US6697502B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image processing method for detecting human figures in a digital image
Assignee: Monument Peak Ventures LLC
•
Filing: 2000-12-14
•
Granted: 2004-02-24
•
Expires: 2020-12-14
Abstract
Abstract A digital image processing method for detecting human figures in a digital color image, comprising the steps of: providing a digital color image having pixels representing RGB values; segmenting the image into non-overlapping regions of homogeneous color or texture; detecting candidate regions of human skin color; detecting candidate regions of human faces; and for each candidate face region, constructing a human figure by grouping regions in the vicinity of the face region according to a pre-defined graphical model of the human figure, giving priority to human skin color regions.
Inventors
- 👤 Jiebo Luo
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 05:14
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/40; G06F; G06F18/00; G06F18/20; G06F18/29; G06T7/10; G06T7/11; G06V; G06V10/00; G06V10/70; G06V10/84; G06V40/00; G06V40/10; G06V40/16; G06V40/161; G06T2207/00; G06T2207/10; G06T2207/10024; G06T2207/30; G06T2207/30196; G06T2207/30201
Claims Analysis
Total Claims: 15
Claim 1
Independent Claim
91 words
A digital image processing method for detecting human figures in a digital color image, comprising the steps of: providing a digital color image having pixels representing RGB values; segmenting the digital color image into non-overlapping regions of homogeneous color or texture; detecting candidate regions of human skin color; detecting candidate regions of human faces; and for each candidate face region, constructing a human figure by grouping regions in the vicinity of the face region according to a pre-defined graphical model of the human figure, giving priority to human skin color regions.
Claim 2
Dependent Claim
91 words
A digital image processing method for detecting human figures in a digital color image, comprising the steps of: providing a digital color image having pixels representing RGB values; segmenting the digital color image into non-overlapping regions of homogeneous color or texture; detecting candidate regions of human skin color; detecting candidate regions of human faces; and for each candidate face region, constructing a human figure by grouping regions in the vicinity of the face region according to a pre-defined graphical model of the human figure, giving priority to human skin color regions.
Claim 3
Dependent Claim
21 words
The method as claimed in claim 1 , wherein the segmenting step includes classifying pixels having RGB values based on color/texture.
Claim 4
Dependent Claim
23 words
The method as claimed in claim 1 , wherein the step of detecting skin color regions includes classifying pixels having predetermined RGB values.
Claim 5
Dependent Claim
30 words
The method as claimed in claim 3 , wherein the graphical model is represented by a semantic net in which the links are specified by a set of pre-determined rules.
Claim 6
Dependent Claim
32 words
The method as claimed in claim 3 , wherein the graphical model is represented by a Bayesian network in which the links are specified by a set of pre-determined conditional probability matrices.
Claim 7
Dependent Claim
32 words
The method as claimed in claim 3 , wherein the graphical model is represented by a factor graph in which the links are function nodes specified by a set of pre-determined functions.
Claim 8
Dependent Claim
44 words
The method as claimed in claim 1 , wherein the step of detecting face regions includes searching for a predetermined intensity pattern representative of a human face, by matching the shape of and the amount of intensity valley features within a skin color region.
Claim 9
Dependent Claim
27 words
The method as claimed in claim 1 , wherein the constructing step includes grouping skin color regions as exposed body parts, and non-skin colored regions as clothing.
Claim 10
Dependent Claim
17 words
The method as claimed in claim 8 , wherein each node comprises one or more segmented regions.
Claim 11
Dependent Claim
24 words
The method as claimed in claim 1 , wherein the graphical model is derived based on anthropological proportions and kinetics of human body movements.
Claim 12
Dependent Claim
29 words
The method as claimed in claim 1 , wherein the constructing step includes using a collection of graphical models of the human figure for different poses and picture framing.
Claim 13
Dependent Claim
31 words
The method as claimed in claim 1 , wherein the graphical model comprises a collection of nodes corresponding to body parts, and links between nodes characterizing the relationships between body parts.
Claim 14
Dependent Claim
92 words
A digital image processing method for detecting human figures in a digital color image having pixels representing RGB values, comprising the steps of: providing a digital color image having pixels representing RGB values; segmenting the digital color image into non-overlapping regions of homogeneous color or texture; selecting a region as a candidate face region; attempting to construct a human figure by grouping regions in the vicinity according to a pre-defined graphical model of the human figure; and identifying the grouped regions as a human figure if the constructed figure meets predetermined criteria.
Claim 15
Dependent Claim
92 words
A digital image processing method for detecting human figures in a digital color image having pixels representing RGB values, comprising the steps of: providing a digital color image having pixels representing RGB values; segmenting the digital color image into non-overlapping regions of homogeneous color or texture; selecting a region as a candidate face region; attempting to construct a human figure by grouping regions in the vicinity according to a pre-defined graphical model of the human figure; and identifying the grouped regions as a human figure if the constructed figure meets predetermined criteria.
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) | 2007-02-23 | 2007-08-25 | 2008-02-24 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-02-23 | 2011-08-25 | 2012-02-24 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-02-23 | 2015-08-25 | 2016-02-24 | $7700.00 | Window Closed / Lapsed |