Patent US6907141B1 successfully refreshed from Google Patents.
← Back to Patent Explorer
US6907141B1 Expired / Lapsed US ⏱️ 0.0 years remaining

Image data sorting device and image data sorting method

Assignee: Fujifilm Business Innovation Corp
•
Filing: 2000-11-21
•
Granted: 2005-06-14
•
Expires: 2020-11-21
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract The image data sorting device is configured with a characteristic value extraction unit that extracts from an image data piece a characteristic value of the image data piece; a relation evaluation unit that evaluates a mutual relation between the characteristic values extracted from plural image data pieces; a clustering unit that executes clustering to events expressed by the characteristic values of the plural image data pieces on the basis of the evaluation result of the above relation; and a sorting register unit that sorts the plural image data pieces on the basis of the result of the above clustering. The image data sorting device with the above configuration can provide a user with facility of use, whereby the appropriateness of the sorting can be secured without requiring any preprocessing, etc., and automatic sorting of the image data pieces can be carried out independently of the types of the image data pieces.

Inventors

  • 👤 Hitoshi Okamoto

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-09 12:18
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/50; G06F16/58; G06F16/583; G06F16/5838; G06F16/51; G06F18/00; G06F18/20; G06F18/23; G06V; G06V10/00; G06V10/40; G06V10/56; G06V10/70; G06V10/762; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99937

