Patent US6167167A successfully refreshed from Google Patents.
US6167167A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image extractions apparatus and method
Assignee: Canon Inc
•
Filing: 1997-07-02
•
Granted: 2000-12-26
•
Expires: 2017-07-02
Abstract
Abstract There is disclosed an image extraction method for extracting, from a subject image that records both the background and the object to be extracted, image data of the object using a mask. An initial mask used for extracting the subject region is generated on the basis of difference data between the subject image and the background image that records the background alone, the region of the initial mask is grown on the basis of the similarity between the features of a first region and its neighboring second region in the subject image corresponding to the initial mask, and the image data of the object is extracted from the first image on the basis of the grown mask region.
Inventors
- 👤 Masakazu Matsugu
- 👤 Hideo Takiguchi
- 👤 Koji Hatanaka
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 11:40
CPC Classifications
H; H04; H04N; H04N19/00; H04N19/50; H04N19/503; H04N19/20
Claims Analysis
Total Claims: 38
Claim 1
Independent Claim
184 words
An image extraction method for extracting image data of an object from a first image that records both a background and the object to be extracted, using a mask, comprising: the first step of generating an initial mask for extracting an image of the object on the basis of difference data between the first image and a second image that records the background alone by combining a first region obtained on the basis of first data representing a brightness difference between the first and second images and a second region obtained on the basis of second data representing a color difference between the first and second images, said second region being set in the vicinity of the first region; the second step of growing a region of the generated initial mask on the basis of a similarity between a feature of a first region of the first image corresponding to the initial mask, and a feature of the second region; and the third step of extracting the image data of the object from the first image on the basis of the grown mask region.
Claim 2
Dependent Claim
184 words
An image extraction method for extracting image data of an object from a first image that records both a background and the object to be extracted, using a mask, comprising: the first step of generating an initial mask for extracting an image of the object on the basis of difference data between the first image and a second image that records the background alone by combining a first region obtained on the basis of first data representing a brightness difference between the first and second images and a second region obtained on the basis of second data representing a color difference between the first and second images, said second region being set in the vicinity of the first region; the second step of growing a region of the generated initial mask on the basis of a similarity between a feature of a first region of the first image corresponding to the initial mask, and a feature of the second region; and the third step of extracting the image data of the object from the first image on the basis of the grown mask region.
Claim 3
Dependent Claim
88 words
The method according to claim 1, wherein the first step comprises: the step of obtaining a first binary image region by a binarization process of data representing the brightness difference between the first and, second images using a predetermined threshold value; the step of obtaining a second binary image region by a binarization process of data representing the color difference between the first and second images using a predetermined threshold value; and the step of generating the initial mask by combining the first and second binary image regions.
Claim 4
Dependent Claim
51 words
The method according to claim 1, wherein the second step includes the step of checking based on brightness and hue similarities between the first and second regions if a pixel in the second region is to be incorporated in the first region, and growing the mask region upon incorporating the pixel.
Claim 5
Dependent Claim
77 words
The method according to claim 1, wherein the second step comprises: the step of respectively extracting first and second edge intensity images from the first and second images; the step of calculating an edge density on the basis of data representing a difference between the first and second edge intensity images; and the step of suppressing growing of the mask when the calculated edge density is not more than a predetermined threshold value in a growing direction.
Claim 6
Dependent Claim
40 words
The method according to claim 1, wherein the first step comprises: the step of normalizing the difference data representing the difference between the first and second images, and generating the initial mask on the basis of normalized brightness difference data.
Claim 7
Dependent Claim
77 words
The method according to claim 1, wherein the first step comprise: the step of extracting first and second edge intensity images representing edge intensities of the first and second images, respectively; and the step of normalizing both the first and second edge intensity images using a predetermined normalization coefficient when the edge intensity image is an image having a small number of edges, the normalization coefficient being a maximum intensity value of the first edge intensity image.
Claim 8
Dependent Claim
80 words
The method according to claim 1, wherein the first step comprises: the step of extracting first and second edge intensity images representing edge intensity of the first and second images, respectively; and the step of normalizing both the first and second edge intensity images using a maximum edge intensity value within a predetermined size region having a predetermined point of the first edge intensity image as a center when the first edge intensity image is an image having many edges.
