JP7274644B2 - Article recognition device - Google Patents

Description

Embodiments of the present invention relate to article recognition devices.

2. Description of the Related Art Some article recognition apparatuses extract feature points from an image of an article and recognize the article based on the extracted feature points. Such an article recognition device may extract feature points from an area other than the article by including the pattern of the installation table on which the article is installed, the external light, or the like in the image. As a result, the object recognition device has a problem that the object recognition accuracy may deteriorate.

JP 2017-123163 A

In order to solve the above problems, an article recognition device capable of effectively recognizing articles is provided.

According to embodiments, an article recognition device comprises an image interface, a distance information interface, and a processor. The image interface acquires a photographed image of the article placed on the installation table. A distance information interface acquires distance information indicating a distance from the installation table and the article. The processor extracts image information for recognizing the article from the image, generates a list including the image information, and extracts image information at the same distance from the installation table from the list based on the distance information. and recognize the item based on the image information of the list.

FIG. 1 is a diagram schematically showing a configuration example of an article recognition device according to the first embodiment. FIG. 2 is a block diagram showing a configuration example of the article recognition device according to the first embodiment. FIG. 3 is a diagram showing an example of a captured image according to the first embodiment. FIG. 4 is a diagram showing an example of feature point information according to the first embodiment. FIG. 5 is a diagram showing an example of feature point information according to the first embodiment. FIG. 6 is a diagram showing an example of feature point information according to the first embodiment. FIG. 7 is a diagram showing an example of feature point information according to the first embodiment. FIG. 8 is a flow chart showing an operation example of the article recognition device according to the first embodiment. FIG. 9 is a diagram showing an example of feature point information according to the second embodiment. FIG. 10 is a diagram showing an example of feature point information according to the second embodiment.

Hereinafter, embodiments will be described with reference to the drawings.
(First embodiment)
First, the first embodiment will be explained.
An article recognition device according to the first embodiment recognizes an article. An article recognition device photographs an article set on itself. An article recognition device extracts feature points from a photographed image. The article recognition device recognizes the article based on the extracted feature points.

For example, an article recognition device is installed at a cash register or the like for payment of merchandise. For example, an article recognition device recognizes merchandise. Also, the article recognition device may be used to pay for the recognized merchandise. The article recognition device may be installed as a self-checkout where users themselves perform payment processing. Also, the article recognition device may be installed as a normal cash register where a store clerk performs payment processing. Moreover, it may be installed as an article recognition device, an inspection device for determining whether or not an article is purchased after settlement, or the like.

FIG. 1 is a diagram schematically showing a configuration example of an article recognition device 1 according to an embodiment. As shown in FIG. 1, the article recognition device 1 includes a housing 2, a camera 3, a distance sensor 4, an operation section 5, a display section 6, a mounting table 7, a control section 10, and the like.

The housing 2 is a frame that forms the outer shape of the article recognition device 1 . The housing 2 is formed so that the installation table 7 can be installed. In the example shown in FIG. 1, the housing 2 is formed in a U-shape.

The camera 3 is installed in the upper part of the housing 2 facing downward. The camera 3 photographs the article A on the installation base 7 . That is, the camera 3 is installed so as to photograph the article A from above. The camera 3 may be installed so as to photograph the article A from obliquely above. The position and orientation at which the camera 3 is installed are not limited to a specific configuration. The camera 3 transmits the captured image to the control section 10 .

The distance sensor 4 is installed downward on the upper part of the housing 2 . The distance sensor 4 measures the distance from a predetermined reference plane (for example, the distance from the predetermined reference plane to the distance sensor 4 or the distance from the predetermined reference plane to a plane parallel to the distance sensor 4).

The distance sensor 4 generates distance information indicating the distance from a predetermined reference plane based on the measurement result. For example, distance information indicates the coordinates of each point in a predetermined three-dimensional coordinate system. The distance sensor 4 transmits the generated distance information to the controller 10 .