Claims Analysis

Total Claims: 25
Claim 1
Independent Claim 159 words
An image data sorting device comprising: a characteristic value extraction unit that extracts characteristic values of an image data piece from image data pieces, wherein the image data piece is converted into a color space L*a*b and thereafter characteristic values are extracted, wherein extracted characteristic values are expressed in Ij dimensional vector (j=1, 2, . . . , n, here 1≦Ij, 1≦n) in which n types of characteristic value vectors are obtained; a relation evaluation unit that evaluates a mutual relation between the characteristic value vectors that the characteristic value extraction unit extracts from plural image data pieces; a clustering unit that executes clustering to events expressed by the characteristic value vectors of the plural image data pieces on the basis of an evaluation result of the relation acquired by the relation evaluation unit; and a sorting register unit that automatically sorts the plural image data pieces on the basis of a result of clustering by the clustering unit.
Claim 2
Dependent Claim 159 words
An image data sorting device comprising: a characteristic value extraction unit that extracts characteristic values of an image data piece from image data pieces, wherein the image data piece is converted into a color space L*a*b and thereafter characteristic values are extracted, wherein extracted characteristic values are expressed in Ij dimensional vector (j=1, 2, . . . , n, here 1≦Ij, 1≦n) in which n types of characteristic value vectors are obtained; a relation evaluation unit that evaluates a mutual relation between the characteristic value vectors that the characteristic value extraction unit extracts from plural image data pieces; a clustering unit that executes clustering to events expressed by the characteristic value vectors of the plural image data pieces on the basis of an evaluation result of the relation acquired by the relation evaluation unit; and a sorting register unit that automatically sorts the plural image data pieces on the basis of a result of clustering by the clustering unit.
Claim 3
Dependent Claim 80 words
An image data sorting device according to claim 1 , wherein: the characteristic extraction unit extracts the n types of characteristic value vectors as the characteristic value of the image data piece; and the relation evaluation unit, synthesizing the n types of characteristic value vectors to each of the n types of characteristic value vectors that the characteristic value extraction unit extracts from the plural image data pieces, evaluates the relation between the image data pieces based on synthesis result.
Claim 4
Dependent Claim 27 words
An image data sorting device according to claim 1 , wherein the clustering unit executes clustering by means of a non-hierarchical method based on a cluster number.
Claim 5
Dependent Claim 33 words
An image data sorting device according to claim 1 , wherein the clustering unit executes by means of a hierarchical method that joins clusters on the basis of the relation between the clusters.
Claim 6
Dependent Claim 27 words
An image data sorting device according to claim 1 , wherein the clustering unit executes clustering by means of a fuzzy technique that employs a fuzzy theory.
Claim 7
Dependent Claim 29 words
An image data sorting device according to claim 1 , wherein the clustering unit executes clustering by means of a crisp technique that does not employ a fuzzy theory.
Claim 8
Dependent Claim 28 words
An image data sorting device according to claim 1 , wherein the clustering unit includes a cluster number specifying unit that specifies a cluster number when executing clustering.
Claim 9
Dependent Claim 52 words
An image data sorting device according to claim 1 , further comprising: an image storage unit that stores plural image data pieces; and an image management unit that manages the plural image data pieces stored in the image storage unit on the basis of a sorting result by the sorting register unit.
Claim 10
Dependent Claim 57 words
An image data sorting device according to claim 8 , wherein the image management unit manages the plural image data pieces stored in the image storage unit on the basis of the sorting result by the sorting register unit and attribute information relating to the image data pieces, which are given to the plural image data pieces.
Claim 11
Dependent Claim 47 words
An image data sorting device according to claim 8 , wherein, when the image storage unit stores a specific number of image data pieces, the clustering unit and the sorting register unit execute clustering and sorting of the image data pieces stored in the image storage unit.
Claim 12
Dependent Claim 42 words
An image data sorting device according to claim 8 , wherein the clustering unit and the sorting register unit execute clustering and sorting of the image data pieces stored in the image storage unit each time a specific period of time passes.
Claim 13
Dependent Claim 91 words
An image data sorting device according to claim 8 , wherein, when there is a new image data piece to be stored in the image storage unit after clustering and sorting of the image data pieces stored in the image storage unit, the clustering unit and the sorting register unit execute sorting of the new image data pieces in such a manner that the new image data piece belongs to a cluster having the highest relation among existing clusters relating to the image data pieces stored in the image storage unit.
Claim 14
Dependent Claim 59 words
An image data sorting device according to claim 12 , wherein the clustering unit and the sorting register unit execute sorting of the new image data piece on the basis of the relation with the characteristic value acquired from the center of gravity of the existing clusters relating to the image data pieces stored in the image storage unit.
Claim 15
Dependent Claim 63 words
An image data sorting device according to claim 12 , wherein the clustering unit and the sorting register unit execute sorting of the new image data piece on the basis of a center value of the relations between the characteristic value of the new image data piece and the characteristic values of the image data pieces each stored in the image storage unit.
Claim 16
Dependent Claim 65 words
An image data sorting device according to claim 8 , wherein, when more than a specific number of image data pieces are added in the image storage unit after sorting by the sorting register unit, the clustering unit and the sorting register unit destroy the existing sorting and execute clustering and sorting of all of the image data pieces stored in the image storage unit.
Claim 17
Dependent Claim 53 words
An image data sorting device according to claim 8 , wherein, when a specific time passes after sorting by the sorting register unit, the clustering unit and the sorting register unit destroy the existing sorting and execute clustering and sorting of all of the image data pieces stored in the image storage unit.
Claim 18
Dependent Claim 43 words
An image data sorting device according to claim 1 , further comprising an image output unit that outputs image data pieces located near the center of each cluster, upon completion of clustering by the clustering unit and sorting by the sorting register unit.
Claim 19
Dependent Claim 51 words
An image data sorting device according to claim 1 , further comprising an image output unit that outputs image data pieces having a high relation with image data pieces located near the center of each cluster, upon completion of clustering by the clustering unit and sorting by the sorting register unit.
Claim 20
Dependent Claim 26 words
An image data sorting device according to claim 17 , wherein the image output unit outputs only the image data pieces relating to a designated cluster.
Claim 21
Dependent Claim 56 words
An image data sorting device according to claim 17 , wherein, after clustering by the clustering unit and sorting by the sorting register unit have been executed, when clustering by the clustering unit and sorting by the sorting register unit are executed again, the image output unit again outputs image data pieces after being sorted again.
Claim 22
Dependent Claim 129 words
An image data sorting method comprising the steps of: extracting characteristic values of an image data piece from image data pieces, wherein, the image data piece is converted into a color space L*a*b and thereafter characteristic values are extracted, wherein extracted characteristic values are expressed in Ij dimensional vector (j=1, 2, . . . , n, here 1≦Ij, 1≦n) in which n types of characteristic value vectors are obtained; evaluating a mutual relation between each of the n types of characteristic value vectors; executing clustering to events expressed by the n types of characteristic value vectors of the plural image data pieces on the basis of an evaluation result of the relation; and automatically sorting the plural image data pieces on the basis of a result of the clustering.
Claim 23
Dependent Claim 129 words
An image data sorting method comprising the steps of: extracting characteristic values of an image data piece from image data pieces, wherein, the image data piece is converted into a color space L*a*b and thereafter characteristic values are extracted, wherein extracted characteristic values are expressed in Ij dimensional vector (j=1, 2, . . . , n, here 1≦Ij, 1≦n) in which n types of characteristic value vectors are obtained; evaluating a mutual relation between each of the n types of characteristic value vectors; executing clustering to events expressed by the n types of characteristic value vectors of the plural image data pieces on the basis of an evaluation result of the relation; and automatically sorting the plural image data pieces on the basis of a result of the clustering.
Claim 24
Dependent Claim 126 words
An image data sorting method comprising the steps of: extracting n types of characteristic value vectors, wherein an image data piece is converted into a color space L*a*b and thereafter characteristic values are extracted, are expressed by an Ij dimensional vector (j=1, 2, . . . , n, here 1≦Ij, 1≦n) from image data pieces; synthesizing the n types of characteristic value vectors to each of the n types of characteristic value vectors, and evaluating a mutual relation between the image data pieces based on synthesis result; executing clustering to the characteristic value vectors of the plural image data pieces in accordance with an evaluation result of the relation; and automatically sorting the plural image data pieces on the basis of a result of the clustering.
Claim 25
Dependent Claim 126 words
An image data sorting method comprising the steps of: extracting n types of characteristic value vectors, wherein an image data piece is converted into a color space L*a*b and thereafter characteristic values are extracted, are expressed by an Ij dimensional vector (j=1, 2, . . . , n, here 1≦Ij, 1≦n) from image data pieces; synthesizing the n types of characteristic value vectors to each of the n types of characteristic value vectors, and evaluating a mutual relation between the image data pieces based on synthesis result; executing clustering to the characteristic value vectors of the plural image data pieces in accordance with an evaluation result of the relation; and automatically sorting the plural image data pieces on the basis of a result of the clustering.

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2008-06-13 2008-12-13 2009-06-14 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2012-06-13 2012-12-13 2013-06-14 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2016-06-13 2016-12-13 2017-06-14 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag