WO2005084227A2 - Systemes et procedes pour le controle automatique de marchandises - Google Patents

Systemes et procedes pour le controle automatique de marchandises Download PDF

Info

Publication number
WO2005084227A2
WO2005084227A2 PCT/US2005/006079 US2005006079W WO2005084227A2 WO 2005084227 A2 WO2005084227 A2 WO 2005084227A2 US 2005006079 W US2005006079 W US 2005006079W WO 2005084227 A2 WO2005084227 A2 WO 2005084227A2
Authority
WO
WIPO (PCT)
Prior art keywords
subsystem
checkout
visual
match
data
Prior art date
Application number
PCT/US2005/006079
Other languages
English (en)
Other versions
WO2005084227A3 (fr
Inventor
Jim Ostrowski
Mario Munich
John Wiseman
Original Assignee
Evolution Robotics, Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US11/023,004 external-priority patent/US7100824B2/en
Application filed by Evolution Robotics, Inc. filed Critical Evolution Robotics, Inc.
Priority to US10/554,516 priority Critical patent/US7337960B2/en
Publication of WO2005084227A2 publication Critical patent/WO2005084227A2/fr
Publication of WO2005084227A3 publication Critical patent/WO2005084227A3/fr
Priority to US12/074,263 priority patent/US8430311B2/en

Links

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07G—REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
    • G07G1/00—Cash registers
    • G07G1/0036—Checkout procedures
    • G07G1/0045—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader
    • G07G1/0054—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader with control of supplementary check-parameters, e.g. weight or number of articles
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47F—SPECIAL FURNITURE, FITTINGS, OR ACCESSORIES FOR SHOPS, STOREHOUSES, BARS, RESTAURANTS OR THE LIKE; PAYING COUNTERS
    • A47F9/00—Shop, bar, bank or like counters
    • A47F9/02—Paying counters
    • A47F9/04—Check-out counters, e.g. for self-service stores
    • A47F9/046—Arrangement of recording means in or on check-out counters
    • A47F9/047—Arrangement of recording means in or on check-out counters for recording self-service articles without cashier or assistant
    • A47F9/048—Arrangement of recording means in or on check-out counters for recording self-service articles without cashier or assistant automatically

