COMMODITY RECOGNITION APPARATUS AND COMMODITY RECOGNITION METHOD

• US 20140126772A1
• Filed: 10/29/2013
• Published: 05/08/2014
• Est. Priority Date: 11/05/2012
• Status: Active Grant

• Current Assignee: Toshiba Tec Corporation (Toshiba Corporation)
• Original Assignee: Toshiba Tec Corporation (Toshiba Corporation)
• Inventors: Miyakoshi, Hidehiko
• Granted Patent: US 9,235,764 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/68 Food, e.g. fruit or vegetables

Abstract

A candidate output element configured to output recognition target commodities as candidates of a recognized commodity in a descending order of the similarity degrees calculated by the similarity degree calculation element, a distance measurement element configured to measure the distance from the image capturing section to a commodity photographed by the image capturing section, and a changing element configured to change the number of candidates of a recognized commodity output by the candidate output element according to the distance measured by the distance measurement element.

Claims

1. A commodity recognition apparatus, comprising:

a feature amount extraction element configured to extract an appearance feature amount of a commodity contained in an image captured by an image capturing section for capturing a commodity;

a similarity degree calculation element configured to calculate, for each recognition target commodity, a similarity degree representing how much similar the appearance feature amount is to a feature amount data which represents surface information of a commodity and is stored in a recognition dictionary file for each recognition target commodity by comparing the appearance feature amount extracted by the feature amount extraction element with the feature amount data;

a candidate output element configured to output recognition target commodities as candidates of a recognized commodity in a descending order of the similarity degrees calculated by the similarity degree calculation element;

a distance measurement element configured to measure the distance from the image capturing section to the commodity photographed by the image capturing section; and

a changing element configured to change the number of the candidates of a recognized commodity output by the candidate output element according to the distance measured by the distance measurement element.

2. The commodity recognition apparatus according to claim 1, wherein the candidate output, which displays a recognition target commodity of candidates of a recognized commodity in a selectable manner, includes a first determination element for determining the recognition target commodity selected from the candidates of a recognized commodity as a commodity photographed by the image capturing section.

3. The commodity recognition apparatus according to claim 1, further comprising a distance determination configured to determine whether or not the distance measured by the distance measurement element is a proper value;

wherein

the changing element decreases the number of the candidates of a recognized commodity obtained in case that the distance is a proper value compared with that in case that the distance is not the proper value.

4. The commodity recognition apparatus according to claim 3, further comprising a second determination element configured to determine, in a case in which the distance is determined by the distance determination element to be the proper value and the highest similarity degree of the recognition target commodity output by the candidate output element as a candidate of a recognized commodity is greater than a preset determination value, a commodity having the highest similarity degree as a commodity photographed by the image capturing section.

5. The commodity recognition apparatus according to claim 3, further comprising a warning element configured to output a warning if the distance determination element determines that the distance is not to be the proper value.

6. A commodity recognition method, comprising:

extracting an appearance feature amount of a commodity contained in an image captured by an image capturing section;

calculating, for each recognition target commodity, a similarity degree representing how much similar the appearance feature amount is to the feature amount data which represents surface information of a commodity and is stored in a recognition dictionary file for each recognition target commodity by comparing the appearance feature amount with the feature amount data;

outputting recognition target commodities as candidates of a recognized commodity in a descending order of the similarity degrees; and

changing the number of the candidates of a recognized commodity according to the distance between the image capturing section and a commodity photographed by the image capturing section.