Claim 9
Dependent Claim
53 words
The method according to claim 3, wherein the second step includes the step of comparing differences between brightness and hue values of the first and second regions with predetermined threshold values, and determining that the second region is similar to the first region when the differences are smaller than the predetermined threshold values.
Claim 10
Dependent Claim
21 words
The method according to claim 3, wherein the second region includes eight neighboring pixels of a pixel in the first region.
Claim 11
Dependent Claim
24 words
The method according to claim 1, wherein the second step further comprises the fourth step of shaping a contour line of the grown mask.
Claim 12
Dependent Claim
125 words
The method according to claim 10, wherein the fourth step comprises: the step of detecting the contour line of the grown mask; the step of generating an edge intensity image representing a difference between the first and second images; the step of setting a region having a predetermined width in a direction perpendicular to an extending direction of the contour line in the edge intensity image; the step of selecting a plurality of pixels of the edge intensity images in the region of the predetermined width as contour point candidates; and the step of selecting one contour point on the basis of continuity between a pixel on the contour line and the plurality of contour point candidates, thereby shaping the contour line of the mask.
Claim 13
Dependent Claim
16 words
The method according to claim 11, wherein the continuity is determined by inspecting pixel value continuity.
Claim 14
Dependent Claim
15 words
The method according to claim 11, wherein the continuity is determined by inspecting shape continuity.
Claim 15
Dependent Claim
22 words
The method according to claim 11, wherein the continuity is determined by inspecting continuity with a pixel present inside the contour line.
Claim 16
Dependent Claim
21 words
The method according to claim 11, wherein the continuity is determined by weighting and evaluating pixel value continuity and shape continuity.
Claim 17
Dependent Claim
20 words
The method according to claim 10, wherein the fourth step further includes the step of smoothing the shaped contour line.
Claim 18
Dependent Claim
58 words
The method according to claim 10, wherein the fourth step comprises: the active contour shaping step of recursively executing a process for deforming or moving a contour shape of the mask to minimize a predetermined evaluation function on the basis of the initial mask or a contour of the grown mask, and image data of the first image.
Claim 19
Dependent Claim
53 words
The method according to claim 17, wherein the active contour shaping step comprises: generating a contour line by performing an active contour shaping process of data of the initial mask, and performing an active contour shaping process of the image data of the first image on the basis of the generated contour line.
Claim 20
Dependent Claim
181 words
An image extraction apparatus for extracting image data of an object from a first image that records both a background and the object to be extracted, using a mask, comprising: generating means for generating an initial mask for extracting an image of the object on the basis of difference data between the first image and a second image that records the background alone by combining a first region obtained on the basis of first data representing a brightness difference between the first and second images and a second region obtained on the basis of second data representing a color difference between the first and second images, said second region being set in the vicinity of the first region; growing means for growing a region of the generated initial mask on the basis of a similarity between a feature of a first region of the first image corresponding to the initial mask, and a feature of the second region; and extracting means for extracting the image data of the object from the first image on the basis of the grown mask region.
Claim 21
Dependent Claim
181 words
An image extraction apparatus for extracting image data of an object from a first image that records both a background and the object to be extracted, using a mask, comprising: generating means for generating an initial mask for extracting an image of the object on the basis of difference data between the first image and a second image that records the background alone by combining a first region obtained on the basis of first data representing a brightness difference between the first and second images and a second region obtained on the basis of second data representing a color difference between the first and second images, said second region being set in the vicinity of the first region; growing means for growing a region of the generated initial mask on the basis of a similarity between a feature of a first region of the first image corresponding to the initial mask, and a feature of the second region; and extracting means for extracting the image data of the object from the first image on the basis of the grown mask region.
Claim 22
Dependent Claim
85 words
The apparatus according to claim 19, wherein said generating means comprises: means for obtaining a first binary image region by a binarization process of data representing the brightness difference between the first and second images using a predetermined threshold value; means for obtaining a second binary image region by a binarization process of data representing the color difference between the first and second images using a predetermined threshold value; and means for generating the initial mask by combining the first and second binary image regions.
Claim 23
Dependent Claim
50 words
The apparatus according to claim 19, wherein said growing means includes means for checking based on brightness and hue similarities between the first and second regions if a pixel in the second region is to be incorporated in the first region, and growing the mask region upon incorporating the pixel.