Definitions

  • the present invention generally relates to object recognition and, more particularly, to systems and method for automatically detecting objects based on pattern recognition and weight measurement.
  • the customer may scan the UPC of each item and put the item on a weighing scale. Then, the self-checkout system looks up a database to get the weight data of the item. If the weight data of the item matches the reading of the weighing scale, the item is added to a checkout list.
  • these existing self-checkout systems rely on customers to process the merchandise. Typically, the customers are not as experienced as the cashiers in processing the merchandise, and as a consequence, exiting self-checkout systems may be slower in processing the merchandise than the conventional checkout systems. This can result in lost revenue to the store negating the savings in cashier's labor cost if revenue is dependent upon the checkout speed.
  • a self-checkout system can yield high throughput and reduce labor and turnover costs if the system can detect and recognize items in the absence of a user needing to physically scan UPCs and/or weigh the items individually.
  • a self-checkout system can yield high throughput and reduce labor and turnover costs if the system can detect and recognize items in the absence of a user needing to physically scan UPCs and/or weigh the items individually.
  • a system for self-checking out an object includes: a scale subsystem for measuring a weight of the object; at least one visual sensor for taking at least one image of the object; and a check out subsystem coupled to the at least one visual sensor and the scale subsystem and configured to recognize the object by analyzing the at least one image and the weight.
  • a system for checking out an object includes: a check out lane; a conveyor subsystem adjacent the lane; at least one visual sensor for taking at least one image of the object on the conveyor subsystem; a scale subsystem for measuring a weight of the object; and a check out subsystem configured to receive the at least one image from the at least one visual sensor and the weight from the scale subsystem and analyze the at least one image and the weight to recognize the object.
  • a method of self-checking out an object includes steps of: placing the object on a conveyor subsystem; moving the object inside a controlled lighted area via the conveyor subsystem; detecting the object; recognizing the object; measuring a weight of the object in the absence of human intervention; determining if the weight matches the object; and in case of match, adding the object to a checkout list.
  • a method of checking out an object includes steps of: placing a first separator ahead of the object; placing the object on a conveyor subsystem; placing a second separator behind the object on the conveyor subsystem; starting a transaction upon recognizing the first separator; detecting the object; turning on a lighting subsystem; capturing one or more images of the object; recognizing the object based on the one or more images; recognizing a UPC of the object; measuring the weight of the object; determining if the weight matches the object if UPC is recognized; in case of match, adding the object to a checkout list; in case of no match, sending a notification of an exception, stopping the conveyor subsystem, and resolving the exception; and terminating the transaction upon recognizing the second separator.
  • the notification of an exception can be transferred through an Ethernet connection linking a plurality of subsystems or through at least one wireless device linking a plurality of subsystems.
  • a method of automating a self- checkout transaction includes steps of: moving an object on a conveyor subsystem; receiving visual image data of the object from a visual subsystem; analyzing received visual image data to extract one or more visual features; comparing the one or more visual features with feature data stored in an object database to find a set of matches; sending a recognition alert; measuring a weight of the object using a scale subsystem located under the conveyor subsystem; determining if the weight matches the object; if the determination is positive, adding the object to a checkout list; and if the determination is negative, sending a notification of an exception, stopping the conveyor subsystem, and resolving the exception.
  • the notification of an exception can be transferred between the subsystems through an Ethernet connection linking a plurality of subsystems or through at least one wireless device linking the subsystems.
  • the visual subsystem captures visual image data for color and shape recognition, tracking of object and detection of the size of the objects.
  • a system for self-checking out an object includes: a conveyor subsystem configured to move the object; a housing that encloses a portion of the conveyor subsystem; at least one visual sensor configured to capture at least one image of the object and mounted on the housing; a lighting subsystem that illuminates an area within the housing and is mounted on the housing; a motion trigger subsystem for detecting the object and triggering the lighting subsystem and the at least one visual sensor; and a check out subsystem coupled to the at least one visual sensor and configured to recognize the object by analyzing the at least one image.
  • the visual subsystem captures visual image data for color and shape recognition, tracking of object and detection of the size of the objects.
  • FIG. 1 illustrates a system for merchandise automatic checkout in accordance with one embodiment of the present invention
  • FIG. 2A illustrates one embodiment of a recognition system included in the check out system shown in FIG. 1 ;
  • FIG. 2B illustrates another embodiment of a recognition system included in the check out system shown in FIG. 1 ;
  • FIG. 2C illustrates yet another embodiment of a recognition system included in the check out system in shown FIG. 1;
  • FIG. 3 illustrates one example of a data structure for a relational database that can be used with the system in FIG. 1 ;
  • FIG. 4 is a flowchart illustrating the steps that may be carried out by the system in FIG. 1 ;
  • FIG. 5 is a flowchart illustrating a process to be carried out at the step of automatic processing in FIG. 4;
  • FIG. 6 is a flowchart that illustrates a process to be carried out by the recognition system in FIG. 2 in accordance with one embodiment of the present invention.
  • FIG. 7 is a flowchart that illustrates a process for training the system in
  • FIG. 1 in accordance with one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION
  • the present invention provides systems and methods through which one or more visual sensors, such as one or more cameras, operatively coupled to a computer system can view, recognize and identify items moving on a conveyor subsystem for automatic check out in the absence of human intervention.
  • automated refers to the "absence of a user's or human's intervention or efforts, particularly in connection with not having to put an item on a scale or to scan the UPC of an item as in the case of conventional checkout systems.
  • the items may be checked out for purchase in a store, and as a further example, the items may be located on a conveyor belt adjacent a checkout lane of a store environment.
  • One or more visual sensors can be placed in a housing that covers a portion of the conveyor belt such that merchandise images may be obtained as the merchandise moves through the housing. Using the images, the merchandise is automatically recognized.
  • FIG. 1 illustrates an embodiment of a self-check out system 100 that may include a checkout lane 102 of a store environment (not to scale) and a checkout counter 104.
  • a point-of-sale (POS) (or, equivalents checkout subsystem) 106 may rest on the checkout counter 104.
  • One or more input devices may be coupled to the POS subsystem 106.
  • Exemplary input devices may include a barcode scanner, a scale, a keyboard, keypad, touch screen, card reader, and the like.
  • the POS subsystem 106 may correspond to a checkout terminal used by a checker or cashier.
  • the POS subsystem 106 may correspond to a self-service checkout terminal.
  • the checkout system 100 may further include a merchandise conveyor subsystem 110 that may be part of a conveyor belt machine well known in the supermarket industry.
  • the conveyor subsystem 110 may be used to place merchandise 112 on it by a shopper. So placed, the conveyor subsystem 110 may then move the merchandise 112 in one of the following manners. In one embodiment of the present invention, the conveyor belt 110 may move continuously. In another embodiment, the conveyor belt 110 may start moving when a conventional motion detector, such as IR detector, detects a customer approaching the checkout lane 102 and sends a signal to the conveyor belt 110. In still another embodiment, a scale subsystem 122 may start the conveyor belt 110 upon detection of any weight on the conveyor belt 110.
  • a conventional motion detector such as IR detector
  • the location of the scale subsystem 122 can be any where along the conveyor belt 110 including but not limited to the beginning of the conveyor belt 110.
  • the scale subsystem 122 can be located at the beginning of the conveyor belt 110 to provide an indication that there is merchandise 112 on the conveyor belt 110 waiting to be checked out.
  • the scale subsystem 122 detects merchandise 112 on the conveyor belt 110, it will send a signal to start moving the conveyor belt 110 and to begin the automatic checkout process.
  • a housing 114 may be placed over the conveyor belt 110 and cover a portion of the conveyor belt 110.
  • the housing 114 functions as a structure where a motion trigger subsystem 116, one or more visual cameras 120, and a lighting subsystem 118 are mounted, it may have any dimension or shape that accommodates the flow of items therethrough.
  • the housing may also include a UPC reader subsystem 113 configured to recognize the UPC of the merchandise 112 contained in the image.
  • the UPC reader subsystem 113 may be a conventional UPC scanner.
  • the UPC recognition may be done with a visual sensor.
  • a motion trigger subsystem 116 may be employed to detect the merchandise 112 moving on the conveyor subsystem 110 and past the motion trigger subsystem 116.
  • the motion trigger subsystem 116 may include sensor(s), such as conventional IR detectors.
  • the motion trigger subsystem 116 may be coupled to a lighting subsystem 118.
  • the motion trigger subsystem 116 may trigger the lighting subsystem 118 to light the interior of the housing 114 to provide optimum light illumination when the visual sensors 120 capture visual images.
  • the motion trigger subsystem 116 may be also coupled to the visual sensors 120 and trigger the visual sensors 120 to obtain images of the merchandise 112.
  • Triggering of the visual sensors 120 and lighting subsystem 118 may be synchronized such that the lighting subsystem 118 can provide optimum illumination.
  • the motion trigger subsystem 116 can be turned on automatically based on a signal sent by the visual sensor 120 when it detects a motion of merchandise 112 passing through. The automatic checkout process can be initiated when the motion trigger subsystem 116 is turned on.
  • only two visual sensors 120 are shown in FIG. 1. However, it should be apparent to those of ordinary skill that the present invention may be practiced with any number of visual sensors. [030] As will be described in greater detail later in connection with FIG.
  • the visual sensors 120 may be used to recognize the presence and identity of the merchandise 112 and provide an indication or instruction to the POS subsystem 106.
  • the visual sensors 120 may also determine the size of the merchandise 112 by analyzing the visual images of the merchandise 112, as described in connection with FIGS. 2, 3, 6 and 7.
  • the visual sensors 120 may track which merchandise has been recognized and which has not.
  • Each of the visual sensors 120 may be a digital camera with a CCD imager, a CMOS imager, an infrared imager, and the like.
  • the visual sensors 120 may include normal lenses or special lenses, such as wide-angle lenses, fish-eye lenses, omni-directional lenses, and the like. Further, the lens may include reflective surfaces, such as planar, parabolic, or conical mirrors, which may be used to provide a relatively large field of view or multiple viewpoints.
  • the checkout system 100 may further include a scale subsystem 122, which can be employed to weigh merchandise 112, for example, when the merchandise is fruit or vegetables.
  • the structural incorporation of the scale subsystem 122 with the conveyor belt 110 is well known in the art and not detailed for simplicity.
  • the system 100 may determine the particular fruit or vegetable based on images of its color, texture, and/or shape. So determined, the system 100 may then charge a price of the particular fruit or vegetable based on its weight and price/pound.
  • the scale subsystem 122 may also be used to check if the merchandise 112 is correctly recognized based on the analysis of images captured by the visual sensor 120.
  • the system 100 may use the visual images captured by the visual sensors 120 to recognize the merchandise 112. Then, the system 100 may look up its object database 302 (shown in FIG. 3) to obtain the weight data and/or Universal Product Code (UPC) information of the recognized merchandise 112. By comparing the reading of the scale subsystem 122 for the recognized merchandise 112 with the weight data and/or UPC information, the system 100 may determine if the merchandise 112 has been correctly recognized. [033] Illustratively, the reading of the scale subsystem 122 may not match the weight data and/or UPC information if one or more items are stacked on top of each other on the conveyor subsystem 110.
  • object database 302 shown in FIG. 3
  • UPC Universal Product Code
  • the visual sensors 120 may try to recognize the stacked items as a single item and may result a false recognition. In case of mismatch between the reading and the weight data and/or UPC information, the merchandise 112 may raise an exception as described later.
  • one or more special markings such as ID number or UPC code, may be introduced onto the merchandise packaging.
  • the special markings may be printed in ink that is not visible under normal lighting but visible under special lighting, such as UV (or IR) lighting, wherein the lighting subsystem 118 may include a light source for illuminating the special markings.
  • the ink may be an invisible UV fluorescent ink used for conventional security and authentication.
  • the special markings may be invisible to the naked eye, they can be printed in various sizes and, if needed, cover the entire surface of the package without detracting from the advertisement/eye-appeal of the package design.
  • the merchandise 112 may be illuminated by the lighting subsystem 118 to reveal the imprinted special markings.
  • the visual sensors 120 may capture visual images including the special markings and analyze the visual images to identify the merchandise 112, as described in connection with FIGS. 2, 3, 6 and 7.
  • a shopping cart 124 may occupy the check out lane 102 adjacent the conveyor subsystem 110.
  • the shopping cart 124 may include a basket 126 and a lower shelf 128.
  • One or more items 128 may be carried on the basket 126 and lower shelf 128 inadvertently or intentionally to defraud the store.
  • additional visual sensors 132a- b may be located adjacent the check out lane 102 such that the item 130 may be at least partially within the field of view of the visual sensor 132a-b. More detail on the bottom-of-the-basket prevention is referred to U.S. Patent application entitled “Systems and Methods for Merchandise Checkout" filed on December 27, 2O04, serial no. 11/023,004, which is hereby incorporated herein by reference in its entirety.
  • the system 100 may start a new transaction upon recognition of a first separator 140.
  • the first separator 140 may be, for example, a plastic bar that the system 10O is trained to recognize based on ViPR (visual pattern recognition). Such recognition of a separator bar 140 may be based on a variety of characteristics including but not limited to features, colors, sizes and shapes.
  • ViPR visual pattern recognition
  • the customer may place a second separator 142, wherein the system 100 is also trained to recognize the second separator 142.
  • FIG. 2A illustrates an embodiment 200 of a recognition system included in the automatic check out system 100 in FIG. 1.
  • the system 200 may be implemented in a variety of ways, such as by dedicated hardware, by software executed by a microprocessor, by firmware and/or computer readable medium executed by a microprocessor or by a combination of both dedicated hardware and software. Also, for simplicity, only one visual sensor 202 and one checkout subsystem 206 are shown in FIG. 2A. However, it should be apparent to those of ordinary skill that any number of visual sensors and checkout subsystems may be used without deviating from the sprit and scope of the present invention. [038] The visual sensor 202 may capture images of the items 112 and send visual data 204 to the computer 206 that may process the visual data 204. In one embodiment, the visual data 204 may include the visual images of the one or more items 112.
  • the visual sensor 202 may communicate with the computer 206 via an appropriate interface, such as a direct connection or a networked connection.
  • This interface may be hard wired or wireless. Examples of interface standards that may be used include, but are not limited to, Ethernet, IEEE 802.11 , Bluetooth, Universal Serial Bus, FireWire, S-Video, NTSC composite, frame grabber, and the like.
  • the computer 206 may analyze the visual data 204 provided by the visual sensor 202 and identify visual features of the visual data 204.
  • the features may be identified using an object recognition process that can identify visual features of an image.
  • the visual features may correspond to scale-invariant features.
  • SIFT scale- invariant feature transformation
  • the computer 206 may be a PC, a server computer, or the like, and may be equipped with a network communication device such as a network interface card, a modem, infra-red (IR) port, or other network connection device suitable for connecting to a network.
  • the computer 206 may be connected to a network such as a local area network or a wide area network, such that information, including information about merchandise sold by the store, may be accessed from the computer 206.
  • the information may be stored on a central computer system, such as a network fileserver, a mainframe, a secure Internet site, and the like.
  • the computer 206 may execute an appropriate operating system.
  • the appropriate operating system may include, but is not limited to, operating systems such as Linux, Unix, VxWorks®, QNX® Neutrino®, Microsoft® Windows® 3.1 , Microsoft® Windows® 95, Microsoft® Windows® 98, Microsoft® Windows® NT, Microsoft® Windows® 2000, Microsoft® Windows® Me, Microsoft® Windows® XP, Apple® MacOS®, IBM OS/2®, Microsoft® Windows® CE, or Palm OS®.
  • the appropriate operating system may advantageously include a communications protocol implementation that handles incoming and outgoing message traffic passed over the network.
  • the computer 206 may be connected to a server 218 that may provide the database information 214 stored in an Object Database 222 and/or a Log Data Storage 224.
  • the server 218 may send a query to the computer 206.
  • a query is an interrogating process initiated by the Supervisor Application 220 residing in the server 218 to acquire Log Data from the computer 206 regarding the status of the computer 206, transactional information, cashier identification, time stamp of a transaction and the like.
  • the computer 206 after receiving a query 214 from the server 218, may retrieve information from the log data 216 to pass on relevant information back to the server 218, thereby answering the interrogation.
  • a Supervisor Application 220 in the server 218 may control the flow of information therethrough and manage the Object Database 222 and Log Data Storage 224.
  • the server 218 may store all or at least part of the analyzed visual data, such as features descriptors and coordinates associated with the identified features, along with other relevant information in the Object Database 222.
  • the Object Database 222 will be discussed in greater detail later in connection with FIG. 3. [043] It will be understood that during system training, it may be convenient to arrange the physical connection between a visual sensor and a checkout subsystem in the proximity where they will be located in an operation mode though the mode of data connection may vary.
  • training images may be captured in a photography studio or on a "workbench,” which can result in higher-quality training images and less physical strain on a human system trainer. Further, it will be understood that during system training, the computer 206 may not need to output match data 208.
  • the features of the training images may be captured and stored in the Object Database 222.
  • the computer 206 may compare the visual features with the database information 214 that may include a plurality of known objects stored in the Object Database 222. If the computer 206 finds a match in the database information 214, it may return match data 208 to the checkout subsystem 206. Examples of appropriate match data will be discussed in greater detail later in connection with FIG. 3.
  • the server 218 may provide the computer 206 with an updated, or synchronized copy of the Object Database 222 at regular intervals, such as once per hour or once per day, or when an update is requested by the computer 206 or triggered by a human user.
