US6253201B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Scalable solution for image retrieval
Assignee: Uniloc 2017 LLC
•
Filing: 1998-06-23
•
Granted: 2001-06-26
•
Expires: 2018-06-23
Abstract
Abstract The invention is a method and apparatus for determining similarity between images based upon a count of the number of similar characterizations of the images. To provide for efficiency in the comparison process, indexed lists of image identifiers are maintained, and the count of similar characterizations of an image is determined by the count of occurrences of the image's identifier in selected lists. The selected lists are determined by a characterization of a target image from which similar images are to be identified. The indexing and retrieval techniques presented herein are suitable for a variety of image characterization techniques, such as characterizations based upon the color content or edge content of partitions of an image. Multiple indexes can be associated with one or more characteristic measures of each partition, allowing for image retrieval based on one or more characteristics of the target image.
Inventors
- 👤 Mohamed Abdel-Mottaleb
- 👤 Max Wu
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 10:07
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/50; G06F16/58; G06F16/583; G06F16/5854; G06F16/5838; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99933; Y10S707/99934; Y10S707/99935
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
98 words
A method of image retrieval, comprising the steps of: partitioning a target image into a plurality of content-independent partitions, characterizing each partition of the plurality of content-independent partitions to form an index value associated with each partition, obtaining a list of image identifiers associated with the index value, accumulating counts of each image identifier in the list of image identifiers associated with each partition of the plurality of content-independent partitions, and retrieving at least one image associated with at least one of the image identifiers, based upon the counts of the at least one of the image identifiers.
Claim 2
Independent Claim
98 words
A method of image retrieval, comprising the steps of: partitioning a target image into a plurality of content-independent partitions, characterizing each partition of the plurality of content-independent partitions to form an index value associated with each partition, obtaining a list of image identifiers associated with the index value, accumulating counts of each image identifier in the list of image identifiers associated with each partition of the plurality of content-independent partitions, and retrieving at least one image associated with at least one of the image identifiers, based upon the counts of the at least one of the image identifiers.
Claim 3
Dependent Claim
39 words
The method of claim 1 , wherein the step of characterizing each partition includes the step of characterizing at least one of: edges of the target image within each partition, and colors of the target image within each partition.
Claim 4
Dependent Claim
39 words
The method of claim 1 , wherein the step of characterizing each partition includes the step of quantizing a characteristic of the target image within each partition to form the index value from a predetermined set of index values.
Claim 5
Dependent Claim
26 words
The method of claim 1 , further including the step of providing a sorted list of image identifiers based on the counts of the image identifiers.
Claim 6
Independent Claim
91 words
A method of indexing an image, comprising the steps of: identifying the image by an image identifier, partitioning the image into a plurality of content independent partitions, characterizing each content independent partition of the plurality of partitions to form at least one index value of a plurality of index values, and appending the image identifier to at least one list of a plurality of lists of image identifiers associated with each partition, the at least one list being determined by the at least one index value that characterizes the each partition.
Claim 7
Independent Claim
91 words
A method of indexing an image, comprising the steps of: identifying the image by an image identifier, partitioning the image into a plurality of content independent partitions, characterizing each content independent partition of the plurality of partitions to form at least one index value of a plurality of index values, and appending the image identifier to at least one list of a plurality of lists of image identifiers associated with each partition, the at least one list being determined by the at least one index value that characterizes the each partition.
Claim 8
Dependent Claim
22 words
The method of claim 5 , wherein the image identifier corresponds to a location of the image in a database of images.
Claim 9
Dependent Claim
37 words
The method of claim 5 , wherein the step of characterizing each partition includes the step of characterizing at least one of: edges of the image within each partition, and colors of the image within each partition.
Claim 10
Dependent Claim
41 words
The method of claim 5 , wherein the step of characterizing each partition includes the step of quantizing a characteristic of the image within each partition to form the at least one index value from a predetermined set of index values.
Claim 11
Dependent Claim
48 words
The method of claim 8 , wherein the step of quantizing the characteristic includes the steps of quantizing the characteristic to a first quantization value of a first set of quantization values, and, quantizing the characteristic to a second quantization value of a second set of quantization values.
