Patent US6445819B1 successfully refreshed from Google Patents.
US6445819B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image processing method, image processing device, and recording medium
Assignee: Fujifilm Corp
•
Filing: 1999-09-10
•
Granted: 2002-09-03
•
Expires: 2019-09-10
Abstract
Abstract An image processing method, image processing device and recording medium are provided in which the effects of erroneous extraction of a region assumed to correspond to a main portion within an image are mitigated. On the basis of image data of an image which is an object of processing, plural face candidate regions, which are assumed to correspond to faces of persons, are extracted. A degree of overlapping is computed for a pair of overlapping face candidate regions. A weight point is set for each face candidate region such that a weight point of a face candidate region which overlaps with another face candidate region is higher than a weight point of a face candidate region which does not overlap with another face candidate region, and the higher the degree of overlapping with another face candidate region, the higher the weight point. By comparing weight points of face candidate regions with a threshold value, a face region corresponding to a face of a person is extracted from the respective face candidate regions. A weighted average value, in which density values of the respective face candidate regions are weighted in accordance with degrees of overlapping, is computed as a face region density.
Inventors
- 👤 Naoto Kinjo
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 11:23
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/10; G06T7/11; G06V; G06V40/00; G06V40/10; G06V40/16; G06V40/161; G06T2207/00; G06T2207/30; G06T2207/30196; G06T2207/30201
Claims Analysis
Total Claims: 13
Claim 1
Independent Claim
138 words
An image processing method comprising the steps of: on the basis of image data, extracting candidate regions which are assumed to correspond to main portions in an image represented by the image data; determining, for each of candidate regions which overlap with another candidate region among the extracted candidate regions, a degree of overlapping with another candidate region; and for an extracted candidate region, evaluating the probability of being a region corresponding to a main portion in the image, in such a manner that, for a candidate region overlapping with another candidate region, an evaluation of the probability of being a region corresponding to a main portion within the image is higher than said evaluation for a candidate region not overlapping with another candidate region, and becomes higher as a degree of overlapping with another candidate region increases.
Claim 2
Dependent Claim
138 words
An image processing method comprising the steps of: on the basis of image data, extracting candidate regions which are assumed to correspond to main portions in an image represented by the image data; determining, for each of candidate regions which overlap with another candidate region among the extracted candidate regions, a degree of overlapping with another candidate region; and for an extracted candidate region, evaluating the probability of being a region corresponding to a main portion in the image, in such a manner that, for a candidate region overlapping with another candidate region, an evaluation of the probability of being a region corresponding to a main portion within the image is higher than said evaluation for a candidate region not overlapping with another candidate region, and becomes higher as a degree of overlapping with another candidate region increases.
Claim 3
Dependent Claim
125 words
An image processing method according to claim 1 , wherein at least one of a value in which a distance between a pair of overlapping candidate regions is normalized by using respective sizes of the pair of overlapping candidate regions as a standard; a value in which a surface area of an overlapped region of a pair of overlapping candidate regions is normalized by using respective sizes of the pair of candidate regions as a standard; and a value in which a size along a predetermined direction of an overlapped region of a pair of overlapping candidate regions is normalized by using as a standard respective sizes along the predetermined direction of the pair of overlapping candidate regions, is used as the degree of overlapping.
Claim 4
Dependent Claim
65 words
An image processing method according to claim 1 , wherein, for an extracted candidate region, by comparing an evaluation value, which expresses the results of evaluating the probability of being a region corresponding to a main portion, with a threshold value, a candidate region having a high probability of being a region corresponding to a main portion is selected from among the extracted candidate regions.
Claim 5
Dependent Claim
84 words
An image processing method according to claim 1 , wherein a weight is applied, to an extracted candidate region or to a candidate region selected from among the extracted candidate regions, in accordance with an evaluation value which expresses the results of evaluating the probability of being a region corresponding to a main portion, and a weighted average of an image characteristic amount of the extracted candidate region or the selected candidate region is computed as an image characteristic amount of the main portion.
Claim 6
Dependent Claim
100 words
An image processing method according to claim 1 , wherein after evaluation, for an extracted candidate region, of the probability of being a region corresponding to a main portion, when carrying out, on the basis of the results of evaluation, a predetermined image processing which includes at least one of selecting a candidate region having a high probability of being a region corresponding to a main portion and weighting an extracted candidate region, the standard for evaluation is changed or the standard for the selection or the weighting is change in accordance with the type of the predetermined image processing.
