Controlling shopper checkout throughput

• US 8,061,603 B2
• Filed: 03/20/2008
• Issued: 11/22/2011
• Est. Priority Date: 03/20/2008
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Otto, Charles A., Haas, Norman, Flickner, Myron D., Hampapur, Arun, Pankanti, Sharathchandra U., Connell, Jonathan H. II
• Primary Examiner(s): Lee; Seung
• Assistant Examiner(s): JOHNSON, SONJI N
• Application Number:
  US12/052,051
• Publication Number:
  US 20090236419A1
• Time in Patent Office: 1,342 Days
• Field of Search: 235/383, 73/11.3, 382/100
• US Class Current: 235/383
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles

Abstract

The present invention provides a solution for controlling checkout throughput. Specifically, under the present invention a set of attributes of an item will be obtained. An analysis of the set of attributes will then be performed to determine whether an inconsistency exists based on a tolerance threshold. Such analysis can include, for example, comparing the weight of the item to its expected weight. This can help determine if a mistake has been made or fraud has been committed. Whether an inconsistency is observed is based on a tolerance threshold. For example, a certain deviation (i.e., the tolerance threshold) from an expected value could be allowed to could be allowed to reduce errors during the checkout process and thereby increase checkout throughput. As such, the present invention allows the tolerance threshold to be tuned based on a desired checkout throughput.

Claims

1. A method for controlling a checkout throughput, comprising:

capturing an image of an item with an image capture device, wherein the capturing includes waiting for a low motion of the item, taking dark and bright images of the item and using the dark and bright images to segment the item from a background to obtain a captured image of the item;

scanning a barcode of the item with a scanning device;

wherein the image capture device and the scanning device are adjacent to each other and are both positioned within a common enclosure and the item is positioned outside the common enclosure;

processing the image to capture an appearance of the item;

wherein the processing includes extracting at least one visual feature;

searching a database of items to determine an identity of the item and a set of expected attributes of the item, based on the captured image barcode, wherein the set of expected attributes includes at least one of;

an expected identity of the item, an expected appearance of the item, an expected physical dimension of the item, an expected price of the item, and an expected weight of the item;

obtaining a set of actual attributes for the item, wherein the obtaining is performed by at least one of;

a scale, a user input, and the barcode scan;

analyzing the set of actual attributes and the set of expected attributes to determine whether an inconsistency exists;

wherein an inconsistency exists when the set of actual attributes differs from the expected set of attributes by more than a tolerance threshold; and

automatically and dynamically tuning the tolerance threshold based on a desired checkout throughput, wherein the tuning comprises increasing the tolerance threshold in the case that an actual checkout throughput is greater than the desired checkout throughput, and decreasing the tolerance threshold in the case that the actual checkout throughput is less than the desired checkout throughput.

2. The method of claim 1, the expected and actual sets of attributes being selected from a group consisting of an identity of the item, an appearance of the item, a physical dimension of the item, a price of the item, and a weight of the item.

3. The method of claim 1, the method being performed at a checkout station.

4. The method of claim 1, the desired checkout throughput being based on at least one of the following:

a waiting time of shoppers, a shopping pattern of the shoppers, or a type of business selling the item.

5. A system for tuning a tolerance threshold for shopping checkout, comprising:

an image capture module for capturing an image of an item, wherein the capturing includes waiting for a low motion of the item, taking dark and bright images of the item and using the dark and bright images to segment the item from a background to obtain a captured image of the item;

a scanning module for scanning a barcode of the item with a scanning device;

wherein the image capture module and the scanning module are adjacent to each other and are both positioned within a common enclosure and the item is positioned outside the common enclosure;

a module for processing the image to capture an appearance of the item;

wherein the processing includes extracting at least one visual feature;

a module for determining an identity of the item and a set of expected attributes of the item, based on the captured image, wherein the set of expected attributes includes at least one of;

an expected identity of the item, an expected appearance of the item, an expected physical dimension of the item, an expected price of the item, and an expected weight of the item;

a module for obtaining a set of actual attributes for the item, wherein the obtaining is performed by at least one of;

a scale, a user input, and the barcode scan;

a module for analyzing the set of actual attributes and the set of expected attributes to determine whether an inconsistency exists;

wherein an inconsistency exists when the set of actual attributes differs from the expected set of attributes by more than a tolerance threshold; and

a module for automatically and dynamically tuning the tolerance threshold based on a desired checkout throughput, wherein the tuning comprises increasing the tolerance threshold in the case that an actual checkout throughput is greater than the desired checkout throughput, and decreasing the tolerance threshold in the case that the actual checkout throughput is less than the desired checkout throughput.