Claim 12
Dependent Claim
94 words
An image retrieval system comprising: a partitioner that partitions a target image into a plurality of content independent partitions, a characterizer that characterizes the plurality of content independent partitions into a plurality of target image indexes, and, a search engine, operably coupled to the characterizer, that identifies at least one reference image of a plurality of reference images that is similar to the target image based on a count of occurrences of an identifier of the at least one reference image in a plurality of lists corresponding to the plurality of target image indexes.
Claim 13
Dependent Claim
94 words
An image retrieval system comprising: a partitioner that partitions a target image into a plurality of content independent partitions, a characterizer that characterizes the plurality of content independent partitions into a plurality of target image indexes, and, a search engine, operably coupled to the characterizer, that identifies at least one reference image of a plurality of reference images that is similar to the target image based on a count of occurrences of an identifier of the at least one reference image in a plurality of lists corresponding to the plurality of target image indexes.
Claim 14
Dependent Claim
120 words
The image retrieval system of claim 10 , wherein the search engine includes: a list extractor that extracts each list of the plurality of lists from indexed lists of image identifiers based on each target index of the plurality of target indexes, an accumulator, operably coupled to the list extractor, that accumulates a plurality of counts, each count of the plurality of counts corresponding to occurrences of each identifier of a plurality of reference image identifiers in the each list that is extracted by the list extractor, and, a sorter, operably coupled to the accumulator, that identifies the at least one reference image that corresponds to an at least one identifier having a highest count of the plurality of counts.
Claim 15
Dependent Claim
46 words
The image retrieval system of claim 10 , wherein the search engine further includes a selector that selects the at least one reference image from the plurality of reference images for rendering on a display based on the at least one identifier having the highest count.
Claim 16
Dependent Claim
41 words
The image retrieval system of claim 10 , wherein the characterizer also characterizes the plurality of reference images to produce indexed lists of image identifiers, from which the plurality of lists corresponding to the plurality of target image indexes is derived.
Claim 17
Dependent Claim
86 words
The image retrieval system of claim 10 , wherein the characterizer includes: a characteristic processor, operably coupled to the partitioner, that processes each content independent partition of the plurality of partitions based on a descriptive characteristic of the each partition to produce characteristic measures of a plurality of characteristic measures corresponding to the plurality of partitions, and, a quantizer, operably coupled to the characteristic processor, that produces the plurality of target image indexes based on the plurality of characteristic measures corresponding to the plurality of partitions.
Claim 18
Dependent Claim
29 words
The image retrieval system of claim 14 , wherein the descriptive characteristic of the each partition is a count of occurrences of edges that are contained in the partition.
Claim 19
Dependent Claim
55 words
The image retrieval system of claim 15 , wherein the edges that are contained in the partition are distinguished as horizontal edges, vertical edges, right-diagonal edges, and left-diagonal edges, and the count of occurrences of edges is a histogram of occurrences of the horizontal edges, the vertical edges, the right-diagonal edges, and the left-diagonal edges.
Claim 20
Dependent Claim
29 words
The image retrieval system of claim 14 , wherein the descriptive characteristic of the each partition is a count of occurrences of colors that are contained in the partition.
Claim 21
Dependent Claim
42 words
The image retrieval system of claim 17 , wherein the colors are distinguished as a plurality of color centers, and the count of occurrences of colors is a histogram of occurrences of an each quantized color of the plurality of color centers.
Claim 22
Dependent Claim
63 words
The image retrieval system of claim 14 , wherein the characteristic measures is a histogram of occurrences of elements of the descriptive characteristic, and wherein the quantizer normalizes the histogram of occurrences to produce a normalized histogram and selects each index of the plurality of target image indexes based on the normalized histogram corresponding to the each partition of the plurality of partitions.
Claim 23
Dependent Claim
32 words
The image retrieval system of claim 14 , wherein the quantizer produces more than one of the plurality of target image indexes based on a plurality of sets of overlapping quantization levels.
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) | 2004-06-25 | 2004-12-25 | 2005-06-26 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2008-06-25 | 2008-12-25 | 2009-06-26 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2012-06-25 | 2012-12-25 | 2013-06-26 | $7700.00 | Window Closed / Lapsed |