Claim 7
Dependent Claim
133 words
An image processing method according to claim 5 , wherein when said predetermined image processing is an image processing whose processing results are greatly affected when a candidate region is erroneously extracted or a candidate region is mis-evaluated, one of the following is carried out: the standard of evaluation of the probability of being a region corresponding to a main portion is changed so as to be made more strict; the standard for the selection is changed such that only a candidate region evaluated as having a high probability of being a region corresponding to a main portion is selected; and a standard for weighting is changed such that a weight for a candidate region evaluated as having a low probability of being a region corresponding to a main portion is relatively small.
Claim 8
Dependent Claim
135 words
An image processing method according to claim 5 , wherein when the predetermined image processing is an image processing whose processing results are only slightly affected even if a candidate region is erroneously extracted or a candidate region is mis-evaluated, one of the following is carried out: the standard of evaluation of the probability of being a region corresponding to a main portion is changed so as to be made less strict; the standard for the selection is changed such that a candidate region evaluated as having a low probability of being a region corresponding to a main portion is also selected; and a standard for weighting is changed such that a weight for a candidate region evaluated as having a low probability of being a region corresponding to a main portion is relatively large.
Claim 9
Dependent Claim
79 words
An image processing method according to claim 1 , wherein, for a candidate region whose density within the candidate region is higher than a first predetermined value or lower than a second predetermined value, the evaluation of the probability of being a region corresponding to a main portion is lowered, or the standard for selection at the time a candidate region having a high probability of being a region corresponding to a main portion is selected is made higher.
Claim 10
Dependent Claim
144 words
An image processing device comprising: extracting means for, on the basis of image data, extracting candidate regions which are assumed to correspond to main portions in an image represented by the image data; computing means for determining, for each of candidate regions which overlap with another candidate region among the extracted candidate regions, a degree of overlapping with another candidate region; and evaluating means for evaluating, for an extracted candidate region, the probability of being a region corresponding to a main portion in the image, in such a manner that, for a candidate region overlapping with another candidate region, an evaluation of the probability of being a region corresponding to a main portion within the image is higher than said evaluation for a candidate region not overlapping with another candidate region, and becomes higher as a degree of overlapping with another candidate region increases.
Claim 11
Dependent Claim
144 words
An image processing device comprising: extracting means for, on the basis of image data, extracting candidate regions which are assumed to correspond to main portions in an image represented by the image data; computing means for determining, for each of candidate regions which overlap with another candidate region among the extracted candidate regions, a degree of overlapping with another candidate region; and evaluating means for evaluating, for an extracted candidate region, the probability of being a region corresponding to a main portion in the image, in such a manner that, for a candidate region overlapping with another candidate region, an evaluation of the probability of being a region corresponding to a main portion within the image is higher than said evaluation for a candidate region not overlapping with another candidate region, and becomes higher as a degree of overlapping with another candidate region increases.
Claim 12
Dependent Claim
159 words
A recording medium on which is stored a program for executing at a computer a processing comprising: a first step of, on the basis of image data, extracting candidate regions which are assumed to correspond to main portions in an image represented by the image data; a second step of determining, for each of candidate regions which overlap with another candidate region among the extracted candidate regions, a degree of overlapping with another candidate region; and a third step of, for an extracted candidate region, evaluating the probability of being a region corresponding to a main portion in the image, in such a manner that, for a candidate region overlapping with another candidate region, an evaluation of the probability of being a region corresponding to a main portion within the image is higher than said evaluation for a candidate region not overlapping with another candidate region, and becomes higher as a degree of overlapping with another candidate region increases.
Claim 13
Dependent Claim
159 words
A recording medium on which is stored a program for executing at a computer a processing comprising: a first step of, on the basis of image data, extracting candidate regions which are assumed to correspond to main portions in an image represented by the image data; a second step of determining, for each of candidate regions which overlap with another candidate region among the extracted candidate regions, a degree of overlapping with another candidate region; and a third step of, for an extracted candidate region, evaluating the probability of being a region corresponding to a main portion in the image, in such a manner that, for a candidate region overlapping with another candidate region, an evaluation of the probability of being a region corresponding to a main portion within the image is higher than said evaluation for a candidate region not overlapping with another candidate region, and becomes higher as a degree of overlapping with another candidate region increases.
References Cited (Backward Citations)
JPS52156624A
Cited
JPS5312330A
Cited
JPS53145620A
Cited
JPS53145622A
Cited
JPS53145621A
Cited
JPH04346333A
Cited
US5907631A
Cited
US5501538A
Cited
US5710831A
Cited
US5867593A
Cited
US5629752A
Cited
JPH08184925A
Cited
JPH08183925A
Cited
JPH09138471A
Cited
US5881171A
Cited
US5930391A
Cited
US5978100A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2005-09-02 | 2006-03-04 | 2006-09-03 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2009-09-02 | 2010-03-04 | 2010-09-03 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2013-09-02 | 2014-03-04 | 2014-09-03 | $7700.00 | Window Closed / Lapsed |