Patent US2607143A successfully refreshed from Google Patents.
Patent US1868763A successfully refreshed from Google Patents.
EP0899680B1
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method for automatic detection of human eyes in digital images
Assignee: Eastman Kodak Co
•
Filing: 1998-08-15
•
Granted: 2006-03-29
•
Expires: 2018-08-15
Abstract
No abstract record available.
Inventors
- 👤 Jiebo c/o Eastman Kodak Company Luo
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-06 11:30
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/10; G06V40/18
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
194 words
A computer program product for locating first and second human eye objects each having substantially the same physical characteristics, and the ratio of the distance between the first and second human eye objects and the size of each human eye object is substantially invariant, the computer program product comprising: a computer readable storage medium having a computer program stored thereon for performing the steps of: (a) determining (S4) a potential flesh region in an image (b) determining (S10) valley regions in the image; (c) performing (S14) matching in the image using a template in a neighborhood of the valley regions within the flesh regions to determine a plurality of locations that give a desirable match of the human eye object relative to the template; and (d) finding (S22) a best pair of locations of human eye objects by computing figures of merit individually or in combination for a plurality of verification criteria, said computing of said figures of merit including measuring as one of said verification criteria, the difference between an orientation of a line connecting first and second human eye objects, and an average orientation of the first and second human eye objects.
Claim 2
Dependent Claim
60 words
The computer program product as in claim 1 further comprising either or both (e) determining an estimate size of both the first and second objects based on a shape and size of a determined flesh region or (f) determining an estimate orientation of both the first and second objects based on the shape and orientation of the determined flesh region.
Claim 3
Dependent Claim
21 words
The computer program product as in claim 4 wherein said performing matching further comprises using cross-correlation to identify said desirable locations.
Claim 4
Dependent Claim
57 words
The computer program product as in claim 1, wherein said figures of merit include one or more members selected from the group consisting of orientation, proportion, profile, symmetry, and centrality of pairs of human eye objects matched to the template, and said computing includes determining a pair of locations that give a best combined figure of merit.
Claim 5
Dependent Claim
32 words
The computer program product as in claim 4, wherein said computing of said proportion includes computing a distance between the first and second human eye objects for satisfying an anthropological prior model.
Claim 6
Dependent Claim
42 words
The computer program product as in claim 5, wherein said computing of said profile includes pre-detemnining a model of an eye-to-eye profile and determining an actual profile from the image and computing a goodness-of-fit between the actual profile and the model profile.
Claim 7
Dependent Claim
36 words
The computer program product as in claim 1, wherein said figures of merit include one or more members selected from the group consisting of orientation, proportion, profile, symmetry, evidence of mouth, centrality, and combined correlation score.
Claim 8
Dependent Claim
26 words
The computer program product as in claim 1 further comprising the step of creating an image block of a same size and orientation as the template.
Claim 9
Dependent Claim
29 words
The computer program product as in claim 8 further comprising the step of normalizing at least one of the template and the image block for maximizing robustness of matching.
Claim 10
Dependent Claim
51 words
The computer program product as in claim 9 further comprising the steps of: extracting individual sub-zones in both the template and the image block; and performing cross-correlation for each corresponding sub-zone; and computing an overall cross-correlation score for the image block if the cross-correlation score for each sub-zone exceeds a threshold.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.