For example, the distance sensor 4 includes a light source and a sensor that detects reflected light emitted from the light source. The distance sensor 4 measures the distance based on the reflected light of the light (visible light or invisible light) emitted from the light source. For example, the distance sensor 4 may perform a ToF (Time-for-Flight) method of measuring the distance to the measurement target based on the time it takes for the irradiated light to be reflected by the measurement target and reach the distance sensor 4. good.

The distance sensor 4 may calculate the distance based on the parallax of each image captured by two cameras (stereo cameras). Further, the distance sensor 4 may project a dot pattern and measure the distance from the distortion of the dot pattern.
The configuration of the distance sensor 4 is not limited to a specific configuration.

The operation unit 5 receives inputs of various operations from the operator. The operation unit 5 transmits a signal indicating the accepted operation to the processor 11 . Here, the operation unit 5 is composed of a touch panel. Note that the operation unit 5 may further include a keyboard or numeric keypad.

The display unit 6 displays various information under the control of the processor 11 . For example, the display unit 6 is composed of a liquid crystal monitor. Here, the display section 6 is formed integrally with the operation section 5 .

The installation table 7 is installed in the lower part of the housing 2 . The installation table 7 is a table on which the article A is installed. For example, the installation table 7 is formed in a rectangular shape with a predetermined size. Note that the installation table 7 may include a sensor that detects that the article A has been placed. The sensor sends a signal to processor 11 indicating that item A has been placed.

The control unit 10 controls the article recognition device 1 as a whole. The control unit 10 recognizes the article A placed on the installation table 7 based on an instruction from the operator or the like. The control unit 10 receives various inputs from the operator through the operation unit 5 . Also, the control unit 10 displays various information to the operator through the display unit 6 .

FIG. 2 is a block diagram showing a configuration example of the article recognition device 1. As shown in FIG. As shown in FIG. 2, the article recognition device 1 includes a control section 10, a camera 3, a distance sensor 4, an operation section 5, a display section 6, and the like. The control unit 10, the camera 3, the distance sensor 4, the operation unit 5, and the display unit 6 are electrically connected. The camera 3, distance sensor 4, operation unit 5 and display unit 6 are as described above.

The control unit 10 includes a processor 11, a ROM 12, a RAM 13, an NVM 14, a camera interface 15, a distance sensor interface 16, an operation unit interface 17, a display unit interface 18, and the like. The processor 11, the ROM 12, the RAM 13, the NVM 14, the camera interface 15, the distance sensor interface 16, the operation interface 17, and the display interface 18 are electrically connected. The camera interface 15 electrically connects with the camera 3 . The distance sensor interface 16 electrically connects with the distance sensor 4 . The operating section interface 17 is electrically connected to the operating section 5 . The display interface 18 is electrically connected to the display 6 .

The processor 11 controls the operation of the control unit 10 as a whole. That is, the processor 11 controls the operation of the article recognition device 1 as a whole. Processor 11 may include an internal cache, various interfaces, and the like. The processor 11 implements various processes by executing programs pre-stored in the internal cache, ROM 12 or NVM 14 .

Note that some of the various functions realized by the processor 11 executing the program may be realized by hardware circuits. In this case, processor 11 controls the functions performed by the hardware circuits.

The ROM 12 is a nonvolatile memory in which control programs, control data, and the like are stored in advance. The control program and control data stored in the ROM 12 are installed in advance according to the specifications of the control unit 10 . ROM 12 stores, for example, a program for controlling the circuit board of control unit 10 .

RAM 13 is a volatile memory. The RAM 13 temporarily stores data being processed by the processor 11 . RAM 13 stores various application programs based on instructions from processor 11 . Also, the RAM 13 may store data necessary for executing the application program, execution results of the application program, and the like.

