Patent US6163622A successfully refreshed from Google Patents.
US6163622A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image retrieval system
Assignee: US Philips Corp
•
Filing: 1997-12-18
•
Granted: 2000-12-19
•
Expires: 2017-12-18
Abstract
Abstract In an image retrieval system, a database with a large number of images is searched to find one or more images meeting the specification of a user. This specification is given in the form of a query image. The system determines the similarity between the query image and a particular image from the database by comparing the color histograms of the two images. The histograms are treated as statistical distributions and the similarity is determined on the basis of an information theoretic measure of the distributions. In a first embodiment, the similarity is determined using the Kullback informational divergence of the two histograms. In a second embodiment, the similarity is based on the entropy of the distribution of similarity coefficients of the two histograms is used.
Inventors
- 👤 Mohammed S. Abdel-Mottaleb
- 👤 Ranjit P. Desai
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 11:03
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/50; G06F16/58; G06F16/583; G06F16/5846; G06F16/5838; G06V; G06V10/00; G06V10/70; G06V10/74; G06V10/75; G06V10/758; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99933; Y10S707/99936
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
151 words
An image retrieval system comprising: a database with candidate images; entry means for entering a query image; first histogram means for deriving a first query color histogram from the query image; second histogram means for deriving a first candidate color histogram from a selected candidate image; determining means for determining a first similarity between the selected candidate image and the query image on the basis of either: i) a Kullback informational divergence between the first candidate color histogram and the first query color histogram; or ii) the entropy of the distribution of similarity coefficients over bins of the first candidate color histogram and bins of the first query color histogram; and retrieval means for retrieval of the selected candidate image, selection thereof being determined by the determining means on the basis of information conveyed by the first candidate color histogram in response to information requested by the first query color histogram.
Claim 2
Dependent Claim
151 words
An image retrieval system comprising: a database with candidate images; entry means for entering a query image; first histogram means for deriving a first query color histogram from the query image; second histogram means for deriving a first candidate color histogram from a selected candidate image; determining means for determining a first similarity between the selected candidate image and the query image on the basis of either: i) a Kullback informational divergence between the first candidate color histogram and the first query color histogram; or ii) the entropy of the distribution of similarity coefficients over bins of the first candidate color histogram and bins of the first query color histogram; and retrieval means for retrieval of the selected candidate image, selection thereof being determined by the determining means on the basis of information conveyed by the first candidate color histogram in response to information requested by the first query color histogram.
Claim 3
Dependent Claim
39 words
An image retrieval system according to claim 1, wherein the determining means are arranged to determine the first similarity on the basis of the Kullback informational divergence between the first candidate color histogram and the first query color histogram.
Claim 4
Dependent Claim
53 words
An image retrieval system according to claim 2, wherein the Kullback informational divergence is according to the following equation: ##EQU10## in which: S K (O,P) is the similarity between the candidate image and the query image, O(x) is the normalized first query color histogram, and P(x) is the normalized first candidate color histogram.
Claim 5
Dependent Claim
50 words
An image retrieval system according to claim 1, wherein the determining means are arranged to determine the first similarity on the basis of the entropy of the distribution of said similarity coefficients over the bins of the first candidate color histogram and the bins of the first query color histogram.
Claim 6
Dependent Claim
77 words
An image retrieval system according to claim 4, wherein the entropy of the distribution of said similarity coefficients is according to the following equation: ##EQU11## in which: S E (O,P) is the similarity between the candidate image and the query image, H(S) is the entropy of the probability distribution S of the similarity coefficients, and i j is the similarity coefficient between bin j of the candidate color histogram and bin j of the query color histogram.
Claim 7
Dependent Claim
147 words
An image retrieval system according to claim 1, wherein: the first histogram means are arranged to derive the first query color histogram from a first region of the query image and to derive a second query color histogram from a second region of the query image, the second histogram means are arranged to derive the first candidate color histogram from a first region of the selected candidate image and to derive a second candidate color histogram from a second region of the selected candidate image, and the determining means are arranged to determine a second similarity between the selected candidate image and the query image on the basis of the second query color histogram and the second candidate color histogram, and to determine an overall similarity between the selected candidate image and the query image on the basis of a combination of the first and second similarities.
Claim 8
Dependent Claim
31 words
An image retrieval system according to claim 6, wherein the determining means are arranged to determine the overall similarity using median statistics for combining the first similarity and the second similarity.
Claim 9
Dependent Claim
23 words
An image retrieval system according to claim 1, wherein the entry means are arranged to enable the user to compose the query image.
Claim 10
Independent Claim
127 words
A method for determining a similarity between a candidate image and a query image, the method comprising the following steps: a first step for obtaining the query image, a second step for deriving a color histogram of the query image, a third step for obtaining a color histogram of the candidate image, and a determining step for determining similarity between the candidate image and the query image on the basis of the candidate color histogram and the query color histogram such determination being on the basis of either: i) a Kullback informational divergence between the candidate color histogram and the query color histogram; or ii) the entropy of the distribution of similarity coefficients over bins of the candidate color histogram and bins of the query color histogram.
Claim 11
Independent Claim
127 words
A method for determining a similarity between a candidate image and a query image, the method comprising the following steps: a first step for obtaining the query image, a second step for deriving a color histogram of the query image, a third step for obtaining a color histogram of the candidate image, and a determining step for determining similarity between the candidate image and the query image on the basis of the candidate color histogram and the query color histogram such determination being on the basis of either: i) a Kullback informational divergence between the candidate color histogram and the query color histogram; or ii) the entropy of the distribution of similarity coefficients over bins of the candidate color histogram and bins of the query color histogram.
References Cited (Backward Citations)
US4606065A
Cited
US4979225A
Cited
US5048095A
Cited
EP0627726A1
Cited
US5724442A
Cited
US5793888A
Cited
US5809171A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-12-19 | 2004-06-19 | 2004-12-19 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-12-19 | 2008-06-19 | 2008-12-19 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-12-19 | 2012-06-19 | 2012-12-19 | $7700.00 | Window Closed / Lapsed |