Patent EP0817495A2 successfully refreshed from Google Patents.
EP0817495A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Image subject extraction apparatus and method
Assignee: Canon Inc
•
Filing: 1997-06-30
•
Granted: —
•
Expires: 2017-06-30
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
EP
Data Source
google_patents
Last Synchronized
2026-11-07 09:42
CPC Classifications
H; H04; H04N; H04N19/00; H04N19/50; H04N19/503; H04N19/20
Claims Analysis
Total Claims: 36
Claim 1
Independent Claim
141 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, characterized by comprising: the first step (S18) 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; the second step (S31∼S35) 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 a
second region in the vicinity of the first region; and the third step (S50) of extracting the image data
of the object from the first image on the basis of the
grown mask region.
Claim 2
Dependent Claim
49 words
The method according to claim 1, wherein the
first step includes the step (S16) of using as the
initial mask a binary image region obtained by a
binarization process of difference data representing a
difference between image data of the first and second
images using a predetermined threshold value.
Claim 3
Dependent Claim
20 words
The method according to claim 2, wherein the
difference data represents a brightness difference
between the first and second images.
Claim 4
Dependent Claim
20 words
The method according to claim 2, wherein the
difference data represents a color difference between
the first and second images.
Claim 5
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 a
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 a 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 6
Dependent Claim
53 words
The method according to claim 1, wherein the
second step includes the step (S32, S33) 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 7
Dependent Claim
78 words
The method according to claim 1, wherein the
second step (S34) 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 8
Dependent Claim
41 words
The method according to claim 2, wherein the
first step (S15) 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 9
Dependent Claim
79 words
The method according to claim 2, wherein the
first step (S15) comprises: 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 first 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 10
Dependent Claim
81 words
The method according to claim 2, wherein the
first step (S15) comprises: 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 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 11
Dependent Claim
54 words
The method according to claim 6, wherein the
second step (S32) 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 12
Dependent Claim
21 words
The method according to claim 6, wherein the
second region includes eight neighboring pixels of a
pixel in the first region.
Claim 13
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 14
Dependent Claim
126 words
The method according to claim 13, wherein
the fourth step (S42∼S44) 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 15
Dependent Claim
16 words
The method according to claim 14, wherein
the continuity is determined by inspecting pixel value
continuity.
Claim 16
Dependent Claim
15 words
The method according to claim 14, wherein
the continuity is determined by inspecting shape
continuity.
Claim 17
Dependent Claim
22 words
The method according to claim 14, wherein
the continuity is determined by inspecting continuity
with a pixel present inside the contour line.
Claim 18
Dependent Claim
21 words
The method according to claim 14, wherein
the continuity is determined by weighting and evaluating
pixel value continuity and shape continuity.
Claim 19
Dependent Claim
21 words
The method according to claim 13, wherein
the fourth step further includes the step (S45) of
smoothing the shaped contour line.
Claim 20
Dependent Claim
58 words
The method according to claim 13, 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 21
Dependent Claim
54 words
The method according to claim 20, wherein
the active contour shaping step (S402) 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 22
Dependent Claim
98 words
An image extraction method comprising: the partial region extraction step (S117∼S121) of
extracting a partial region as a portion of a subject to
be extracted from an input image; the region growing step (S122∼S125) of growing the
extracted partial region using the extracted partial
region as a seed by thresholding a similarity to a
neighboring region using a threshold value, the
threshold value being set on the basis of a feature
distribution at individual points of the input image;
and the extraction step (S127) of extracting an image
of the subject on the basis of the region-grown region.
Claim 23
Dependent Claim
41 words
The method according to claim 22, wherein
the partial region extraction step includes the step
(S117) of extracting the partial region on the basis of
a difference between a background image excluding the
subject, and a subject image including the subject.
Claim 24
Dependent Claim
17 words
The method according to claim 22, wherein
the feature distribution is an edge distribution of the
subject.
Claim 25
Dependent Claim
24 words
The method according to claim 22, wherein
the feature distribution is a distribution within a
maximum growing range set based on the partial region.
Claim 26
Dependent Claim
32 words
The method according to claim 22, wherein
the threshold value is set to assume a value that
suppresses growing of the region at an edge position as
compared to a non-edge position.
Claim 27
Dependent Claim
46 words
The method according to claim 25, wherein
the threshold value is set to assume a value that
promotes growing of the region in a region within the
maximum growing range, and to assume a value that
suppresses growing of the region outside the maximum
growing region.
Claim 28
Dependent Claim
33 words
The method according to claim 25, wherein
the maximum growing range is obtained as an output when
a shape of the partial region is smoothed using a
smoothing filter having a predetermined size.
Claim 29
Dependent Claim
43 words
The method according to claim 22, wherein
the input image includes time-serial images, and the
partial region extraction step includes the step of
extracting the partial region on the basis of difference
data between image frames at different times of the
input image.
Claim 30
Dependent Claim
48 words
The method according to claim 22, wherein
the input image includes a plurality of images from a
plurality of different view point positions, and the
partial region extraction step includes the step of
extracting the partial region on the basis of a
disparity distribution between the input images.
Claim 31
Dependent Claim
123 words
An image extraction apparatus for extracting,
from a first image including both a background and an
object to be extracted, image data of the object using a
mask, characterized by comprising: temporary storage means for receiving and
temporarily storing the first image and a second image
that records the background; initial mask generation means for generating an
initial mask of an extraction region on the basis of
difference data between the stored first and second
images; region growing means for growing a region of the
initial mask on the basis of a feature similarity to a
neighboring region; and first image extraction means for extracting the
image data of the object from the first image on the
basis of the grown mask region.
Claim 32
Dependent Claim
107 words
The apparatus according to claim 31, wherein
said initial mask generation means comprises: first seed extraction means for extracting a color
difference seed by performing a threshold value process
of a difference between color components at individual
points of the first and second images; second seed extraction means for respectively
extracting first and second edge intensity images from
the first and second images, and extracting an edge
difference seed by performing a threshold value process
of difference data between the first and second edge
intensity images; and generation means for generating an initial seed on
the basis of outputs from said first and second seed
extraction means.
Claim 33
Dependent Claim
44 words
The apparatus according to claim 32, wherein
said first image extraction means comprises: means for extracting difference edge data between
the first and second images; and means for shaping a contour line of the object on
the basis of the extracted difference edge data.
Claim 34
Dependent Claim
106 words
The apparatus according to claim 33, wherein
said shaping means comprises: threshold value process means for performing a
threshold value process of the difference edge data or
edge data of the first image; first continuity evaluation means for evaluating
shape continuity for edge candidates that remain after
the threshold value process; second continuity evaluation means for evaluating
continuity of image features of the edge candidates; edge selection means for selecting one of the edge
candidates on the basis of outputs from said first and
second continuity evaluation means; and smoothing means for smoothing an extracted contour
line or a correction mask region including the contour
line.
Claim 35
Dependent Claim
28 words
The apparatus according to claim 33, wherein
said region growing means comprises: means for determining a condition for suppressing
a growing process; and means for determining a similarity.
Claim 36
Dependent Claim
92 words
An image extraction apparatus comprising: partial region extraction means for extracting a
partial region as a portion of a subject to be extracted
from an input image; region growing means for growing the extracted
partial region using the extracted partial region as a
seed by processing a similarity to a neighboring region
using a threshold value, the threshold value being set
on the basis of a feature distribution at individual
points of the input image; and extraction means for extracting an image of the
subject on the basis of the region-grown region.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.