The NVM 14 is a non-volatile memory in which data can be written and rewritten. The NVM 14 is composed of, for example, a HDD (Hard Disk Drive), SSD (Solid State Drive), EEPROM (registered trademark) (Electrically Erasable Programmable Read-Only Memory), flash memory, or the like. The NVM 14 stores control programs, applications, various data, and the like according to the operational use of the control unit 10 .

The NVM 14 stores article information. The product information is information related to products. The product information stores the product code, the dictionary information, and the shape information in association with each other.
An article code is an identifier that indicates an article. For example, the product code is composed of numerical values, character strings, symbols, or combinations thereof.

The dictionary information is information for specifying an article using local features. The dictionary information stores feature points and feature amounts of article images. For example, the dictionary information associates the positions of a plurality of feature points with feature amounts and stores them as feature point sets. The dictionary information may also store feature point sets of images of each side of the article.

The outline information indicates the outline of the article in the coordinate system of the feature points of the dictionary information. That is, the outline information indicates the relative positional relationship between the positions of the feature points and the outline. For example, the outline information indicates the coordinates of the four corners of the article.

Also, the item information may include the outer dimensions of the item, the name of the item, the price, and the like. The structure of article information is not limited to a specific structure.

The NVM 14 pre-stores article information about each article. For example, processor 11 receives article information from an external device and stores it in NVM 14 . Also, the article information may be updated as appropriate.

A camera interface 15 (image interface) is an interface for transmitting and receiving data to and from the camera. For example, the camera interface 15 transmits a signal instructing the camera 3 to shoot under the control of the processor 11 . Also, the camera interface 15 acquires a photographed image obtained by photographing from the camera 3 . For example, camera interface 15 may support USB connectivity.

A distance sensor interface 16 (distance information interface) is an interface for transmitting and receiving data to and from the distance sensor 4 . For example, the distance sensor interface 16 transmits a signal to cause the distance sensor 4 to acquire distance information under the control of the processor 11 . Also, the distance sensor interface 16 acquires distance information from the distance sensor 4 . For example, range sensor interface 16 may support USB connectivity.

The operation unit interface 17 is an interface for transmitting and receiving data to and from the operation unit 5 . For example, the operation unit interface 17 receives from the operation unit 5 a signal indicating an operation received from an operator. For example, the operation unit interface 17 may support USB connection.

The display unit interface 18 is an interface for transmitting and receiving data to and from the display unit 6 . Further, the display unit interface 18 transmits information indicating a screen to be displayed to the operator to the display unit 6 under the control of the processor 11 . For example, display interface 18 may support a USB connection.

Note that the article recognition device 1 may be provided with other configurations as necessary in addition to the configurations shown in FIGS. 1 and 2, or a specific configuration may be excluded from the article recognition device 1.

Next, functions realized by the article recognition device 1 will be described. The functions realized by the article recognition device 1 are realized by the processor 11 executing a program stored in the ROM 12, the NVM 14, or the like.

First, the processor 11 has a function of acquiring an image (captured image) of the installation table 7 on which the article is placed. Here, the processor 11 acquires a photographed image of the article placed on the installation table 7 .

For example, the processor 11 detects that an article has been placed on the installation table 7 by the user. For example, processor 11 detects that an article has been placed on installation table 7 based on a signal from installation table 7 . Note that the processor 11 may detect that an article has been placed on the installation table 7 based on the image from the camera 3 . Further, the processor 11 may receive an operation indicating that an article has been placed on the installation table 7 from the user.

When the processor 11 detects that the article has been placed, it takes an image including the article. For example, processor 11 sends a signal to camera 3 to take an image. A processor 11 acquires a captured image from the camera 3 . Note that the processor 11 may set shooting parameters for the camera 3 in order to shoot an image.
Note that the processor 11 may acquire the captured image from an external device.

FIG. 3 shows an example of a captured image. In the example shown in FIG. 3, the photographed image shows the installation table 7, the external light 50, the article A, the article B, the article C, and the like.

The outside light 50 is light that illuminates the installation table 7 . For example, the external light 50 is sunlight, illumination light, or the like.