  • the computer 206 may send a signal to the checkout subsystem 212 that may subsequently display a query on a monitor and request the operator of the checkout subsystem 212 to take an appropriate action, such as identifying the item 112 associated with the query and providing the information of the item 112 using an input device connected to the checkout subsystem 212.
  • a signal can be sent through a wireless device to connect to an operator who may be alerted through a second wireless display device or a monitor that is capable of receiving the signal when the computer 206 cannot find a match.
  • the checkout subsystem 212 may provide transaction data 210 to the computer 206. Subsequently, the computer 206 may send log data 216 to the server 218 that may store the data in the Log Data Storage 224, wherein the log data 216 may include data for one or more transactions. In one embodiment, the computer 206 may store the transaction data 210 locally and provide the server 218 with the stored transaction data for storage in the Log Data Storage 224 at regular intervals, such as once per hour or once per day.
  • the server 218, Object Database 222 and Log Data Storage 224 may be connected to a network such as a local area network or a wide area network, such that information, including information from the Object Database 222 and the Log Data Storage 224, can be accessed remotely. Furthermore, the server 208 may execute an appropriate operating system.
  • the appropriate operating system may include but is not limited to operating systems such as Linux, Unix, Microsoft® Windows® 3.1 , Microsoft® Windows® 95, Microsoft® Windows® 98, Microsoft® Windows® NT, Microsoft® Windows® 2000, Microsoft® Windows® Me, Microsoft® Windows® XP, Apple® MacOS®, or IBM OS/2®.
  • the appropriate operating system may advantageously include a communications protocol implementation that handles incoming and outgoing message traffic passed over the network.
  • the checkout subsystem 212 may take one or more of a wide variety of actions.
  • the checkout subsystem 212 may provide a visual and/or audible indication that a match has been found for the operator of the checkout subsystem 212.
  • the indication may include the name of the object.
  • the checkout subsystem 212 may automatically add the item or object associated with the identified match to a list or table of items for purchase without any action required from the operator of the checkout subsystem 212. It will be understood that the list or table may be maintained in the checkout system 212 memory.
  • a receipt of the items and their corresponding prices may be generated at least partly from the list or table.
  • the checkout system 212 may also store an electronic log of the item, with a designation that it was sent by the computer 206.
  • the scale subsystem 203 may be coupled to the computer 206 and provide a reading to the computer 206.
  • the computer 206 may look up the object database 222 to get weight information of the item. Then, the reading of the scale subsystem 203 may be compared with the weight information to check if the item is recognized correctly.
  • system 200 can include an optional UPC scanner subsystem 207.
  • UPC scanner subsystem 207 can be used as a bar code reader of merchandise to corroborate the data capture by other sensors in system 200 or independently used for checkout as in a conventional check out system.
  • FIG. 2B illustrates another embodiment 230 of a recognition system included in the self-checkout system in FIG. 1. It will be understood that the system 230 may be similar to the system 200 in FIG. 2A with some differences. Firstly, the system 230 may optionally include a feature extractor 238 for analyzing visual data 236 sent by a visual sensor 234 to extract features. The feature extractor 238 may be dedicated hardware. The feature extractor 238 may also send visual display data 240 to a checkout subsystem 242 that may include a display monitor for displaying the visual display data 240.
  • the computer 206 may analyze the visual data 204 to extract features, recognize the items associated with the visual data 204 using the extracted features and send the match data 208 to the checkout subsystem 212.
  • the feature extractor 238 may analyze the visual data 236 to extract features and send the analyzed visual data 244 to the server 246 that may subsequently recognize the items.
  • the server 246 may send the match data 248 to the checkout subsystem 242.
  • the checkout subsystem 212 may send transaction log data to the server 218 via the computer 206 while, in the system 230, the checkout subsystem 242 may send the transaction log data 250 to the server 246 directly.
  • both systems 200 and 230 may use the same object recognition technique, such as SIFT method, even though different components may perform the process of analysis and recognition.
  • the server 246 may include a recognition application 245.
  • the scale subsystem 235 and UPC reader subsystem 243 may be coupled to the checkout subsystem 242.
  • the system 230 may operate without the visual display data 240.
  • the visual display data 240 may be included in the match data 248.
  • raw visual data can be sent directly to the server 246.
  • the components of the system 230 may communicate with one another via connection mechanisms similar to those of the system 200.
  • the visual sensor 234 may communicate with the server 246 via an appropriate interface, such as a direct connection or a networked connection, wherein examples of interface standards may include, but are not limited to, Ethernet, IEEE 802.11 , Bluetooth, Universal Serial Bus, FireWire, S-Video, NTSC composite, frame grabber, and the like.
  • the Object Database 252 and the Log Data Storage 254 may be similar to their counterparts of FIG. 2A.
  • the server 246 may execute an appropriate operating system.
  • the appropriate operating system may include but is not limited to operating systems such as Linux, Unix, Microsoft® Windows® 3.1, Microsoft® Windows® 95, Microsoft® Windows® 98, Microsoft® Windows® NT, Microsoft® Windows® 2000, Microsoft® Windows® Me, Microsoft® Windows® XP, Apple® MacOS®, or IBM OS/2®. As is conventional, the appropriate operating system may advantageously include a communications protocol implementation that handles incoming and outgoing message traffic passed over the network.
  • the system 230 may operate in an operation mode and a training mode. In the operation mode, when the checkout subsystem 242 receives match data 248 from the server 246, the checkout subsystem 242 may take actions similar to those performed by the checkout subsystem 212.
  • the checkout subsystem 242 may provide transaction log data 250 to the server 246. Subsequently, the server 246 may store the data in the Object Database 252. In one embodiment, the checkout subsystem 242 may store the match data 248 locally and provide the server 246 with the match data for storage in the Object Database 252 at regular intervals, such as once per hour or once per day. Finally, the checkout system 230 may perform a verification to assure that the information based on the weight, visual data and UPC reading matches one another before the checkout system 230 includes merchandise into a transaction. When this information based on different sensors cannot be reconciled within the checkout system 230, the checkout system 230 may generate an alert signal to an operator. In yet another alternative embodiment of the current invention, a signal can be sent through a wireless device to connect to an operator who may be alerted through a second wireless display device or a monitor that is capable of receiving the signal when the computer 206 cannot find a match.
  • FIG. 2C illustrates yet another embodiment of a recognition system included in the automatic checkout system in FIG. 1.
  • the system 260 may be similar to the system 230 in FIG. 2B with a difference that the functionality of the feature extractor 238 may be implemented in a checkout subsystem 268.
  • a visual sensor 262 may send visual data 264 to a checkout subsystem 268 that may analyze the data to generate analyzed visual data 272.
  • the visual data 264 may be provided as an input to a server 274 via the checkout subsystem 268 if the server 274 has the capability to analyze the input and recognize the item associated with the input.
  • the server 274 may receive the unmodified visual data 264 via the checkout subsystem 268, and perform the analysis and feature extraction of the unmodified visual data 264.
  • the checkout subsystem 268 may use a reading of a scale subsystem 263 to check if the item is recognized correctly in the same manner as described in connection with FIG. 2A.
  • the reading may be input to a server 274 if the server 274 has the capability to check if the item is recognized correctly.
  • the checkout subsystem 268 may include a UPC reader subsystem 269.
  • a feature extractor 266 may be used to extract features and generate analyzed visual data.
  • the visual extractor 266 may be implemented within a visual sensor unit as shown in FIG. 2B or may be separate from the visual sensor. In this case, the checkout subsystem 268 may simply pass the analyzed visual data 272 to the server 274. [058]
  • the system 260 may operate in an operation mode and a training mode. In the operation mode, the checkout subsystem 268 may store a local copy of the Object Database 276 which advantageously may allow the matching process to occur relatively quickly since matching will be performed in the checkout subsystem 268. During this operation mode, the log data information will be sent to log data storage 278.
  • the server 274 may provide the checkout subsystem 268 with an updated, or synchronized copy of the Object Database 276 at regular intervals, such as once per hour or once per day, or when an update is requested by the checkout subsystem 268. [059]
  • the server 274 may send the match data 270 to the checkout subsystem 268. Subsequently, the checkout subsystem 268 may take actions similar to those performed by the checkout subsystem 242.
  • the server 274 may also provide the match data to a Log Data Storage 278. It will be understood that the match data provided to the Log Data Storage 278 can be the same as or can differ from the match data 270 provided to the checkout subsystem 268.
  • the match data provided to the Log Data Storage 278 may include an associated timestamp, but the match data 270 provided to the checkout subsystem 268 may not include a timestamp.
  • the Log Data Storage 278, as well as examples of appropriate match data provided for the Log Data Storage 278, will be discussed in greater detail later in connection with FIG. 3.
  • the checkout subsystem 268 may store match data locally and provide the server 274 with the match data for storage in the Log Data Storage 278 at regular intervals, such as once per hour or once per day. [060] It will be understood that the component of the system 260 may communicate with one another via connection mechanisms similar to those of the system 230. Also, it is noted that the Object Database 276 and Log Data Storage 278 may be similar to their counterparts of FIG.
