Abstract:
An object recognition system includes a storage device, a reading unit, an output device, and a processor. The storage device stores a dictionary containing attributes of a plurality of registered objects. The attributes includes at least a category and feature values. The reading unit includes an image capturing device. The processor registers a new object by (i) extracting a feature value of the new object from an image of the new object captured by the image capturing device, (ii) comparing the extracted feature value with feature values of registered objects that are registered in the dictionary to calculate a similarity degree therebetween, (iii) registering the extracted feature value in the dictionary as a determination criteria for an object recognition, and (iv) outputting a notification through the output device prior to the registering, upon a result of the comparing meets a predetermined condition.
Abstract:
An information processing system includes an image capturing device, a storage device in which first and second reference data are stored, and a processor. The first reference data include reference image data for a plurality of code-symbolized items, and the second reference data include reference image data unique to each of non-code-symbolized items. The processor is configured to control the image capturing device to start image capturing and start a code symbol detection process with respect to a captured image of a target item, and determine whether or not the target item is a code-symbolized item based on the first reference data. Further, the processor performs a first identification process based on detection of a code symbol on the target item when the target item is the code-symbolized item, and a second identification process based on the second reference data, when the target item is not the code-symbolized item.
Abstract:
A check-out system according to an embodiment includes an image capturing device that captures an image of a merchandise item. A processor determines whether the captured image includes a symbol on the merchandise item corresponding to a merchandise ID. If the captured image includes the symbol, the processor retrieves the merchandise ID. If the captured image does not include the symbol, the processor identifies the merchandise item based on an object recognition processing. The processor retrieves a corresponding merchandise ID and a merchandise category. The processor determines whether the merchandise item is likely to include the symbol based on the merchandise category. If the merchandise item likely includes the symbol, the processor controls a display to display a message instructing an operator to check for the symbol. The processor performs a settlement processing with respect to the merchandise items corresponding to one or more of the retrieved merchandise IDs.
Abstract:
In one embodiment, an information processing apparatus has an imaging device, a memory, a display and a processor. The processor extracts, based on similarities of an imaged image by the imaging device and reference images of a plurality of commodities which are previously stored in the memory, at least one commodity from the plurality of commodities as a candidate for the commodity imaged by the imaging device. The processor controls the display to display the extracted candidates for commodity in the commodity selection screen in a display form in which the extracted candidates for commodity are weighted in accordance with sizes of the similarities.
Abstract:
In one embodiment, a recognition system has an imaging device, a storage device, and a first processor. The first processor extracts a feature amount of an article contained in image data outputted by the imaging device. The first processor recognizes a commodity to which the detected article corresponds, based on similarities between feature amounts for collation of a first commodity and a second commodity stored in the storage device and the extracted feature amount, and selects the recognized commodity from the storage device, as the commodity to which the detected article corresponds, provided that the recognized corresponding commodity is not the first commodity.
Abstract:
According to an embodiment, an information processing apparatus includes an image pickup device and a processor. The image pickup device sequentially picks up an image of an image pickup target, which is positioned in a predetermined image pickup area by an operator and outputs the picked-up image. When detection of an article from the picked-up image ends, the processor judges whether or not the operator has an intention to pick up the image.
Abstract:
An information processing apparatus includes a storage unit, an image capturing unit, and a processing unit. The storage unit stores a plurality of feature values to be used for object recognition and an update program for the feature values, with respect to each of products registered for sale. The image capturing unit is configured to acquire an image of a product registered for sale. The processing unit is configured to extract a feature value of the product from the acquired image, select one of the plurality of the feature values corresponding to the product as a replacement target, by executing the update program corresponding to the product, and replace the selected feature value with the extracted feature value.