Claim 24
Dependent Claim
74 words
The apparatus according to claim 19, wherein said growing means comprises: means for respectively extracting first and second edge intensity images from the first and second images; means for calculating an edge density on the basis of data representing a difference between the first and second edge intensity images; and means for suppressing growing of the mask when the calculated edge density is not more than a predetermined threshold value in a growing direction.
Claim 25
Dependent Claim
39 words
The apparatus according to claim 19, wherein said generating means comprises: means for normalizing the difference data representing the difference between the first and second images, and generating the initial mask on the basis of normalized brightness difference data.
Claim 26
Dependent Claim
76 words
The apparatus according to claim 19, wherein said generating means comprises: means for extracting first and second edge intensity images representing edge intensities of the first and second images, respectively; and means for normalizing both the first and second edge intensity images using a predetermined normalization coefficient when the first edge intensity image is an image having a entail number of edges, the normalization coefficient being a maximum intensity value of the first edge intensity image.
Claim 27
Dependent Claim
78 words
The apparatus according to claim 19, wherein said generating means comprises: means for extracting first and second edge intensity images representing edge intensities of the first and second images, respectively; and means for normalizing both the first and second edge intensity images using a maximum edge intensity value within a predetermined size region having a predetermined point of the first edge intensity image as a center when the first edge intensity image is an image having many edges.
Claim 28
Dependent Claim
52 words
The apparatus according to claim 21, wherein said growing means includes means for comparing differences between brightness and hue values of the first and second regions with predetermined threshold values, and determining that the second region is similar to the first region when the differences are smaller than the predetermined threshold values.
Claim 29
Dependent Claim
21 words
The apparatus according to claim 21, wherein the second region includes eight neighboring pixels of a pixel in the first region.
Claim 30
Dependent Claim
23 words
The apparatus according to claim 19, wherein said growing means further comprises shaping means for shaping a contour line of the grown mask.
Claim 31
Dependent Claim
120 words
The apparatus according to claim 28, wherein said shaping means comprises: means for detecting the contour line of the grown mask; means for generating an edge intensity image representing a difference between the first and second images; means for setting a region having a predetermined width in a direction perpendicular to an extending direction of the contour line in the edge intensity image; means for selecting a plurality of pixels of the edge intensity images in the region of the predetermined width as contour point candidates; and means for selecting one contour point on the basis of continuity between a pixel on the contour line and the plurality of contour point candidates, thereby shaping the contour line of the mask.
Claim 32
Dependent Claim
16 words
The apparatus according to claim 29, wherein the continuity is determined by inspecting pixel value continuity.
Claim 33
Dependent Claim
15 words
The apparatus according to claim 29 wherein the continuity is determined by inspecting shape continuity.
Claim 34
Dependent Claim
22 words
The apparatus according to claim 29, wherein the continuity is determined by inspecting continuity with a pixel present inside the contour line.
Claim 35
Dependent Claim
21 words
The apparatus according to claim 29, wherein the continuity is determined by weighting and evaluating pixel value continuity and shape continuity.
Claim 36
Dependent Claim
19 words
The apparatus according to claim 28, wherein said shaping means further includes means for smoothing the shaped contour line.
Claim 37
Dependent Claim
57 words
The apparatus according to claim 28, wherein said shaping means comprises: active contour shaping means for recursively executing a process for deforming or moving a contour shape of the mask to minimize a predetermined evaluation function on the basis of the initial mask or a contour of the grown mask, and image data of the first image.
Claim 38
Dependent Claim
55 words
The apparatus according to claim 35, wherein said active contour shaping means comprises: means for generating a contour line by performing an active contour shaping process of data of the initial mask, and performing an active contour shaping process of the image data of the first image on the basis of the generated contour line.
References Cited (Backward Citations)
US4958217A
Cited
US4882622A
Cited
EP0400998A2
Cited
US5471535A
Cited
EP0532823A2
Cited
US5598482A
Cited
US5557685A
Cited
EP0634872A2
Cited
EP0671706A2
Cited
EP0706155A1
Cited
US5519436A
Cited
US5768438A
Cited
US5818962A
Cited
US5881171A
Cited
US5875040A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-12-26 | 2004-06-26 | 2004-12-26 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-12-26 | 2008-06-26 | 2008-12-26 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-12-26 | 2012-06-26 | 2012-12-26 | $7700.00 | Window Closed / Lapsed |