Articles A, B, and C are objects to be recognized. Articles A, B, and C are placed on the installation table 7 with a specific surface facing up.

It should be noted that the photographed image may show four or more articles. Also, the captured image may show one or two items. The number of articles shown in the photographed image is not limited to a specific number.

The processor 11 also has a function of acquiring distance information from the distance sensor 4 .
The processor 11 acquires distance information from the distance sensor 4 when detecting that an article has been placed on the installation table 7 by the user. For example, processor 11 sends a signal to distance sensor 4 to perform a distance measurement. Processor 11 acquires distance information from distance sensor 4 .

The processor 11 may acquire the distance information after acquiring the captured image. Also, the processor 11 may acquire the distance information at the same time as the captured image. Also, the processor 11 may acquire the distance information before acquiring the captured image.

The processor 11 also has a function of extracting feature point information (image information) for recognizing an article from the captured image.
That is, the processor 11 extracts feature points from the captured image and calculates the feature amount of each feature point. The feature point information includes information such as feature points and feature amounts.

For example, a feature point is a point uniquely defined within a local region, such as a corner point of an image or a extreme point (maximum/minimum point) of a secondary differential function of image density. A feature point is indicated by coordinates (x, y) representing a position.

A feature amount is a value calculated from a feature point or an image around the feature point. For example, the feature amount is calculated based on the density pattern in the vicinity of the feature point.

The structure of feature point information is not limited to a specific structure.

The processor 11 stores the extracted feature point information in a feature point list.

FIG. 4 shows an example of the feature point list extracted from the captured image by the processor 11 . In FIG. 4, circles 101 indicate feature points. Also, the size of the circle 101 indicates the feature amount. As FIG. 4 shows, processor 11 extracts a plurality of circles 101 . Processor 11 extracts a plurality of circles 101 on items A-C, respectively. Also, the processor 11 extracts a plurality of circles 101 on the outside light 50 .

The processor 11 also has a function of deleting the feature point information extracted on the installation table 7 from the feature point list based on the distance information.

Processor 11 identifies the height of each feature point based on the distance information. After specifying the height of each feature point, the processor 11 deletes the feature point information having the same height as the installation table 7 from the feature point list. For example, the processor 11 deletes feature point information whose height from the installation table 7 is equal to or less than a predetermined threshold from the feature point list.

FIG. 5 shows an example of a feature point list in which feature point information having the same height of the installation table 7 is deleted. External light 50 is reflected on the installation base 7 . Therefore, the feature point information extracted on the outside light 50 has the same height as the installation table 7 . Therefore, the processor 11 deletes the feature point information on the external light 50 from the feature point list, as shown in FIG.

The processor 11 also has a function of recognizing an article based on the feature point list. That is, the processor 11 recognizes the article from feature point information other than the feature point information extracted on the installation table 7 .

Processor 11 acquires one article information from NVM 14 . After obtaining the product information, the processor 11 calculates the similarity rate R of the feature point set based on the feature point set and the feature point list of the product information.

The processor 11 calculates a similarity rate R for each article information stored by the NVM 14 . After calculating the similarity rate R of each article information, the processor 11 specifies the highest similarity rate Rmax from among the similarity rates R. After identifying the similarity rate Rmax, the processor 11 determines whether the similarity rate Rmax exceeds the threshold value Rthr. When determining that the similarity rate Rmax exceeds the threshold value Rthr, the processor 11 recognizes the article corresponding to the article information of the similarity rate Rmax. For example, processor 11 obtains the item code of the item.

Note that the processor 11 may recognize the article by reading the barcode from the captured image. For example, the processor 11 extracts a barcode area in which the barcode appears by predetermined image processing. Having identified the barcode area, the processor 11 decodes the barcode within the barcode area. That is, the processor 11 reads an article code specifying an article from the bar code. The processor 11 recognizes the article whose article code is read.