  • FIG. 3 is a schematic diagram of an Object Database 302 and Log Data Storage 312 (or, equivalent ⁇ , log data storage database) illustrating an example of a relational database structure in accordance with one embodiment of the present invention. It will be understood by one of ordinary skill in the art that a database may be implemented on an addressable storage medium and may be implemented using a variety of different types of addressable storage mediums.
  • the Object Database 302 snd/or the Log Data Storage 312 may be entirely contained in a single device or may be spread over several devices, computers, or servers in a network.
  • the Object Database 302 and/or the Log Data Storage 312 may be implemented i n such devices as memory chips, hard drives, optical drives, and the like.
  • the databases 302 and 312 have the form of a relational database, one oT ordinary skill in the art will recognize that each of the databases may also be, by way of example, an object-oriented database, a hierarchical database, a lightweight directory access protocol (LDAP) directory, an object-oriented-relational database, and the like.
  • the databases may conform to any database standard, or may even conform to a non-standard private specification.
  • the databases 302 and 312 may also be implemented utilizing any number of commercially available database products, such as, by way of example, Oracle® from Oracle Corporation, SQL Server and Access from Microsoft Corporation, Sybase® from Sybase, Incorporated, and the like.
  • the databases 302 and 312 may utilize a relational database management system (RDBMS).
  • RDBMS relational database management system
  • the data may be stored in the form of tables.
  • data within the table may be stored within fields, which may be arranged into columns and rows.
  • Each field may contain one item of information.
  • Each column within a table may be identified by its column name one type of information, such as a value for a SIFT feature descriptor.
  • column names may be illustrated in the tables of FIG. 3.
  • a record also known as a tuple, may contain a collection of fields constituting a complete set of information.
  • the ordering of rows may not matter, as the desired row may be identified by examination of the contents of the fields in at least one of the columns or by a combination of fields.
  • a field with a unique identifier such as an integer, may be used to identify a related collection of fields conveniently.
  • two tables 304 and 306 may be included in the Object Database 302, and one table 314 may be included in the Log Data Storage 312.
  • the exemplary data structures represented by the five tables in FIG. 3 illustrate a convenient way to maintain data such that an embodiment using the data structures can efficiently store and retrieve the data therein.
  • the tables for the Object Database 302 may include a Feature Table 304, and an optional Object Recognition Table 306.
  • the Feature Table 304 may store data relating to the identification of an object and a view.
  • a view can be characterized by a plurality of features.
  • the Feature Table 304 may include fields for an Object ID, a View ID, a Feature ID for each feature stored, a Feature Coordinates for each feature stored, and a Feature Descriptor associated with each feature stored, view name field, an object name field.
  • the Object ID field and the View ID field may be used to identify the records that correspond to a particular view of a particular object.
  • a view of an object may be typically characterized by a plurality of features. Accordingly, the Feature ID field may be used to identify records that correspond to a particular feature of a view.
  • the View ID field for a record may be used to identify the particular view corresponding to the feature and may be used to identify related records for other features of the view.
  • the Object ID field for a record may be used to identify the particular object corresponding to the feature and may be used to identify related records for other views of the object and/or other features associated with the object.
  • the Feature Descriptor field may be used to store visual information about the feature such that the feature may be readily identified when the visual sensor observes the view or object again.
  • the Feature Coordinate field may be used to store the coordinates of the feature. This may provide a reference for calculations that depend at least in part on the spatial relationships between multiple features.
  • An Object Name field may be used to store the name of the object and may be used to store the price of the object.
  • the Feature Table 304 may, optionally, store additional information associated with the object.
  • the View Name field may be used to store the name of the view. For example, it may be convenient to construct a view name by appending a spatial designation to the corresponding object name. As an illustration, if an object name is "Cola 24-Pack," and the object is packaged in the shape of a box, it may be convenient to name the associated views “Cola 24-Pack Top View,” “Cola 24- Pack Bottom View,” “Cola 24-Pack Front View,” “Cola 24-Pack Back View,” “Cola 24-Pack Left View,” and “Cola 24-Pack Right View.” [067]
  • the optional Object Recognition Table 306 may include the Object ID field (such as a Universal Product Code), the View ID field, Weight field, UPC field, and the Feature ID field.
  • the optional Object Recognition Table 306 may advantageously be indexed by the Feature Descriptor, which may facilitate the matching of observed images to views and/or objects.
  • the illustrated Log Data Storage 312 includes an Output Table 314.
  • the Output Table 314 may include fields for an Object ID, a View ID, a Camera ID, a Timestamp, UPC, weight, and an Image.
  • the system may append records to the Output Table 314 as it recognizes objects during operation. This may advantageously provide a system administrator with the ability to track, log, and report the objects recognized by the system.
  • the Camera ID field for a record may be used to identify the particular visual sensor associated with the record.
  • the Image field for a record may be used to store the image associated with the record.
  • FIG. 4 is a flowchart 400 illustrating the steps that may be carried out by the system 100 in accordance with one embodiment of the present invention. It will be appreciated by those of the ordinary skill that the illustrated steps (or method) may be modified in a variety of ways without departing from the spirit and scope of the system or the method. For example, in another embodiment, various portions of the illustrated method may be combined, be rearranged in an alternate sequence, be removed, and the like. In addition, it should be noted that the method may be performed in a variety of ways, such as by software executing in a general-purpose computer, by firmware executed by a microprocessor, by dedicated hardware, and the like.
  • the customer may place a first se parator 140 on the belt 110 to initiate a transaction process, where the system 100 is trained to recognize the first separator 140. Upon recognition of the first separator 140, the system 100 may start a new transaction.
  • the customer may put one or more items 112 on the belt 110 in a state 406. Subsequently, in a state 408, the customer may put the second separator 142 as an indicator for terminating the transaction.
  • the second separator 142 may be a plastic bar that the system 100 is trained to recognize.
  • a motion detector or IR sensors may detect the start of the transaction. Then, the method proceeds to a state 410.
  • the system 100 may perform automatic processing of the items 112, wherein more details of the state 410 will be given later in connection with FIG. 5.
  • FIG. 5 is a flowchart 500 illustrating a process to be carried out in the operational block 410 in FIG. 4.
  • the automatic processing may begin in a state 502.
  • the system 100 may determine if the first separator140 has entered into the housing 114 on the moving belt 110. Recognition of the first separator 140 may be done with ViPR (visual pattern recognition) or with color identification options. If the answer to the state 502 is YES, the method proceeds to a state 504 to start a new transaction for the current customer. Subsequently, the method advances to a state 506.
  • ViPR visual pattern recognition
  • a transaction can also be started by, for example, a customer pressing a start button.
  • the system 100 may check if it can detect any items 112 on the belt 110. If any item is detected in the state 506, the system 100 may optionally turn on the lighting subsystem 118 in a state 508. Next, in a state 510, the visual sensors 120 may get image(s) of the item 112. If the system 110 cannot detect any item in the state 506, the method proceeds to a state 512. In the state 512, the system 100 may determine if it can detect the second separator 142.
  • the system 100 may end the transaction in a state 514 and wait for the first separator of the next customer to start a new transaction.
  • the system 100 may determine if it can recognize the merchandise 112 in a state 516. Recognition of the item may be done with ViPR that is explained in connection with FIGS. 2, 3 and 6. Alternatively, the color and shape of the item 112 may be used to recognize the item 112.
  • the system 100 may determine if it can recognize the UPC, where the UPC may be obtained from the visual image captured in the state 510 or th UPC may be obtained with a conventional UPC scanner. If a UPC is not in the visual image, the system 100 may not take any further steps to recognize the UPC. Then, the method proceeds to a state 520.
  • the system 100 may use the UPC reader subsystem 113 as a primary recognition tool. In this embodiment, the system 100 may use the visual image to recognize the item 112 if the UPC of the item 112 cannot be recognized.
  • the scale subsystem 122 may weigh the item 112. It is noted that the state 520 may. also be performed in parallel with the states 516 and 518. Subsequently, in a state 522, the system 100 may determine if the merchandise recognized in the state 516 matches the UPC recognized in the state 518. Also, the reading of the scale subsystem 122 obtained in the state 520 may be used to determine if the recognition in the states 516 and/or 518 is correct. The system 100 may look up the object database 302 (shown in FIG. 3) to get the weight data of the merchandise recognized in the state 516.
  • the system 100 may check if the merchandise 112 is correctly recognized in the state 516. Likewise, the system 100 may look up the same database to get the weight data of the merchandise corresponding to the UPC recognized in the state 518. By comparing the reading of the scale subsystem 122 with the weight data, the system 100 may check if the UPC is correctly recognized in the state 520. If a match is found, the system 100 may add the item to a checkout list in a state 524. Otherwise, the method proceeds to a state 526. [078] In the state 526, the system 100 may send an exception recognition to stop the conveyor belt 110.
