Context-based image recognition for consumer market research
US-2016125265-A1 · May 5, 2016 · US
US10445570B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10445570-B2 |
| Application number | US-201815892894-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 9, 2018 |
| Priority date | Mar 21, 2017 |
| Publication date | Oct 15, 2019 |
| Grant date | Oct 15, 2019 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An information processing apparatus includes a detecting unit that detects a feature location in an image, a sorting unit that sorts regions in the image into plural regions different in terms of attribute, a memory that stores a rule that associates an attribute of a region with a priority of the region, and a determining unit that checks the feature locations detected from two images against each other, and determines a similarity between the two images by accounting for, in check results, the priority of the region associated by the rule with the attribute of the region containing the feature locations.
Opening claim text (preview).
What is claimed is: 1. An information processing apparatus comprising: a detecting unit that detects a feature location in an image; a sorting unit that sorts regions in the image into a plurality of regions different in terms of attribute; a memory that stores a rule that associates an attribute of a region with a priority of the region; and a determining unit that checks the feature locations detected from two images against each other, and determines a similarity between the two images by accounting for, in check results, the priority of the region associated by the rule with the attribute of the region containing the feature locations. 2. The information processing apparatus according to claim 1 , wherein the rule further associates a position of the region in the image with the priority of the region, and wherein the determining unit determines the similarity by accounting for the priority of the region associated by the rule with the position of the region containing the feature locations to be checked. 3. The information processing apparatus according to claim 2 , wherein the rule further associates a magnitude of a deviation between the positions of regions having a common attribute in the two images with the priority of the region, and wherein the determining unit determines the similarity by accounting for the priority of the regions associated by the rule with the magnitude of the deviation between the positions of the regions containing the feature locations to be checked. 4. The information processing apparatus according to claim 3 , wherein the rule further associates a size of a feature quantity of the feature location contained in the region with the priority of the region; and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the size of the feature quantity of the region containing the feature locations to be checked. 5. The information processing apparatus according to claim 3 , further comprising an identifying unit that identifies a type of an application program that has been used to designate an image that serves as a determination target for the similarity, wherein the rule associates the attribute of the region with the priority of the region, on each type of the application program, and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the attribute of the region containing the feature locations to be checked, and the type of the identified application program. 6. The information processing apparatus according to claim 2 , wherein the rule further associates a size of a feature quantity of the feature location contained in the region with the priority of the region; and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the size of the feature quantity of the region containing the feature locations to be checked. 7. The information processing apparatus according to claim 2 , further comprising an identifying unit that identifies a type of an application program that has been used to designate an image that serves as a determination target for the similarity, wherein the rule associates the attribute of the region with the priority of the region, on each type of the application program, and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the attribute of the region containing the feature locations to be checked, and the type of the identified application program. 8. The information processing apparatus according to claim 7 , wherein the region contains a first region where characters are displayed, and a second region where a photograph or a picture is displayed, wherein the rule associates the attribute with the priority such that a priority of the first region is set to be higher than a priority of the second region if the application program is configured to edit a character string, and such that the priority of the second region is set to be higher than the priority of the first region if the application program is configured to edit an image. 9. The information processing apparatus according to claim 1 , wherein the rule further associates a magnitude of a deviation between the positions of regions having a common attribute in the two images with the priority of the regions, and wherein the determining unit determines the similarity by accounting for the priority of the regions associated by the rule with the magnitude of the deviation between the positions of the regions containing the feature locations to be checked. 10. The information processing apparatus according to claim 9 , wherein the rule further associates a size of a feature quantity of the feature location contained in the region with the priority of the region; and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the size of the feature quantity of the region containing the feature locations to be checked. 11. The information processing apparatus according to claim 9 , further comprising an identifying unit that identifies a type of an application program that has been used to designate an image that serves as a determination target for the similarity, wherein the rule associates the attribute of the region with the priority of the region, on each type of the application program, and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the attribute of the region containing the feature locations to be checked, and the type of the identified application program. 12. The information processing apparatus according to claim 1 , wherein the rule further associates a size of a feature quantity of the feature location contained in the region with the priority of the region; and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the size of the feature quantity of the region containing the feature locations to be checked. 13. The information processing apparatus according to claim 1 , further comprising an identifying unit that identifies a type of an application program that has been used to designate an image that serves as a determination target for the similarity, wherein the rule associates the attribute of the region with the priority of the region, on each type of the application program, and wherein the determining unit determines the similarity by accounting for the priority associated by the rule with the attribute of the region containing the feature locations to be checked, and the type of the identified application program. 14. The information processing apparatus according to claim 13 , wherein the region contains a first region where characters are displayed, and a second region where a photograph or a picture is displayed, wherein the rule associates the attribute with the priority such that a priority of the first region is set to be higher than a priority of the second region if the application program is configured to edit a character string, and such that the priority of the second region is set to be higher than the priority of the first region if the application program is configured to edit an image. 15. The information processing apparatus according to claim 1 , further comprising a content determining unit that determines content of an image, wherein the rule associates the attribute of the region with the priority of the region on a content b
by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation · CPC title
Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title
involving reference images or patches · CPC title
involving the use of two or more images · CPC title
Region-based segmentation · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.