The processor 11 also has a function of specifying an article area in which an article recognized from the photographed image is captured.
The processor 11 acquires outline information of the recognized article. The processor 11 identifies the article area based on the positions of the feature points and the outline information of the feature point information used for recognition in the captured image. For example, the processor 11 identifies an area in which the upper surface of the article is captured in the captured image from the positions of the feature points in the feature point information used for recognition in the captured image and the outer shape information. The processor 11 identifies the identified area as an article area.

Note that when an article is recognized by reading a barcode, the processor 11 acquires dictionary information of article information of the recognized article. The processor 11 matches feature point information in the feature point list with dictionary information. For example, the processor 11 extracts the feature point closest to the feature point set of the dictionary information from the feature point list. The processor 11 may extract feature points corresponding to the feature point set from feature points within a predetermined distance from the barcode area or within a predetermined area set based on the position of the barcode area.

After extracting the feature points closest to the feature point set of the dictionary information from the feature point list, the processor 11 identifies the article area based on the position and outline information of the extracted feature points.

The processor 11 also has a function of deleting feature point information within the product area from the feature point list.
The processor 11 determines whether the feature point of each feature point information in the feature point list is within the article area. The processor 11 deletes the feature point information of the feature points determined to be within the article area from the feature point list.

The processor 11 repeats the operation from recognizing the article to deleting the feature point information to recognize each article from the photographed image.

In the example shown in FIG. 5, for example, processor 11 identifies article A based on the feature point list. After identifying item A, processor 11 identifies an item region of item A. FIG. After specifying the article area of the article A, the processor 11 deletes the feature point information within the article area of the article A from the feature point list.

FIG. 6 shows an example of a feature point list in which the feature point information within the article area of article A is deleted. As FIG. 6 shows, the circle 101 within the item area of item A has been deleted.

After deleting the feature point information within the article region of the article A from the feature point list, the processor 11 identifies the article B based on the feature point list. After identifying item B, processor 11 identifies an item region of item B. FIG. After specifying the article region of the article B, the processor 11 deletes the feature point information within the article region of the article B from the feature point list.

FIG. 7 shows an example of a feature point list in which the feature point information within the article region of article B is deleted. As shown in FIG. 7, the circles 101 within the article regions of article A and article B have been deleted.

Similarly, processor 11 recognizes item C.

The processor 11 also has a function of outputting a warning based on the number of pieces of feature point information in the feature point list when the article cannot be recognized.

For example, when determining that the similarity rate Rmax is equal to or less than the threshold value Rthr in the recognition process, the processor 11 determines that the article cannot be recognized (recognition has failed). When determining that the article cannot be recognized, the processor 11 counts the number of pieces of feature point information in the feature point list. After counting the number of pieces of feature point information in the feature point list, the processor 11 determines whether the counted number is equal to or less than a predetermined threshold.

When determining that the counted number is equal to or less than the predetermined threshold value, the processor 11 determines that recognition of the article has been completed.

When it is determined that the counted number exceeds the predetermined threshold, the processor 11 determines that there are unrecognized articles and outputs a warning indicating that there are unrecognized articles. For example, processor 11 uses display 6 to display a warning. Processor 11 may also send an alert to an external device. The method by which processor 11 outputs a warning is not limited to a specific method.

Next, an operation example of the article recognition device 1 will be described. FIG. 8 is a flowchart for explaining an operation example of the article recognition device 1. FIG.

First, the processor 11 of the article recognition device 1 determines whether an article has been placed on the installation table 7 (ACT 11). If it is determined that no article is placed on the installation table 7 (ACT11, NO), the processor 11 returns to ACT11.

When determining that an article has been placed on the installation table 7 (ACT 11, YES), the processor 11 obtains a photographed image using the camera 3 (ACT 12). After acquiring the captured image, the processor 11 acquires distance information using the distance sensor 4 (ACT 13).