  • the exception may be processed in a state 528, where the exception processing may involve a manual intervention or operator notification via a wireless device.
  • the system 100 may check if the exception is resolved in a state 530. If the answer to the state 530 is positive, the method proceeds to a state 506.
  • FIG. 6 is a flowchart 600 that illustrates a method to be carried out by the recognition system 200 to recognize objects in accordance with one embodiment of the present invention. It will be appreciated by those of the ordinary skill that the illustrated method may be modified in a variety of ways without departing from the spirit and scope of the present invention. For example, in another embodiment, various portions of the illustrated method may be combined, be rearranged in an alternate sequence, be removed, and the like. In addition, it should be noted that the method may be performed in a variety of ways, such as by software executing in a general-purpose computer, by firmware and/or computer readable medium executed by a microprocessor, by dedicated hardware, and the like.
  • the method 600 may begin in a state 602.
  • a visual sensor such as a camera
  • a motion trigger subsystem may trigger the visual sensor and a lighting subsystem upon detection of the object.
  • the method may advance from the state 602 to an optional state 604.
  • the method may analyze the visual data acquired in the state 602 to extract visual features.
  • the process of analyzing the visual data may be performed by a computer 206, a feature extractor 238, a checkout system 268 or a server 274 (shown in FIGS. 2A-C).
  • a variety of visual recognition techniques may be used, and it will be understood by one of ordinary skill in the art that an appropriate visual recognition technique may depend on a variety of factors, such as the visual sensor used and/or the visual features used.
  • the visual features may be identified using an object recognition process that can identify visual features.
  • the visual features may correspond to SIFT features.
  • the method may advance from the state 604 to a state 606.
  • the identified visual features may be compared to visual features stored in a database, such as an Object Database 222.
  • the comparison may be done using the SIFT method described earlier.
  • the method may find one match, may find multiple matches, or may find no matches.
  • the method finds multiple matches it may, based on one or more measures of the quality of the matches, designate one match, such as the match with the highest value of an associated quality measure, as the best match.
  • a match confidence may be associated with a match, wherein the confidence is a variable that is set by adjusting a parameter with a range, such as 0% to 100%, that may relate to, for example, the fraction of the features that are recognized as matching between the visual data and a particular stored image, or stored set of features.
  • the parameter with a range may also relate to factors including but not limited to re-projection of the feature distance or conditional numbers of affine transform, where these parameters are well known in the art.
  • a pre-determined threshold such as a 90% confidence level, the match may not be used.
  • the method finds multiple matches with match confidence that exceed the pre-determined threshold, the method may return all such matches. The method may advance from the state 606 to a decision block 608.
  • a determination may be made as to whether the match found in the state 606 is considered reliable.
  • the system 100 may optionally wait for one or more extra cycles to compare the matched object from these extra cycles, so that the system 100 can more reliably determine the true object.
  • the system 100 may verify that the matched object is identically recognized for two or more cycles before determining a reliable match. Another implementation may compute the statistical probability that each object that can be recognized is present over several cycles.
  • a match may be considered reliable if the value of the associated quality measure or associated confidence exceeds a predetermined threshold.
  • a match may be considered reliable if the number of identified features exceeds a predetermined threshold.
  • a secondary process such as matching against a smaller database, may be used to compare this match to any others present.
  • the optional decision block 610 may not be used, and the match may always be considered reliable.
  • several visual sensors can be used to increase the reliability of recognition.
  • the method may return to the state 602 to acquire another image. If the method determines that the match is considered reliable, the method may proceed to a state 612.
  • FIG. 7 is a flowchart 700 that illustrates a method for training the system 100 in accordance with one embodiment of the present invention. It will be appreciated by those of ordinary skill that the illustrated method may be modified in a variety of ways without departing from the spirit and scope of the present invention. For example, in another embodiment, various portions of the illustrated method may be combined, be rearranged in an alternate sequence, be removed, and the like. In addition, it should be noted that the method may be performed in a variety of ways, such as by software executing in a general- purpose computer, by firmware and/or computer readable medium executed by a microprocessor, by dedicated hardware, and the like.
  • the method may begin in a state 702.
  • the method may receive visual data of an item from a visual sensor, such as a camera.
  • a visual sensor such as a camera
  • training images may be captured in a photography studio or on a "workbench,” which may result in higher-quality training images and less physical strain on a human system trainer.
  • the method may advance from the state 702 to a state 704.
  • the system may receive electronic data from the manufacturer of the item, where the electronic data may include information associated with the item, such as merchandise specifications, weights, UPC and visual images.
  • the method may receive data associated with the image received in the state 702.
  • Data associated with an image may include, for example, the distance between the visual sensor and the object of the image at the time of image capture, may include an object name, may include a view name, may include an object ID, may include a view ID, may include a unique identifier, may include a text string associated with the object of the image, may include a name of a computer file (such as a sound clip, a movie clip, or other media file) associated with the image, may include a price of the object of the image, may include the UPC associated with the object of the image, and may include a flag indicating that the object of the image is a relatively high security- risk item.
  • a computer file such as a sound clip, a movie clip, or other media file
  • the associated data may be manually entered, may be automatically generated or retrieved, or a combination of both.
  • the operator of the system 100 may input all of the associated data manually.
  • one or more of the associated data items, such as the object ID or the view ID may be generated automatically, such as sequentially, by the system.
  • one or more of the associated data items may be generated through another input method. For example, a UPC associated with an image may be inputted using a barcode scanner.
  • each face of an item that needs to be recognized should be captured.
  • all such faces of a given object may be associated with the same object ID, but associated with different view IDs.
  • an item that needs to be recognized is relatively malleable and/or deformable, such as a bag of pet food or a bag or charcoal briquettes
  • several images may be taken at different deformations of the item. It may be beneficial to capture a relatively high-resolution image, such as a close-up, of the most visually distinctive regions of the object, such as the product logo. It may also be beneficial to capture a relatively high-resolution image of the least malleable portions of the item.
  • all such deformations and close-ups captured of a given object may be associated with the same object ID, but associated with different view IDs.
  • the method may advance from the state 704 to a state 706.
  • the shapes and colors of the items may be taken at different angles or directions in order to capture a sample of the variety of the items.
  • the method may store the image received in the state 702 and the associated data collected in the state 704.
  • the system 100 may store the image and the associated data in a database, which was described earlier in connection with FIGS. 2A-C.
  • the method may advance to a decision block 708.
  • the method may determine whether or not there are additional images to capture.
  • the system 100 may ask an operator whether or not there are additional images to capture, and the user's response may determine the action taken by the method.
  • the query to the user may be displayed on a checkout subsystem and the operator may respond via the input devices of the checkout subsystem. If there are additional images to capture, the method may return to the state 702 to receive an additional image. If there are no additional images to capture, the method may proceed to a state 710.
  • the method may perform a training subprocess on the captured image or images.
  • the method may scan the database that contains the images stored in the state 706, select images that have not been trained, and run the training subroutine on the untrained images.
  • the system 100 may analyze the image, find the features present in the image and save the features in the Object Database 222.
  • the method may advance to an optional state 712.
  • the method may delete the images on which the system 100 was trained in the state 710.
  • the matching method described earlier in connection with FIG. 6 may use the features associated with a trained image and may not use the actual trained image.
  • deleting the trained images may reduce the amount of disk space or memory required to store the Object Database. Then, the method may end and be repeated as desired.
  • the system 100 may be trained prior to its initial use, and additional training may be performed repeatedly. It will be understood that the number of training images acquired in different training cycles may vary in a wide range.
  • embodiments of the system and method may advantageously permit one or more visual sensors, such as one or more cameras, operatively coupled to a computer system to view and recognize items located on a conveyor subsystem of a retail store environment. These self- checkout systems may advantageously increase the checkout out speed and replace cashers, and as a consequence, may reduce labor and turnover costs.