6. The system of claim 5, the expected and actual sets of attributes being selected from a group consisting of an identity of the item, an appearance of the item, a physical dimension of the item, a price of the item, and a weight of the item.

7. The system of claim 5, the system being implemented at a shopping checkout station.

8. The system of claim 5, the desired shopper throughput being based on at least one of the following:

a waiting time of shoppers, a shopping pattern of the shoppers, or a type of business selling the item.

9. A program product stored on a non-transitory computer readable medium for tuning a tolerance threshold for shopping checkout, the non-transitory computer readable medium comprising program code for causing a computer system to:

capture an image of an item with an image capture device, wherein the capturing includes waiting for a low motion of the item, taking dark and bright images of the item and using the dark and bright images to segment the item from a background to obtain a captured image of the item;

scan a barcode of the item with a scanning device;

wherein the image capture device and the scanning device are adjacent to each other and are both positioned within a common enclosure and the item is positioned outside the common enclosure;

process the image to capture an appearance of the item;

wherein the process includes extracting at least one visual feature;

determine an identity of the item and a set of expected attributes of the item, based on the captured image, wherein the set of expected attributes includes at least one of;

an expected identity of the item, an expected appearance of the item, an expected physical dimension of the item, an expected price of the item, and an expected weight of the item;

obtain a set of actual attributes for the item, wherein the obtaining is performed by at least one of;

a scale, a user input, and the barcode scan;

analyze the set of actual attributes and the set of expected attributes to determine whether an inconsistency exists;

wherein an inconsistency exists when the set of actual attributes differs from the expected set of attributes by more than a tolerance threshold; and

automatically and dynamically tune the tolerance threshold based on a desired checkout throughput, wherein the tuning comprises increasing the tolerance threshold in the case that an actual checkout throughput is greater than the desired checkout throughput, and decreasing the tolerance threshold in the case that the actual checkout throughput is less than the desired checkout throughput.

10. The program product of claim 9, the expected and actual sets of attributes being selected from a group consisting of an identity of the item, an appearance of the item, a physical dimension of the item, a price of the item, and a weight of the item.

11. The program product of claim 9, the program product being performed at a checkout station.

12. The program product of claim 9, the desired shopper throughput being based on at least one of the following:

a waiting time of shoppers, a shopping pattern of the shoppers, or a type of business selling the item.

13. A method for deploying a system for tuning a tolerance threshold for shopping checkout, comprising:

providing a computer infrastructure being operable to;

capture an image of an item with an image capture device, wherein the capturing includes waiting for a low motion of the item, taking dark and bright images of the item and using the dark and bright images to segment the item from a background to obtain a captured image of the item;

scan a barcode of the item with a scanning device;

wherein the image capture device and the scanning device are adjacent to each other and are both positioned within a common enclosure and the item is positioned outside the common enclosure;

process the image to capture an appearance of the item;

wherein the process includes extracting at least one visual feature;

search a database of items to determine an identity of the item and a set of expected attributes of the item, based on the captured image wherein the set of expected attributes includes at least one of;

an expected identity of the item, an expected appearance of the item, an expected physical dimension of the item, an expected price of the item, and an expected weight of the item;

obtain a set of actual attributes for the item, wherein the obtaining is performed by at least one of;

a scale, a user input, and the barcode scan;

analyze the set of actual attributes and the set of expected attributes to determine whether an inconsistency exists;

wherein an inconsistency exists when the set of actual attributes differs from the expected set of attributes by more than a tolerance threshold; and

automatically and dynamically tune the tolerance threshold based on a desired checkout throughput, wherein the tuning comprises increasing the tolerance threshold in the case that an actual checkout throughput is greater than the desired checkout throughput, and decreasing the tolerance threshold in the case that the actual checkout throughput is less than the desired checkout throughput.