After obtaining the distance information, the processor 11 extracts feature point information from the captured image and stores it in the feature point list (ACT 14). When the feature point information is extracted from the captured image and stored in the feature point list, the processor 11 deletes the feature point information extracted on the installation table 7 from the feature point list (ACT 15).

After deleting the feature point information, the processor 11 recognizes the article based on the feature point information in the feature point list (ACT 16). When the article is successfully recognized (ACT17, YES), the processor 11 identifies the article area of the recognized article in the captured image (ACT18). After identifying the article area, the processor 11 deletes the feature point information within the article area from the feature point list (ACT 19).

After deleting the feature point information within the article area from the feature point list, the processor 11 returns to ACT16.

When the article recognition fails, the processor 11 determines whether or not the number of pieces of feature point information in the feature point list is equal to or less than a predetermined threshold (ACT20). When determining that the number of pieces of feature point information in the feature point list is equal to or less than the predetermined threshold (ACT20, YES), the processor 11 displays on the display section 6 that the recognition processing is completed (ACT21).

When determining that the number of pieces of feature point information in the feature point list exceeds a predetermined threshold (ACT20, NO), the processor 11 outputs a warning indicating that there is an article for which recognition has failed (ACT22).

When the completion of the recognition process is displayed on the display unit 6 (ACT 21), or when a warning is output indicating that there is an article for which recognition has failed (ACT 22), the processor 11 ends the operation.

Note that the processor 11 may pay for the recognized goods. For example, the processor 11 acquires credit card information from the user and settles the goods based on the credit card information. Also, the processor 11 may receive cash from the user to settle the goods.

The processor 11 may also transmit the article code of the recognized article to the external device. The processor 11 may also display information indicating the recognized article on the display unit 6 .

The article recognition apparatus configured as described above deletes the feature point information extracted on the installation table on which the article is placed in the photographed image. The article recognition device recognizes the article based on the remaining feature point information. As a result, the article recognition device can eliminate feature point information generated by factors other than the article, such as external light or the pattern of the installation table. Therefore, the article recognition device can appropriately recognize the article.

Also, the article recognition device deletes feature point information within the article area of the recognized article. As a result, the article recognition device can delete feature point information generated by an already recognized article. Therefore, the article recognition device can recognize the article based on the feature point information generated by the unrecognized article.

Also, the article recognition device outputs a warning when the number of pieces of feature point information remaining after article recognition exceeds a predetermined threshold. As a result, the article recognition device can warn that there is an article for which recognition has failed.
(Second embodiment)
Next, a second embodiment will be described.
The article recognition apparatus according to the second embodiment differs from that according to the first embodiment in that an area wider than the upper surface of the recognized article is specified as an article area. Therefore, other points are denoted by the same reference numerals, and detailed description thereof is omitted.

The configuration of the article recognition device 1 according to the second embodiment is the same as that according to the first embodiment, so the description is omitted.

Next, functions realized by the article recognition device 1 will be described. The functions realized by the article recognition device 1 are realized by the processor 11 executing a program stored in the ROM 12, the NVM 14, or the like.

The processor 11 has a function of identifying an area wider than the upper surface of the recognized article as an article area.
The processor 11 acquires outline information of the recognized article. The processor 11 specifies an area in which the upper surface of the article is captured based on the positions of the feature points and the outline information of the feature point information used for recognition in the captured image. After identifying the area where the upper surface of the article is captured, the processor 11 identifies an area larger than the area as the article area.

For example, the processor 11 identifies an area in which the upper surface of the article is captured and an area in which the side surface of the article is captured as the article area. For example, the processor 11 identifies the area where the side of the article is captured based on camera characteristics, distance to the article, position of the article and/or height of the article.

Note that the processor 11 may specify, as the article area, an area obtained by enlarging the area in which the upper surface of the article is shown by a predetermined magnification. In addition, the processor 11 may specify, as the article area, an area in which the upper surface of the article is captured and which is enlarged by a predetermined number of dots. The method by which the processor 11 identifies the article area is not limited to any particular method.

