METHOD AND APPARATUS FOR REDUCING RECOGNITION TIMES IN AN IMAGE-BASED PRODUCT RECOGNITION SYSTEM

• US 20140036630A1
• Filed: 07/31/2012
• Published: 02/06/2014
• Est. Priority Date: 07/31/2012
• Status: Active Grant

• Current Assignee: NCR Voyix Corporation
• Original Assignee: NCR Corporation
• Inventors: Herwig, Nathaniel Christopher
• Granted Patent: US 9,135,789 B2
• Time in Patent Office: Days
• US Class Current: 367/87
• CPC Class Codes: G01G 19/4144 for controlling weight of goods in commercial establishments, e.g. supermarket, P.O.S. systems
• CPC Class Codes: G01S 15/86 Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection
• CPC Class Codes: G01S 7/539 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles
• CPC Class Codes: G07G 1/0063 with means for detecting the geometric dimensions of the article of which the code is read, such as its size or height, for the verification of the registration

Abstract

A product recognition system comprises a product image data collector arranged to capture image data which is representative of an image of a product item. The product recognition system also comprises an acoustic energy source arranged to emit acoustic energy towards the product item. The product recognition further comprises a product acoustic data collector arranged to (i) capture acoustic energy deflected from the product item, (ii) process the captured acoustic data which has been deflected from the product item to provide product acoustic data which is representative of one or more characteristics of the product item, and (iii) compare the product acoustic data with a store of reference acoustic data to provide one or more subsets of items against which the captured image data can be compared to identify the product item.

Claims

1. A product recognition system comprising:

a product image data collector arranged to capture image data which is representative of an image of a product item;

an acoustic energy source arranged to emit acoustic energy towards the product item; and

a product acoustic data collector arranged to (i) capture acoustic energy deflected from the product item, (ii) process the captured acoustic data which has been deflected from the product item to provide product acoustic data which is representative of one or more characteristics of the product item, and (iii) compare the product acoustic data with a store of reference acoustic data to provide one or more subsets of items against which the captured image data can be compared to identify the product item.

2. A product recognition system according to claim 1, wherein the acoustic energy source comprises an ultrasound emitter.

3. A product recognition system according to claim 1, wherein the acoustic energy source and the product acoustic data collector are disposed on same side of the product item.

4. A product recognition system according to claim 1, further comprising a weigh scale having a weighing plate in which the acoustic energy source or the product acoustic data collector, or both, are disposed.

5. A product recognition system according to claim 1, wherein the product acoustic data collector includes (i) an acoustic energy capture device arranged to capture acoustic energy reflected from the product item, and (ii) control circuitry arranged to process the captured acoustic energy to provide acoustic data which is representative of one or more characteristics of the product item.

6. A product recognition system according to claim 5, wherein the control circuitry is further arranged to compare the product acoustic data with the store of reference acoustic data.

7. A product recognition system according to claim 6, wherein the control circuitry is further arranged to generate the one or more subsets of items against which the captured image data can be paired to identify the product item.

8. A product recognition system according to claim 7, wherein the control circuitry is further arranged to categorize the generated one or more subsets of items into one or more categories of items.

9. An apparatus for reducing recognition times in an image-based product recognition system, the apparatus comprising:

at least one acoustic energy source arranged to emit acoustic energy towards the product item;

a store of reference acoustic data which is representative of a relatively large database of product items;

an acoustic energy capture device arranged to capture acoustic data which is representative of deflected acoustic energy from the product item; and

control circuitry arranged to (i) compare the captured acoustic data with the store of reference acoustic data, (ii) identify a relatively small subset of items from the relatively large database of items based upon the comparison of the captured acoustic data with the store of reference product acoustic data, and (iii) provide the relatively small subset of product items to the image-based product recognition system to allow the product recognition system to identify the product item based upon the relatively small subset of the relatively large database of items and thereby to assist the image-based product recognition system in identifying the product item.

10. An apparatus according to claim 9, wherein the at least one acoustic energy source comprises an ultrasound emitter.

11. An apparatus according to claim 10, wherein the acoustic energy capture device comprises an ultrasound receiver.

12. An apparatus according to claim 9, wherein the store of reference product acoustic data is representative of characteristics of a relatively large database of items against which the captured acoustic data which is representative of deflected acoustic energy from the product item is compared.

13. A method of reducing recognition times in an image recognition system to identify a product item, the method comprising:

emitting acoustic energy towards the product item to be identified;

capturing acoustic energy deflected from the product item;

processing the captured acoustic energy to provide acoustic data which is representative of one or more characteristics of the product item;

comparing the acoustic data which is representative of one or more characteristics of the product item with a store of reference acoustic data which is representative of characteristics of a relatively large database of product items to provide a relatively small one or more subsets of the relatively large database of product items; and

providing the relatively small one or more subsets of items to the image recognition system to allow the image recognition system to process the one or more subsets of items to identify the product item.

14. A method according to claim 13, wherein emitting acoustic energy towards the product item to be identified includes emitting ultrasound energy towards the product item to be identified.

15. A method according to claim 14, wherein capturing acoustic energy deflected from the product item includes capturing amount and frequency of ultrasound energy reflected from the product item.

16. A method according to claim 14, wherein capturing acoustic energy deflected from the product item includes capturing multiple frequencies of ultrasound energy reflected from the product item.

17. A method according to claim 13, wherein capturing acoustic energy deflected from the product item includes capturing amount and frequency of acoustic energy reflected from the product item.

18. A method according to claim 13, wherein capturing acoustic energy deflected from the product item includes capturing multiple frequencies of acoustic energy reflected from the product item.