Automated apparatus and method for object recognition at checkout counters

• US 5,497,314 A
• Filed: 03/07/1994
• Issued: 03/05/1996
• Est. Priority Date: 03/07/1994
• Status: Expired due to Term

• Current Assignee: Jeffrey M. Novak
• Original Assignee: Jeffrey M. Novak
• Inventors: Novak, Jeffrey M.
• Primary Examiner(s): Hayes, Gail O.
• Assistant Examiner(s): Thomas, Joseph
• Application Number:
  US08/206,955
• Time in Patent Office: 729 Days
• Field of Search: 364/400, 364/401, 364/402, 364/403, 364/404, 186/52, 186/56, 186/58, 186/59, 186/60-69, 235/383, 235/462, 235/385, 382/8, 382/1, 382/110, 382/111, 382/203, 382/143, 382/216, 382/294, 348/91, 348/150
• US Class Current: 705/17
• CPC Class Codes: A47F 9/046 Arrangement of recording means in or on check-out counters record carriers or readers per se G06K
• CPC Class Codes: G06K 7/10871 randomly oriented data-fields, code-marks therefore, e.g. concentric circles-code
• CPC Class Codes: G06Q 20/202 Interconnection or interaction of plural electronic cash registers [ECR] or to host computer, e.g. network details, transfer of information from host to ECR or from ECR to ECR
• CPC Class Codes: G06Q 20/203 Inventory monitoring
• CPC Class Codes: G06Q 20/204 comprising interface for record bearing medium or carrier for electronic funds transfer or payment credit
• CPC Class Codes: G06Q 20/208 Input by product or record sensing, e.g. weighing or scanner processing
• CPC Class Codes: G06V 20/68 Food, e.g. fruit or vegetables
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles

Abstract

An automated check-out system for retail stores, such as supermarkets, employing digitized video signals and other means to determine and differentiate individual products, and thereby register the data for billing and inventory purposes. The sensors control the flow and positioning of retail items into the housing wherein the light source is regulated and controlled. Within the housing, optical imaging of the retail item is made with the electronic signal being digitized. By use of computerized databases, the digitized signal is compared to the finite set of data for products of approximately the same size, shape, weight and other comparative variables. Further confirmation of product identity is achieved by use of bar code differentiation, multiple image comparisons and, if necessary, optical display to the store personnel operating the cash register station serving multiple check-out lanes within the store. The customer is guided through the transaction by use of a video display screen. Once the items are registered, the customer then may bag the items and proceed to the centralized cashier station to complete the transaction.

Claims

1. A method for automatically recognizing and identifying, without human intervention, a particular object from a set of unknown objects of different sizes, shapes and pictorial characteristics for purposes of customer billing and inventory control, said method comprising:

providing a computerized data base for storage of object data sets for all objects to be identified, the data sets containing information regarding the size and shape of each object and one or more digitized images of pictorial characteristics of each object from various random orientations by which each object can be recognized and identified by the combination of size, shape and pictorial characteristics;

providing an identification station into which each object to be identified can be introduced without regard to its orientation within the station;

viewing each object at the identification station to capture a digital image of the object;

converting the captured image to a digitized signal;

communicating to the computerized data base the digitized signal of the image captured at the identification station;

comparing the digitized signal of the captured image with the stored object data sets within the computerized data base until the highest correlating combination of size, shape and pictorial characteristics extracted from the digitized signal of the captured image is made with one or more of the object data sets contained within the data base of object data sets; and

positively recognizing and identifying the object by said comparison.

2. The method of claim 1 in which the frame scan lines and image scan lines of the digital image are extracted and communicated to the data base and compared with the stored data sets to confirm the object identification.

3. The method of claim 1 in which the pixels of the digital image are extracted and communicated to the data base and compared with the stored data sets to confirm the object identification.

4. The method of claim 1 in which the information contained in the object data sets of the data base also includes the weight of each object to be identified, and at the identification station the weight of the object is measured, and the measured weight is converted to a digitized signal that is communicated to the data base so as to reduce the number of stored object data sets that are compared to positively recognize and identify the object.

5. The method of claim 1 in which the object identification data is stored and periodically communicated to a main processing unit for use in billing and inventory control.