FIG. 9 shows an example of a feature point list extracted from the captured image by the processor 11 . Here, it is assumed that the photographed images show the article D, the article E, and the article F. As shown in FIG. In FIG. 9, circles 102 indicate feature points. The size of the circle 102 indicates the feature amount. As FIG. 9 shows, processor 11 extracts a plurality of circles 102 .

The processor 11 extracts a plurality of circles 102 on the upper surfaces of the article D, the article E, and the article F, respectively. The processor 11 also extracts a plurality of circles 102 on the sides of the article E and the article F, respectively.

FIG. 10 shows an example of an article area identified by processor 11 . Here, it is assumed that the processor 11 has recognized the article F. As FIG. 10 shows, processor 11 identifies an article region 201 that includes the top and sides of article F. FIG. Also, the processor 11 deletes the feature point information within the product area 201 from the feature point list.

An example of the operation of the article recognition device 1 is the same as that according to the first embodiment, so the explanation is omitted.

The article recognition apparatus configured as described above extracts an area larger than the upper surface of the article from the photographed image as an article area. As a result, the article recognition device can extract, as an article area, an area including the upper surface used for article recognition and the side surface of the article. Therefore, the article recognition device can delete the feature point information extracted from the side of the recognized article. Therefore, the article recognition device can recognize the article more appropriately in subsequent recognition processing.

While several embodiments of the invention have been described, these embodiments have been presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.
The invention described in the scope of claims at the time of filing of the present application will be additionally described below.
[C1]
an image interface for acquiring an image of the article placed on the installation table;
a distance information interface that acquires distance information indicating distances from the installation table and the article;
extracting image information for recognizing the article from the image, generating a list containing the image information;
deleting image information having the same height as the height of the installation table from the list based on the distance information;
recognizing an item based on the image information of the list;
a processor;
An article recognition device comprising:
[C2]
The image information includes feature points and feature amounts,
The article recognition device according to C1.
[C3]
The processor
deleting from the list image information within the article area of the recognized article;
recognizing an article based on the list from which image information within the article area of the recognized article is deleted;
The article recognition device according to C1 or 2 above.
[C4]
The article area includes an upper surface area of the article and a side area of the article,
The article recognition device according to C3.
[C5]
an image interface for acquiring a photographed image of an article;
extracting image information for recognizing the article from the image, generating a list containing the image information;
recognizing an article based on the image information of the list;
deleting from the list image information within the article area of the recognized article;
recognizing an article based on the list from which image information within the article area of the recognized article is deleted;
outputting a warning if the number of image information items in the list exceeds a predetermined threshold when the item cannot be recognized from the list;
a processor;
An article recognition device comprising:

DESCRIPTION OF SYMBOLS 1... Article recognition apparatus, 2... Housing, 3... Camera, 4... Distance sensor, 5... Operation part, 6... Display part, 7... Installation stand, 10... Control part, 11... Processor, 12... ROM, 13... RAM, 14... NVM, 15... Camera interface, 16... Distance sensor interface, 17... Operation unit interface, 18... Display unit interface, 50... Outside light, 101... Yen, 102... Yen, 201... Article area.

Claims (4)

an image interface for acquiring an image of the article placed on the installation table;
a distance information interface that acquires distance information indicating distances from the installation table and the article;
extracting image information for recognizing the article from the image, generating a list containing the image information;
deleting image information at the same distance from the installation table from the list based on the distance information;
recognizing an item based on the image information of the list;
a processor;
An article recognition device comprising: The image information includes feature points and feature amounts,
The article recognition device according to claim 1. The processor
deleting from the list image information within the article area of the recognized article;
recognizing an article based on the list from which image information within the article area of the recognized article is deleted;
3. The article recognition device according to claim 1 or 2. The article area includes an upper surface area of the article and a side area of the article,
4. The article recognition device according to claim 3.

Images