Abstract

L'invention concerne des systèmes et des procédés qui permettent de contrôler automatiquement des articles placés sur une courroie transporteuse dans le but d'augmenter l'efficacité d'un processus de contrôle et les recettes en un point de vente. Ce système comprend un sous-système de transport servant à déplacer les articles, un boîtier qui renferme une partie de ce sous-système de transport, un sous-système d'éclairage qui éclaire une zone à l'intérieur du boîtier, des capteurs visuels qui prennent des images des articles, y compris le code universel des produits, et un système de contrôle qui reçoit les images des capteurs visuels et identifie automatiquement les articles. Ce système peut comprendre un sous-système de mesure situé sous le sous-système de transport afin de mesurer le poids des articles, le poids de chaque article permettant de vérifier si l'article correspondant est correctement identifié. Le système selon l'invention est fondé sur le principe consistant à relier des caractéristiques visuelles tirées des images stockées dans une base de données pour collationner des caractéristiques extraites des images prises par les capteurs visuels.
PCT/US2005/006079 2004-02-27 2005-02-28 Systemes et procedes pour le controle automatique de marchandises WO2005084227A2 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US10/554,516 US7337960B2 (en) 2004-02-27 2005-02-28 Systems and methods for merchandise automatic checkout
US12/074,263 US8430311B2 (en) 2004-02-27 2008-02-29 Systems and methods for merchandise automatic checkout

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
US54856504P 2004-02-27 2004-02-27
US60/548,565 2004-02-27
US62155104P 2004-10-22 2004-10-22
US60/621,551 2004-10-22
US11/023,004 US7100824B2 (en) 2004-02-27 2004-12-27 System and methods for merchandise checkout
US11/023,004 2004-12-27

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US11/023,004 Continuation-In-Part US7100824B2 (en) 2004-02-27 2004-12-27 System and methods for merchandise checkout

Related Child Applications (2)

Application Number Title Priority Date Filing Date
US10/554,516 A-371-Of-International US7337960B2 (en) 2004-02-27 2005-02-28 Systems and methods for merchandise automatic checkout
US12/074,263 Continuation US8430311B2 (en) 2004-02-27 2008-02-29 Systems and methods for merchandise automatic checkout

Publications (2)

Publication Number Publication Date
WO2005084227A2 true WO2005084227A2 (fr) 2005-09-15
WO2005084227A3 WO2005084227A3 (fr) 2006-10-05

Family

ID=34923071

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2005/006079 WO2005084227A2 (fr) 2004-02-27 2005-02-28 Systemes et procedes pour le controle automatique de marchandises

Country Status (1)

