Patent US2114005A successfully refreshed from Google Patents.
Patent US5964833A successfully refreshed from Google Patents.
Patent US5325449A successfully refreshed from Google Patents.
US5325449A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for fusing images and apparatus therefor
Assignee: Sarnoff Corp
•
Filing: 1992-05-15
•
Granted: 1994-06-28
•
Expires: 2012-05-15
Abstract
Abstract A method for fusing two or more source images to form a composite image with extended information content and apparatus for forming the composite image from the source images is disclosed. Each source image is decomposed into a number of source images of varying resolution. The decomposed source images are analyzed using directionally sensitive operators to generate a set of oriented basis functions characteristic of the information content of the original images. The oriented basis functions for the composite image are then selected from those of the different source images and the inverse of the decomposition performed to construct the composite image. Apparatus for fusing two or more source images to form a composite image is also disclosed.
Inventors
- 👤 Peter J. Burt
- 👤 Gooitzen S. van der Wal
- 👤 Raymond J. Kolczynski
- 👤 Rajesh Hingorani
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 17:17
CPC Classifications
G; G06; G06T; G06T5/00; G06T5/50; H; H04; H04N; H04N19/00; H04N19/20; H04N19/23; H04N7/00; H04N7/18; H04N7/181; G06T2207/00; G06T2207/20; G06T2207/20016; G06T2207/20212; G06T2207/20221
Claims Analysis
Total Claims: 47
Claim 1
Independent Claim
136 words
A method for forming a composite image from N source images where N is greater than one comprising the steps of: (a) decomposing each source image I N into a plurality L of sets of oriented component patterns P N (m, L), where m is the number of patterns in each of the L sets for the N th source image; (b) computing a saliency measure S N (m, L) for each component pattern P N (m, L); (c) selecting component patterns from the component pattern sets P N (m, L) using the saliency measures S N (m, L) for each component pattern to form a set of oriented component patterns P c (m, L) of the composite image; and (d) constructing the composite image from the set of oriented component patterns P c (m, L).
Claim 2
Independent Claim
136 words
A method for forming a composite image from N source images where N is greater than one comprising the steps of: (a) decomposing each source image I N into a plurality L of sets of oriented component patterns P N (m, L), where m is the number of patterns in each of the L sets for the N th source image; (b) computing a saliency measure S N (m, L) for each component pattern P N (m, L); (c) selecting component patterns from the component pattern sets P N (m, L) using the saliency measures S N (m, L) for each component pattern to form a set of oriented component patterns P c (m, L) of the composite image; and (d) constructing the composite image from the set of oriented component patterns P c (m, L).
Claim 3
Dependent Claim
18 words
The method of claim 1 further comprising the step of aligning the source images prior to step (a).
Claim 4
Dependent Claim
45 words
The method of claim 1 wherein the step of decomposing each source image I N into a plurality L of sets of oriented component patterns P N (m, L) comprises applying oriented operators to an image feature at each picture element of each source image.
Claim 5
Dependent Claim
34 words
The method of claim 3 wherein each oriented component pattern P N (m, L) is the gradient of the local image intensity at each picture element of each source image in a particular direction.
Claim 6
Dependent Claim
31 words
The method of claim 4 wherein the gradient operators are the first derivatives of the image intensity at each picture element in first and second orthogonal directions in each source image.
Claim 7
Dependent Claim
44 words
The method of claim 5 wherein the gradient operators also include the first derivatives of the image intensity in third and fourth directions in each source image which are orthogonal two one another and at a forty five degree angle to the first direction.
Claim 8
Dependent Claim
38 words
The method of claim 3 wherein the step of selecting component patterns from the source image pattern sets P N (m, L) for each value of m and L comprises selecting the component pattern having the greatest saliency.
Claim 9
Dependent Claim
42 words
The method of claim 7 wherein the step of selecting component patterns from the source image pattern sets P N (m, L) for each value of m and L comprises selecting the component pattern having the amplitude with the greatest absolute magnitude.
Claim 10
Dependent Claim
44 words
The method of claim 3 wherein the step of selecting component patterns from the source image pattern sets P N (m, L) for each value of m and L comprises selecting a linear combination of the amplitudes of the component patterns for each image.
Claim 11
Dependent Claim
34 words
The method of claim 9 wherein the linear combination of the amplitudes of the component patterns for each image is a weighted average of the amplitudes of the component patterns of the source images.
Claim 12
Dependent Claim
30 words
The method of claim 10 wherein the weight assigned to a particular component pattern in each of the source images depends upon the normalized saliency of the particular component pattern.
Claim 13
Dependent Claim
37 words
The method of claim 10 wherein the weighted average of the amplitudes of the component patterns is the weighted root mean square of the amplitudes of the particular component pattern and other components within a local neighborhood.
