Price determination system and method using digitized gray-scale image recognition and price-lookup files

• US 5,969,317 A
• Filed: 11/13/1996
• Issued: 10/19/1999
• Est. Priority Date: 11/13/1996
• Status: Expired due to Term

• Current Assignee: NCR Corporation
• Original Assignee: NCR Corporation
• Inventors: Espy, Calvin L., Briggs, Barry D., Huang, Jianzhong, Ming, John C., Peng, Antai
• Primary Examiner(s): Hajec, Donald
• Assistant Examiner(s): Dunn, Drew A.
• Application Number:
  US08/748,440
• Time in Patent Office: 1,070 Days
• Field of Search: 235/378, 235/383, 235/385, 382/170, 382/177, 382/190, 382/203, 382/216, 705/20, 705/23
• US Class Current: 235/378
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06Q 20/201 Price look-up processing, e.g. updating
• CPC Class Codes: G06Q 20/208 Input by product or record sensing, e.g. weighing or scanner processing
• CPC Class Codes: G07F 7/00 Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles

Abstract

An item recognition system and method which is particularly suited for automating entry of items too small to carry readable bar code labels. The system includes a camera which digitizes the image to produce a digitized image and a gray-scale digitized image. A binary image of the gray-scale image is then produced from which the computer records an image of the item, and a computer coupled to the camera which digitizes the image to produce a digitized image and a gray-scale digitized image. A binary image of the gray-scale image is then produced from which the computer identifies the item from the binary image and obtains the price from a price-lookup file.

Claims

1. A system for determining the price of an item, the system comprising:

a camera which records an image of the item;

a frame grabber which digitizes the image to produce a digitized image and produces a gray-scale image of the digitized image;

an image thresholder which produces a binary image of the gray-scale image;

a feature extractor which extracts at least one feature from the binary image;

a feature database which contains a plurality of reference items and each reference item is described by at least one reference feature;

a price-lookup file which contains a price for each of the plurality of reference items; and

a computer which compares the at least one feature with the reference features, identifies the item as matching one of the reference items, and obtains the price of the item from the price-lookup file.

2. The system of claim 1 wherein the at least one feature comprises an indirect feature.

3. The system of claim 2 wherein the indirect feature is derived from at least two direct features.

4. The system of claim 1 wherein the at least one feature comprises a direct feature.

5. The system of claim 4 wherein the direct feature comprises a contour shape.

6. The system of claim 1 further comprising:

a transaction server coupled to the computer; and

at least one transaction terminal coupled to the transaction server.

7. The system of claim 1 further comprising:

a plurality of additional cameras for producing a plurality of additional images of additional items; and

a multiplexor which selectively connects one of the cameras to the frame grabber.

8. A method of obtaining a price of an item comprising the steps of:

sending a first message identifying a transaction terminal and including a request for item recognition to an image processing server;

switching a multiplexor to connect a frame grabber adapter coupled to the image processing server to a camera associated with the transaction terminal;

signaling the camera to record an image of the item by the image processing server;

capturing the image by the camera;

digitizing the image to produce a digitized image and a gray-scale digitized image;

producing a binary image of the gray-scale image;

extracting predetermined features from the binary image by the image processing server;

executing a parsing algorithm to identify the item from corresponding features in a feature database by the image processing server;

determining an identification number for the item from the feature database by the image processing server;

sending a second message addressed to the transaction terminal and containing the identification number to a transaction server coupled to the transaction terminal;

obtaining a description and the price for the item from a price-lookup file by the transaction server;

forwarding the description and the price to the transaction terminal by the transaction server; and

adding the description and price to the transaction by the transaction terminal.

9. A system for determining a price for an item comprising:

a camera which records an image of the item;

a frame grabber which digitizes the image to produce a digitized image and produces a gray-scale image of the digitized image;

an image thresholder which produces a binary image of the gray-scale image;

a feature extractor which extracts at least one feature from the binary image;

a transaction terminal coupled to the camera which identifies the item from the at least one feature; and

a transaction server coupled to the transaction terminal which obtains the price from a price-lookup file and returns it to the transaction terminal.

10. A method of determining a price for an item comprising the steps of:

recording an image of the item by a camera;

producing a digitized image of the image;

producing a grey-scale image of the digitized image;

producing a binary image of the grey-scale image; and

identifying the item from extracted features of the binary image, including the substep of construction a chain code representing the item, and comparing the chain code to previously stored chain codes in a database; and

obtaining a price associated with the item from a price-lookup file.

11. A system for determining the price of an item, the system comprising:

a camera which records an image of the item;

a frame grabber which digitizes the image to produce a digitized image and produces a gray-scale image of the digitized image;

an image thresholder which produces a binary image of the gray-scale image;

a feature extractor which extracts at least one direct feature from the binary image;

a feature database which contains a plurality of reference items and each reference item is described by at least one reference feature;

a price-lookup file which contains a price for each of the plurality of reference items;

a computer which;

generates at least one indirect feature from the at least one direct feature;

compares both the at least one direct feature and the at least one indirect feature with the reference features;

identifies the item as matching one of the reference items; and

obtains the price of the item from the price-lookup file.

12. A system for determining the price of an item, the system comprising:

a camera which records an image of the item;

a frame grabber which digitizes the image to produce a digitized image and produces a gray-scale image of the digitized image;

an image thresholder which produces a binary image of the gray-scale image;

an apparatus which computes a chain code from the binary image;

a feature database which contains a plurality of reference items wherein each reference item is described by a reference chain code;

a price-lookup file which contains a price for each of the plurality of reference items; and

a computer which compares the chain code with the reference chain codes, identifies the item as matching one of the reference items, and obtains the price of the item from the price-lookup file.

13. A method of obtaining a price of an item comprising the steps of:

capturing an image of the item by a camera;

producing a digitized image of the image;

producing a gray-scale image of the digitized image;

producing a binary image of the gray-scale image;

extracting at least one feature from the binary image;

executing a parsing algorithm to identify the item from a plurality of reference features in a feature database which contains a plurality of reference items and each reference item is described by at least one of the reference features;

determining an identification number for the item from the feature database; and

obtaining the price from a price-lookup file.