Country Link
WO (1) WO2005084227A2 (fr)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010018348A2 (fr) * 2008-08-14 2010-02-18 Azdine Bahou Dispositif d'identification et de paiement automatique par reconnaissance optique des produits agroalimentaires ou pharmaceutiques.
US8740085B2 (en) 2012-02-10 2014-06-03 Honeywell International Inc. System having imaging assembly for use in output of image data
EP2770485A1 (fr) 2013-02-25 2014-08-27 Wincor Nixdorf International GmbH Cuvette d'emballage de taille variable
CN104794830A (zh) * 2015-03-31 2015-07-22 广西智通节能环保科技有限公司 一种自助购物结账装置及自助购物结账方法
DE102009013636B4 (de) * 2009-03-18 2018-02-15 Wincor Nixdorf International Gmbh Vorrichtung und Verfahren zur Warenerfassung
CN108537994A (zh) * 2018-03-12 2018-09-14 深兰科技（上海）有限公司 基于视觉识别及重量感应技术的智能商品结算系统及方法
US10204314B2 (en) 2016-02-09 2019-02-12 Walmart Apollo, Llc Systems, devices, and methods for machine reading
CN109886169A (zh) * 2019-02-01 2019-06-14 腾讯科技（深圳）有限公司 应用于无人货柜的物品识别方法、装置、设备及存储介质
RU2716298C1 (ru) * 2019-10-21 2020-03-11 Сергей Васильевич Черненко Кассовый бокс с виртуальным автоматическим разделителем покупок и способ управления им
IT201900016229A1 (it) * 2019-09-13 2021-03-13 Antares Vision S P A Bilancia e metodo per il riconoscimento automatico di un oggetto

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3639762A (en) * 1969-02-14 1972-02-01 Burton B Hughes Marking consumer items by rendering colorless markings permanently colored with radiation exposure
US5495097A (en) * 1993-09-14 1996-02-27 Symbol Technologies, Inc. Plurality of scan units with scan stitching
US5883968A (en) * 1994-07-05 1999-03-16 Aw Computer Systems, Inc. System and methods for preventing fraud in retail environments, including the detection of empty and non-empty shopping carts

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3639762A (en) * 1969-02-14 1972-02-01 Burton B Hughes Marking consumer items by rendering colorless markings permanently colored with radiation exposure
US5495097A (en) * 1993-09-14 1996-02-27 Symbol Technologies, Inc. Plurality of scan units with scan stitching
US5883968A (en) * 1994-07-05 1999-03-16 Aw Computer Systems, Inc. System and methods for preventing fraud in retail environments, including the detection of empty and non-empty shopping carts

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010018348A2 (fr) * 2008-08-14 2010-02-18 Azdine Bahou Dispositif d'identification et de paiement automatique par reconnaissance optique des produits agroalimentaires ou pharmaceutiques.
WO2010018348A3 (fr) * 2008-08-14 2010-04-15 Azdine Bahou Dispositif d'identification et de paiement automatique par reconnaissance optique des produits agroalimentaires ou pharmaceutiques.
DE102009013636B4 (de) * 2009-03-18 2018-02-15 Wincor Nixdorf International Gmbh Vorrichtung und Verfahren zur Warenerfassung
US8740085B2 (en) 2012-02-10 2014-06-03 Honeywell International Inc. System having imaging assembly for use in output of image data
EP2770485A1 (fr) 2013-02-25 2014-08-27 Wincor Nixdorf International GmbH Cuvette d'emballage de taille variable
WO2014128004A1 (fr) 2013-02-25 2014-08-28 Wincor Nixdorf International Gmbh Bacs d'emballage de tailles variables
CN104794830A (zh) * 2015-03-31 2015-07-22 广西智通节能环保科技有限公司 一种自助购物结账装置及自助购物结账方法
CN104794830B (zh) * 2015-03-31 2017-07-18 福建爱特点信息科技有限公司 一种自助购物结账装置及自助购物结账方法
US10515338B2 (en) 2016-02-09 2019-12-24 Walmart Apollo, Llc Systems, devices, and methods for machine reading
US10204314B2 (en) 2016-02-09 2019-02-12 Walmart Apollo, Llc Systems, devices, and methods for machine reading
US10354223B2 (en) 2016-02-09 2019-07-16 Walmart Apollo, Llc Systems, devices, and methods for machine reading
CN108537994A (zh) * 2018-03-12 2018-09-14 深兰科技（上海）有限公司 基于视觉识别及重量感应技术的智能商品结算系统及方法
CN109886169A (zh) * 2019-02-01 2019-06-14 腾讯科技（深圳）有限公司 应用于无人货柜的物品识别方法、装置、设备及存储介质
CN109886169B (zh) * 2019-02-01 2022-11-22 腾讯科技（深圳）有限公司 应用于无人货柜的物品识别方法、装置、设备及存储介质
IT201900016229A1 (it) * 2019-09-13 2021-03-13 Antares Vision S P A Bilancia e metodo per il riconoscimento automatico di un oggetto
WO2021048813A1 (fr) * 2019-09-13 2021-03-18 Antares Vision S.P.A. Balance et procédé de reconnaissance automatique d'un produit
RU2716298C1 (ru) * 2019-10-21 2020-03-11 Сергей Васильевич Черненко Кассовый бокс с виртуальным автоматическим разделителем покупок и способ управления им
WO2021045648A1 (fr) * 2019-10-21 2021-03-11 Сергей Васильевич ЧЕРНЕНКО Comptoir caisse avec séparateur automatique virtuel des achats

Also Published As

Publication number Publication date
WO2005084227A3 (fr) 2006-10-05

Similar Documents

Publication Publication Date Title
US7337960B2 (en) Systems and methods for merchandise automatic checkout
US7100824B2 (en) System and methods for merchandise checkout
US7246745B2 (en) Method of merchandising for checkout lanes
WO2005084227A2 (fr) Systemes et procedes pour le controle automatique de marchandises
US7646887B2 (en) Optical flow for object recognition
CN108320404B (zh) 基于神经网络的商品识别方法、装置、自助收银台
US8876001B2 (en) Methods and apparatus for image recognition in checkout verification
CN208188867U (zh) 一种用于无人自动售货的商品识别系统
US7118026B2 (en) Apparatus, method, and system for positively identifying an item
US20190236530A1 (en) Product inventorying using image differences
US9152828B2 (en) System and method for preventing cashier and customer fraud at retail checkout
US7909248B1 (en) Self checkout with visual recognition
EP0672993A2 (fr) Dispositif et méthode automatisés pour la reconnaissance d'objets
CN101268478B (zh) 采用视频分析检测可疑活动的方法及装置
US7422147B2 (en) System and method for detecting fraudulent transactions of items having item-identifying indicia
US20090060259A1 (en) Upc substitution fraud prevention
JP2020506457A (ja) 自動店内登録システム
US10372998B2 (en) Object recognition for bottom of basket detection
US6471125B1 (en) Method of tracking produce selection data
CN108764129B (zh) 货架以及购物系统
US10720027B2 (en) Reading device and method
CN108304898B (zh) 自助结算购物车
KR20220056443A (ko) 무인 계산대
JP2023114434A (ja) 精算のための複数商品の製品認識

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

WWE Wipo information: entry into national phase

Ref document number: 2006261157

Country of ref document: US

Ref document number: 10554516

Country of ref document: US

WWP Wipo information: published in national office

Ref document number: 10554516

Country of ref document: US

122 Ep: pct application non-entry in european phase