Claim 14
Dependent Claim
41 words
The method of claim 10 wherein the weight assigned to a particular component pattern in each of the source images is the weighted root means square of the amplitudes of the particular component pattern and other components within a local neighborhood.
Claim 15
Dependent Claim
144 words
The method of claim 1 wherein step (a) further comprises the step of decomposing each source image into a plurality K of images I K of different resolution and then decomposing each of the images I K into a plurality L of sets of oriented component patterns P N (m, K, L); wherein step (b) comprises computing a saliency measure S N (m, K, L) for each component pattern P N (m, K L); wherein step (c) comprises computing component patterns from the source image component pattern sets P N (m, K, L) using the saliency measures S N (m, K L) for each component pattern to form a set of oriented component patterns P c (m, K, L) of the composite image; and wherein step (c) comprises constructing the composite image from the set of oriented component patterns P c (m, K, L).
Claim 16
Dependent Claim
44 words
The method of claim 14 wherein the step of decomposing each image I K into a plurality L of sets of oriented component patterns P N (m, K, L) comprises applying oriented operators to a feature of each picture element of each source image.
Claim 17
Dependent Claim
35 words
The method of claim 15 wherein each oriented component pattern P N (m, K, L) is the gradient of the local image intensity at each picture element of each source image in a particular direction.
Claim 18
Dependent Claim
31 words
The method of claim 16 wherein the gradient operators are the first derivatives of the image intensity at each picture element in first and second orthogonal directions in each source image.
Claim 19
Dependent Claim
44 words
The method of claim 17 wherein the gradient operators also include the first derivatives of the image intensity in third and fourth directions in each source image which are orthogonal two one another and at a forty five degree angle to the first direction.
Claim 20
Dependent Claim
44 words
The method of claim 14 wherein the step of selecting component patterns from the source image pattern sets P N (m, L) for each value of m and L comprises selecting a linear combination of the amplitudes of the component patterns for each image.
Claim 21
Dependent Claim
34 words
The method of claim 19 wherein the linear combination of the amplitudes of the component patterns for each image is a weighted average of the amplitudes of the component patterns of the source images.
Claim 22
Dependent Claim
30 words
The method of claim 20 wherein the weight assigned to a particular component pattern in each of the source images depends upon the normalized saliency of the particular component pattern.
Claim 23
Dependent Claim
37 words
The method of claim 20 wherein the weighted average of the amplitudes of the component patterns is the weighted root mean square of the amplitudes of the particular component pattern and other components within a local neighborhood.
Claim 24
Dependent Claim
31 words
The method of claim 1 wherein the step of decomposing each source image I N comprises forming two or more sets of wavelets oriented in different directions in each source image.
Claim 25
Dependent Claim
18 words
The method of claim 23 comprising first and second sets of wavelets in first and second orthogonal directions.
Claim 26
Dependent Claim
38 words
The method of claim 24 wherein the step of selecting component patterns from the source image pattern sets P N (m, L) for each value of m and L comprises selecting the component pattern having the greatest saliency.
Claim 27
Dependent Claim
44 words
The method of claim 24 wherein the step of selecting component patterns from the source image pattern sets P N (m, L) for each value of m and L comprises selecting a linear combination of the amplitudes of the component patterns for each image.
Claim 28
Dependent Claim
148 words
The method of claim 1 wherein step (a) further comprises the step of decomposing each source image into a plurality K of images I K of different resolution and then decomposing each of the images I K into a plurality L of sets of oriented component patterns P N (m, K, L); wherein step (b) comprises computing a saliency measure S N (m, K, L) for each component pattern P N (m, K L) of each image N; wherein step (c) comprises computing component patterns from the source image component pattern sets P N (m, K, L) using the saliency measures S N (m, K L) for each component pattern to form a set of oriented component patterns P c (m, K, L) of the composite image; and wherein step (c) comprises constructing the composite image from the set of oriented component patterns P c (m, K, L).
Claim 29
Independent Claim
172 words
A method for forming a composite image from N source images where N is greater than one comprising the steps of: (a) decomposing each source image into a plurality K of images I K of different resolution and then decomposing each of the images I K into a plurality L of sets of oriented component patterns P N (m, K, L), where m is the number of patterns in each of the L sets for the N th source image; (b) computing a saliency measure S N (m, K, L) for each component pattern P N (m, K, L) of each image N at each resolution level K; (c) selecting component patterns from the source image component pattern sets P N (m, K, L) using the saliency measures S N (m, K, L) for each component pattern to form a set of oriented component patterns P c (m, K, L) of the composite image; and (d) constructing the composite image from the set of oriented component patterns P c (m, K, L).
