Commodity recognition apparatus and commodity recognition method
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.
1. A commodity recognition apparatus, comprising:
an interface that accesses a recognition dictionary file which stores feature amount data representing surface information for each of a plurality of recognition target commodities obtained from reference images of each recognition target commodity captured from a proper distance;
an image capturing section that captures an image of a commodity;
a distance measurement unit that measures a distance from the image capturing section to the commodity captured by the image capturing section; and
a processor, wherein the processor is configured to:
extract an appearance feature amount of the commodity contained in the image captured by the image capturing section;
calculate, for each recognition target commodity, a similarity degree representing how similar the appearance feature amount is to the feature amount data by comparing the appearance feature amount extracted by the feature amount extraction unit with the feature amount data of the recognition dictionary file;
set recognition target commodities having the similarity degree greater than or equal to a first threshold as candidates of a recognized commodity;
determine whether the distance measured by the distance measurement unit is a proper value;
if the measured distance is not a proper value, select and output a first number of recognition target commodities in a descending order of the similarity degree from among the candidates of the recognized commodity; and
if the measured distance is a proper value, select and output a second number of recognition target commodities in a descending order of the similarity degree from among the candidates of the recognized commodity, the second number being smaller than the first number.
2. The commodity recognition apparatus according to claim 1 , wherein the processor is further configured to:
determine the recognition target commodity selected from the output first number or second number of candidates of the recognized commodity as a commodity photographed by the image capturing section.
3. The commodity recognition apparatus according to claim 1 , wherein the processor is further configured to:
determine, in a case where the distance is the proper value and a highest similarity degree of the recognition target commodity set as the candidate of the recognized commodity is greater than a second threshold that is greater than the first threshold, the commodity having the highest similarity degree as a commodity photographed by the image capturing section.
4. The commodity recognition apparatus according to claim 1 , wherein the processor is further configured to output a warning if the distance is not the proper value.
5. A commodity recognition method executed by a commodity recognition apparatus comprising:
an interface that accesses a recognition dictionary file which stores feature amount data representing surface information for each of a plurality of recognition target commodities obtained from reference images of each recognition target commodity captured from a proper distance;
an image capturing section that captures an image of a commodity;
a distance measurement unit that measures a distance from the image capturing section to the commodity captured by the image capturing section; and
a processor;
wherein the processor is configured to:
extract an appearance feature amount of the commodity contained in the image captured by the image capturing section;
calculate, for each recognition target commodity, a similarity degree representing how similar the appearance feature amount is to the feature amount data by comparing the appearance feature amount extracted by the feature amount extraction unit with the feature amount data of the recognition dictionary file;
set recognition target commodities having the similarity degree greater than or equal to a first threshold as candidates of a recognized commodity;
determine whether the distance measured by the distance measurement unit is a proper value;
if the measured distance is not a proper value, select and output a first number of recognition target commodities in a descending order of the similarity degree from among the candidates of the recognized commodity; and
if the measured distance is a proper value, select and output a second number of recognition target commodities in a descending order of the similarity degree from among the candidates of the recognized commodity, the second number being smaller than the first number.
6. The commodity recognition apparatus according to claim 5 , further comprising:
a storage device that stores a range of distance having a recognition rate greater than or equal to a predetermined rate relative to the proper distance as a proper range,
wherein the processor is configured to determine whether the distance measured by the distance measurement unit falls within the proper range as the proper value.