6. A method for the automated check-out registering and inventory of objects sold to customers at a sales outlet which method provides for recognition, identification, differentiation and comparison of individual unknown objects at multiple check-out stations within the outlet without human intervention, said method comprising the steps of:

storing multiple object identification signals in a central data base, each identification signal pertaining to a physical characteristic of one of the individual objects offered for sale within the sales outlet, the characteristics including the size, shape and pictorial characteristics of each object;

providing at each check-out station an object identification station;

moving each object to be recognized and identified into the object identification station;

capturing an image of each object regardless of its orientation within the object identification station;

moving the object out of the identification station once the image is captured;

converting the captured image into an electronic signal that represents the size, shape and pictorial characteristics of the object;

communicating the electronic signal to the central data base;

comparing the electronic signal with the object identification signals stored in the data base until a match is made and the recognition and identification of the object determined;

communicating the known identification of the object to a processor where it is stored and price information assigned to the identified object; and

continuing the identification of all objects to be identified for a particular customer.

7. The method of claim 6 in which the stored multiple object identification signals in the central data base include a signal pertaining to the weight of each object to be identified and at the object identification station the weight of the object is also determined as the object is stopped, and the weight information is converted to a signal and communicated to the central data base, the signal representing the weight being used to the object.

8. The method of claim 7 further comprising the steps of:

providing a memory for the storage of received object identification signals; and

periodically communicating said stored identification signals to a central processor for use in the control of inventory of the objects in the sales outlet.

9. A retail store check-out registration and inventory identification system for recognizing and identifying unknown objects sold to customers of the store, said system comprising:

a central processing unit including memory means for the storage of preestablished object identification data including data sets for all the objects of the store, each object data set providing identification data corresponding to a separate object for sale within the store being serviced by the automated check-out system and including object data sets representing the size, shape and pictorial characteristics of each object from different orientations by which each object can be recognized and identified;

a plurality of customer check-out stations, each station having;

a display screen providing for the display of operative instructions to the customer utilizing the check-out station;

an object identification station;

digital video imaging means combined with the identification station for capturing an optical image of an object in the station regardless of the orientation of the object within the identification station;

transport means to move an object into the object identification station for purposes of imaging;

a first sensor combined with the object transport means to stop said transport means when an object enters the identification station and to activate the video imaging means;

means for digitizing of the electronic signal produced by the video imaging means and which represents the size, shape and pictorial characteristics of an object in the identification station;

means for communicating the digitized signal to the central processing unit;

means for comparing the digitized signal representing the object data received from each check-out station with the object identification data sets stored within said central processing unit to recognize and identify the object and register its identity in the memory; and

means for correlating the multiple electronic object identification signals received from a check-out station for a particular customer.

10. The system of claim 9 in which each multiple electronic object identification signal received from a check-out station for a particular customer is converted to a per object price, a cashier station is provided for customer payment for the objects registered in the memory, and means is provided for communicating the information regarding object price to the cashier station.

11. The system of claim 9 in which each object data set includes a digitized signal representing the weight of each object of the store and each object identification station also includes object weight determination means for weighing each object in the station, and means for converting said weight information to a digitized signal and communicating said signal to the processing unit so as to reduce the number of stored object data sets that are compared to positively recognize and identify the object also being identified by the video imaging means.

12. The system of claim 9 in which the primary identification means is the optical-image based digitized signal.

13. The system of claim 12 in which the secondary identification means is the data of the digitized representation of the object data set.

14. The system of claim 13 in which there is a tertiary identification means including pictorial images of the object captured by the digital video imaging means, means for converting said pictorial images to electronic signals, and means for comparing said signals to electronically stored pictorial images of the objects in the central processing unit.

15. The system of claim 14 in which said pictorial images include the image for the universal product code (UPC) of the object in the identification station and by which the object can be identified by utilizing algorithms measuring the relation to the size and spacing of bars and spaces.

16. The system of claim 14 in which said pictorial images include the image for the UPC of the object in the identification station and by which the object can be identified by comparing the digitized representation of the UPC with stored data sets of the UPCs within the central processing unit.

17. The system of claim 9 in which there is means combined with each of the check-out stations providing for the multiple communication of electronic data and simultaneous computerized analysis of the data in making object identification determinations.

18. The system of claim 10 in which the central processing unit includes means providing for communication between the multiple check-out stations, the cashier'"'"'s station and the central processing unit in addition to the memory means for storage of the object identification data.

19. The system of claim 18 in which the cashier'"'"'s station includes a portable terminal for communicating with the central processing unit.

20. The system of claim 9 in which the check-out stations are combined with a customer-operated automated electronic payment system providing for the payment of the transaction using the customer'"'"'s electronic debit card.