
76 words
A method of performing adaptive edge-preserving filtering comprising the steps of: receiving filter window size, number of filter directions and input data; computing directional mean values and corresponding variances for all directions; inputting or computing an adaptive weighting parameter map; performing an adaptive weighting process; inputting or computing an adaptive combination parameter map; and, computing final filter output based on said input data, result data from said adaptive weighting process and said adaptive combination parameter map.
Claim 23
Independent Claim
76 words
A method of performing adaptive edge-preserving filtering comprising the steps of: receiving filter window size, number of filter directions and input data; computing directional mean values and corresponding variances for all directions; inputting or computing an adaptive weighting parameter map; performing an adaptive weighting process; inputting or computing an adaptive combination parameter map; and, computing final filter output based on said input data, result data from said adaptive weighting process and said adaptive combination parameter map.
References Cited (Backward Citations)
US5271064A
Cited
US5602934A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-06-22 | 2001-12-22 | 2002-06-23 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-06-22 | 2005-12-22 | 2006-06-23 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-06-22 | 2009-12-22 | 2010-06-23 | $7700.00 | Window Closed / Lapsed |