ARTICLE ESTIMATING SYSTEM, ARTICLE ESTIMATING METHOD, AND ARTICLE ESTIMATING PROGRAM

• US 20150003729A1
• Filed: 04/08/2013
• Published: 01/01/2015
• Est. Priority Date: 07/31/2012
• Status: Active Grant

• Current Assignee: Rakuten Group, Inc.
• Original Assignee: Rakuten, Inc. (Rakuten Group, Inc.)
• Inventors: Hayashi, Yasuyuki
• Granted Patent: US 9,311,532 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

A server 2 includes an extraction unit 21, an analysis unit 22, a first estimating unit 24, an information acquisition unit 25 and a second estimating unit 26. The extraction unit 21 extracts an image area for each article. The analysis unit 22 analyzes the image area to acquire analysis information. The first estimating unit 24 narrows down candidates estimated to correspond to the article in the image area based on the analysis information. When the candidates were able to be narrowed down, the information acquisition unit 25 acquires additional information additional information of a reference article. The second estimating unit 26 attempts a narrowing process based on the additional information of the reference article in addition to the analysis information, for the image area including a spine, which is an image area in which candidates were unable to be narrowed down.

Claims

1-9. -9. (canceled)

10. An article estimating system configured to be able to acquire identification information for identifying an article and additional information for the article from a storage which stores the identification information and the additional information in association with each other for each of a plurality of articles each having a cover and a spine, the article estimating system comprising:

at least one memory operable to store program code;

at least one processor operable to read said program code and operate as instructed by said program code, said program code including;

image acquisition code which acquires an image including the plurality of articles;

extraction code which extracts, for each article, an image area showing the article from the acquired image;

analysis code which analyzes the plurality of extracted image areas to acquire analysis information;

first estimating code which attempts a process of narrowing down candidates of identification information estimated to correspond to the article in the image area among identification information of the plurality of articles stored in the storage to a predetermined number or less based on the acquired analysis information, for each of the plurality of image areas;

information acquisition code which acquires additional information for the article of the candidate from the storage as additional information of a reference article when candidates were able to be narrowed down to a predetermined number or less for the at least one image area by the first estimating code; and

second estimating code which attempts the process of narrowing down candidates of the estimated identification information to a predetermined number or less, based on the additional information of the reference article in addition to the analysis information, for the image area including a spine, which is an image area in which candidates were unable to be narrowed down to a predetermined number or less based on the analysis information by the first estimating code when the additional information of the at least one reference article was acquired.

11. The article estimating system according to claim 10, wherein;

size information indicating a size of a spine of the article is included in the additional information stored in the storage, and

when the size information of the at least one reference article was acquired, the second estimating code attempts the process of narrowing down candidates of the estimated identification information to a predetermined number or less, based on the size information of the reference article in addition to the analysis information, for the image area including a spine, which is the image area in which the candidates were unable to be narrowed down to a predetermined number or less based on the analysis information by the first estimating code.

12. The article estimating system according to claim 10, wherein:

page number information indicating the number of pages of the article is included in the additional information stored in the storage, and

when the page number information of the at least one reference article was acquired, the second estimating code attempts the process of narrowing down candidates of the estimated identification information to a predetermined number or less, based on a thickness estimated from the page number information of the reference article in addition to the analysis information, for the image area including a spine, which is the image area in which the candidates were unable to be narrowed down to a predetermined number or less based on the analysis information by the first estimating code.

13. The article estimating system according to claim 10, wherein:

series information indicating whether the article constitutes a series with other articles is included in the additional information stored in the storage, and

when the series information of the at least one reference article was acquired, the second estimating code attempts the process of narrowing down candidates of estimated identification information to a predetermined number or less, based on the series information of the reference article in addition to the analysis information, for the image area including a spine adjacent to the reference article, which is the image area in which the candidates were unable to be narrowed down to a predetermined number or less based on the analysis information by the first estimating code.

14. The article estimating system according to claim 13, wherein the second estimating code compares a degree of discoloration of a background color of the image area in which candidates were able to be narrowed down to a predetermined number or less by the first estimating code with a degree of discoloration of a background color of the image area in which candidates were unable to be narrowed down to a predetermined number or less by the first estimating code, regards an article in the image area having a smaller degree of discoloration as having a newer number, and attempts the process of narrowing down candidates of the estimated identification information to a predetermined number or less.

15. The article estimating system according to claim 10, wherein:

genre information indicating a genre to which the article belongs is included in the additional information stored in the storage, and

when the genre information of the at least one reference article was acquired, the second estimating code attempts the process of narrowing down candidates of estimated identification information to a predetermined number or less, based on the genre information of the reference article in addition to the analysis information, for the image area including a spine adjacent to the reference article, which is the image area in which the candidates were unable to be narrowed down to a predetermined number or less based on the analysis information by the first estimating code.

16. The article estimating system according to claim 10, wherein:

information of a title and an author of the article is included in the additional information stored in the storage,

the analysis code acquires character information as the analysis information by performing an OCR process on the plurality of extracted image areas, and

the first estimating code attempts a process of narrowing down candidates of the identification information estimated to correspond to an article in the image area from among identification information of the plurality of articles stored in the storage to a predetermined number or less, based on the acquired character information and the stored information of the title and the author.

17. An article estimating method configured so that an article estimating system having at least one processor is able to acquire identification information for identifying an article and additional information for the article from a storage which stores the identification information and the additional information in association with each other for each of a plurality of articles each having a cover and a spine, said at least one processor:

acquiring an image including the plurality of articles;

extracting, for each article, an image area showing the article from the acquired image;

analyzing the plurality of extracted image areas to acquire analysis information;

attempting to narrow down candidates of identification information estimated to correspond to the article in the image area among identification information of the plurality of articles stored in the storage to a predetermined number or less based on the acquired analysis information, for each of the plurality of image areas;

acquiring additional information for the article of the candidate from the storage as additional information of a reference article when candidates were able to be narrowed down to a predetermined number or less for the at least one image area; and

further attempting to narrow down candidates of the estimated identification information to a predetermined number or less, based on the additional information of the reference article in addition to the analysis information, for the image area including a spine, which is an image area in which candidates were unable to be narrowed down to a predetermined number or less based on the analysis information when the additional information of the at least one reference article was acquired.