Object recognition apparatus and method for managing data used for object recognition

US9805357B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9805357-B2
Application numberUS-201514800169-A
CountryUS
Kind codeB2
Filing dateJul 15, 2015
Priority dateJul 30, 2014
Publication dateOct 31, 2017
Grant dateOct 31, 2017

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

An apparatus for managing data used for object recognition includes an image capturing unit configured to capture an image of an object, a storage unit storing image data of products registered for sale, an operation panel configured to receive a user selection, and a processor configured to determine the products registered for sale that are similar to the object, based on the captured image and the image data, display the similar products on the operation panel as user selectable items, determine one or more of the similar products designated by the user selection, and invalidate the designated similar products so that efficiency of object recognition by the apparatus can be improved.

First claim

Opening claim text (preview).

What is claimed is: 1. A method for updating product data used for object recognition and carrying out object recognition using the updated data, comprising: maintaining, for each of products registered for sale, image data, inventory data, and a valid flag indicating validity of the product for the object recognition, in a storage device; with respect to each product selected among the registered products, carrying out an update operation including: determining whether or not the selected product is in inventory based on the inventory data of the selected product; when the selected product is determined to be in inventory, setting the valid flag if the valid flag is not set, and maintaining the valid flag if the valid flag is set; and when the selected product is determined to be not in inventory, clearing the valid flag if the valid flag is set, and maintaining a state of the valid flag if the valid flag is not set; and displaying, on a display, a plurality of selectable objects each of which corresponds to one of candidate products that are selected from the registered products based on a feature value obtained from a captured image and the image data of the registered products, wherein a selectable object corresponding to a candidate product for which the valid flag is set is displayed differently from a selectable object corresponding to a candidate product for which the valid flag is not set. 2. The method according to claim 1 , further comprising: maintaining, for each of products registered for sale, an out-of-stock flag indicating an inventory state of the product, wherein the update operation further includes: when the selected product is determined to be in inventory, clearing the out-of-stock flag if the out-of-stock flag is set, and maintaining a state of the out-of-stock flag if the out-of-stock flag is not set; and when the selected product is determined to be not in inventory, setting the out-of-stock flag if the out-of-stock flag is not set, and maintaining the out-of-stock flag if the stock-out flag is set. 3. The method according to claim 1 , wherein the image data of a product registered for sale include one or more feature values representing a feature of a surface of the product. 4. The method according to claim 1 , wherein a luminance of the selectable object corresponding to the candidate product for which the valid flag is set is different from a luminance of the selectable object corresponding to the candidate product for which the valid flag is not set. 5. The method according to claim 1 , wherein the update is automatically carried out at a predetermined time of a day. 6. A non-transitory computer-readable medium comprising a program that is executable in a computing device of a server system to cause the computing device to perform a method of updating product data used for object recognition and carrying out object recognition using the updated data, the method comprising: maintaining, for each of products registered for sale, image data, inventory data, and a valid flag indicating validity of the product for the object recognition, in a storage device; with respect to each product selected among the registered products, carrying out an update operation including: determining whether or not the selected product is in inventory based on the inventory data of the selected product; when the selected product is determined to be in inventory, setting the valid flag if the valid flag is not set, and maintaining the valid flag if the valid flag is set; and when the selected product is determined to be not in inventory, clearing the valid flag if the valid flag is set, and maintaining a state of the valid flag if the valid flag is not set; and displaying, on a display, a plurality of selectable objects each of which corresponds to one of candidate products that are selected from the registered products based on a feature value obtained from a captured image and the image data of the registered products, wherein a selectable object corresponding to a candidate product for which the valid flag is set is displayed differently from a selectable object corresponding to a candidate product for which the valid flag is not set. 7. The non-transitory computer-readable medium according to claim 6 , wherein the method further comprises: maintaining, for each of products registered for sale, an out-of-stock flag indicating an inventory state of the product, wherein the update operation further includes: when the selected product is determined to be in inventory, clearing the out-of-stock flag if the out-of-stock flag is set, and maintaining a state of the out-of-stock flag if the out-of-stock flag is not set; and when the selected product is determined to be not in inventory, setting the out-of-stock flag if the out-of-stock flag is not set, and maintaining the out-of-stock flag if the out-of-stock flag is set. 8. The non-transitory computer-readable medium according to claim 6 , wherein the image data of a product registered for sale include one or more feature values representing a feature of a surface of the product. 9. The non-transitory computer-readable medium according to claim 6 , wherein a luminance of the selectable object corresponding to the candidate product for which the valid flag is set is different from a luminance of the selectable object corresponding to the candidate product for which the valid flag is not set. 10. The non-transitory computer-readable medium according to claim 6 , wherein the update is automatically carried out at a predetermined time of a day. 11. A server system comprising: a storage device; and a processor configured to carry out an operation of updating product data used for object recognition and carrying out object recognition using the updated data, which includes the steps of: maintaining, for each of products registered for sale, image data, inventory data, and a valid flag indicating validity of the product for the object recognition, in the storage device; with respect to each product selected among the registered products, carrying out an update operation including: determining whether or not the selected product is in inventory based on the inventory data of the selected product; when the selected product is determined to be in inventory, setting the valid flag if the valid flag is not set, and maintaining the valid flag if the valid flag is set; and when the selected product is determined to be not in inventory, clearing the valid flag if the valid flag is set, and maintaining a state of the valid flag if the valid flag is not set; and displaying, on a display, a plurality of selectable objects each of which corresponds to one of candidate products that are selected from the registered products based on a feature value obtained from a captured image and the image data of the registered products, wherein a selectable object corresponding to a candidate product for which the valid flag is set is displayed differently from a selectable object corresponding to a candidate product for which the valid flag is not set. 12. The server system according to claim 11 , wherein the steps further comprises: maintaining, for each of products registered for sale, an out-of-stock flag indicating an inventory state of the product, wherein the update operation further includes: when the selected product is determined to be in inventory, clearing the out-of-stock flag if the out-of-stock flag is set, and maintaining a state of the out-of-stock flag if the out-of-stock flag is not set; and when the selected product is determined to be not in inventory, setting the out-of-stock flag

Assignees

Inventors

Classifications

  • G06Q10/087Primary

    Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

  • the supervisor being a human, e.g. interactive learning with a human teacher · CPC title

  • Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries · CPC title

  • G06Q20/208Primary

    Input by product or record sensing, e.g. weighing or scanner processing · CPC title

  • Interactive pattern learning with a human teacher · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9805357B2 cover?
An apparatus for managing data used for object recognition includes an image capturing unit configured to capture an image of an object, a storage unit storing image data of products registered for sale, an operation panel configured to receive a user selection, and a processor configured to determine the products registered for sale that are similar to the object, based on the captured image a…
Who is the assignee on this patent?
Toshiba Tec Kk
What technology area does this patent fall under?
Primary CPC classification G06Q10/087. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Oct 31 2017 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 2 related publications on this page (citations in our corpus or others sharing the same primary CPC).