Claim 30
Independent Claim
172 words
A method for forming a composite image from N source images where N is greater than one comprising the steps of: (a) decomposing each source image into a plurality K of images I K of different resolution and then decomposing each of the images I K into a plurality L of sets of oriented component patterns P N (m, K, L), where m is the number of patterns in each of the L sets for the N th source image; (b) computing a saliency measure S N (m, K, L) for each component pattern P N (m, K, L) of each image N at each resolution level K; (c) selecting component patterns from the source image component pattern sets P N (m, K, L) using the saliency measures S N (m, K, L) for each component pattern to form a set of oriented component patterns P c (m, K, L) of the composite image; and (d) constructing the composite image from the set of oriented component patterns P c (m, K, L).
Claim 31
Dependent Claim
45 words
The method of claim 28 wherein the step of decomposing each source image I N into a plurality L of sets of oriented component patterns P N (m, L) comprises applying oriented operators to an image feature at each picture element of each source image.
Claim 32
Dependent Claim
34 words
The method of claim 29 wherein each oriented component pattern P N (m, L) is the gradient of the local image intensity at each picture element of each source image in a particular direction.
Claim 33
Dependent Claim
31 words
The method of claim 30 wherein the gradient operators are the first derivatives of the image intensity at each picture element in first and second orthogonal directions in each source image.
Claim 34
Dependent Claim
44 words
The method of claim 31 wherein the gradient operators also include the first derivatives of the image intensity in third and fourth directions in each source image which are orthogonal two one another and at a forty five degree angle to the first direction.
Claim 35
Dependent Claim
40 words
The method of claim 28 wherein the step of selecting component patterns from the source image pattern sets P N (m, K, L) for each value of m, K and L comprises selecting the component pattern having the greatest saliency.
Claim 36
Dependent Claim
44 words
The method of claim 33 wherein the step of selecting component patterns from the source image pattern sets P N (m, K, L) for each value of m, K and L comprises selecting the component pattern having the amplitude with the greatest absolute magnitude.
Claim 37
Dependent Claim
46 words
The method of claim 33 wherein the step of selecting component patterns from the source image pattern sets P N (m, K, L) for each value of m, K and L comprises selecting a linear combination of the amplitudes of the component patterns for each image.
Claim 38
Dependent Claim
34 words
The method of claim 35 wherein the linear combination of the amplitudes of the component patterns for each image is a weighted average of the amplitudes of the component patterns of the source images.
Claim 39
Dependent Claim
31 words
The method of claim 36 wherein the step of decomposing each source image I N comprises forming two or more sets of wavelets oriented in different directions in each source image.
Claim 40
Dependent Claim
18 words
The method of claim 37 comprising first and second sets of wavelets in first and second orthogonal directions.
Claim 41
Dependent Claim
144 words
Apparatus for forming a composite image from a plurality of N source images, where N is greater than one, comprising: means for decomposing each source image I N into a plurality L of sets of oriented component patterns P N (m, L), where m is the number of patterns in each of the L sets for the N th source image; means for computing a saliency measure S N (m, L) for each component pattern P N (m, L) connected to the decomposing means; means for selecting component patterns from the component pattern sets P N (m, L) using the saliency measures S N (m, L) for each component pattern to form a set of oriented component patterns P c (m, L) of the composite image; and means for constructing the composite image from the set of oriented component patterns P c (m, L).
Claim 42
Dependent Claim
144 words
Apparatus for forming a composite image from a plurality of N source images, where N is greater than one, comprising: means for decomposing each source image I N into a plurality L of sets of oriented component patterns P N (m, L), where m is the number of patterns in each of the L sets for the N th source image; means for computing a saliency measure S N (m, L) for each component pattern P N (m, L) connected to the decomposing means; means for selecting component patterns from the component pattern sets P N (m, L) using the saliency measures S N (m, L) for each component pattern to form a set of oriented component patterns P c (m, L) of the composite image; and means for constructing the composite image from the set of oriented component patterns P c (m, L).
Claim 43
Dependent Claim
33 words
The apparatus of claim 39 further comprising means for decomposing each source image into a plurality K of images I K of different resolution prior to the means for decomposing each source image.
Claim 44
Dependent Claim
34 words
The apparatus of claim 40 wherein the means for decomposing each source image I N comprises a electrical circuit for performing two different gradient operations on each of the source images I N .
Claim 45
Dependent Claim
37 words
The apparatus of claim 39 wherein the means for computing a saliency measure S N (m, L) for each component pattern P N (m, L) includes electrical circuitry for calculating the weights for the different component patterns.
Claim 46
Dependent Claim
40 words
The apparatus of claim 39 wherein the means for computing a saliency measure S N (m, L) for each component pattern P N (m, L) comprises means for calculating the root mean square weight for the amplitudes different component patterns.
Claim 47
Dependent Claim
32 words
The apparatus of claim 41 wherein the means for constructing each composite image I N comprises a electrical circuit for performing the same two gradient operations on each set of composite patterns.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-06-27 | 1997-12-27 | 1998-06-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-06-27 | 2001-12-27 | 2002-06-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-06-27 | 2005-12-27 | 2006-06-28 | $7700.00 | Window Closed / Lapsed |