Image processing methods and systems for barcode and/or product label recognition

Patent metadata

Field	Value
Publication number	US-9659204-B2
Application number	US-201414303724-A
Country	US
Kind code	B2
Filing date	Jun 13, 2014
Priority date	Jun 13, 2014
Publication date	May 23, 2017
Grant date	May 23, 2017

Abstract

This disclosure provides an image processing method and system for recognizing barcodes and/or product labels. According to an exemplary embodiment, the method uses a multifaceted detection process that includes both image enhancement of a candidate barcode region and other product label information associated with a candidate barcode region to identify a product label, where the candidate barcode region includes a nonreadable barcode. According to one exemplary application, a store profile is generated based on the identifications of the product labels which are associated with a location of a product within a store.

First claim

What is claimed is:

1. A method of identifying a plurality of barcodes associated with a plurality of respective product labels, the product labels including one or more barcodes and other non-barcode related product label information, the method comprising:
an image capturing device capturing an image of a plurality of product labels and storing the captured image in a memory operatively associated with the image capturing device;
a processor operatively associated with the memory detecting and localizing a plurality of barcode candidate regions within the captured image of the plurality of product labels;
the processor cropping the detected and localized plurality of barcode candidate regions to generate one or more respective sub-images of the captured image including images of the one or more barcode candidate regions, the sub-images including a region of the captured image defined by the size of a detected barcode within the respective barcode candidate region and excluding substantially all of the other product label information associated with the respective detected barcode;
the processor processing each sub-image using two or more independent image quality improvement processes to generate modified versions of each of the plurality of barcode candidate regions and respective detected barcodes within the respective barcode candidate regions;
the processor processing the modified versions of each of the plurality of barcode candidate regions using a binary process to decode readable barcodes included in each of the modified versions of each of the candidate barcode regions to generate a numerical representation of the readable barcodes and identifying barcode candidate regions including barcodes nondecodable using the binary process; and
for each of the plurality of barcode candidate regions including a nondecodable barcode,
the processor processing the captured image of the plurality of product labels to determine auxiliary product information regions including a greater number of pixels than the respective barcode candidate region including a nondecodable barcode;
the processor determining a price-tag layout associated with each of the auxiliary product information regions by matching the auxiliary product information regions with one or more reference price-tag templates including the physical layout of the other non-barcode related product information associated with each price-tag template;
the processor extracting the other non-barcode related product label information from the auxiliary product information regions based on a matched price-tag template; and
the processor determining a numerical representation of the nondecodable barcodes associated with each auxiliary product information region based on the extracted other non-barcode related product label information of the respective auxiliary product information region.

2. The method of identifying a barcode according to claim 1 , wherein the two or more independent image quality improvement processes include one or more of contrast enhancement, tone-curve reshaping, gamma-correction, sharpening, de-blurring and morphological filtering.

3. The method of identifying a barcode according to claim 1 , wherein the two or more independent image quality improvement processes are performed in serial or parallel.

4. The method of identifying a barcode associated with a product label according to claim 1 , wherein the barcode is one of a 1D (Dimensional) and 2D barcode.

5. The method of identifying a barcode associated with a product label according to claim 1 , further comprising:
associating each of the plurality of product labels including the respective decoded barcode with a physical location in a retail environment.

6. The method of identifying a barcode associated with a product label according to claim 5 , wherein the step of detecting and localizing a plurality of barcode-candidate-regions within the captured image is biased to generate relatively more false-positives than false-negatives.

7. The method of identifying a barcode associated with a product label according to claim 1 , further comprising:
fusing the decoded readable barcodes and identifying a respective product label based on the fusion.

8. An image processing system for identifying a plurality of barcodes associated with a plurality of respective product labels, the product labels including one or more barcodes and other non-barcode related product label information, the image processing system comprising:
an image capturing device; and
a memory operatively associated with the image capturing device,
a processor operatively associated with one or both of the image capturing device and memory,
the image capturing device configured to capture an image of a plurality of product labels and storing the captured image in the memory operatively associated with the image capturing device;
the processor configured to detect and localize a plurality of barcode candidate regions within the captured image of the plurality of product labels;
the processor configured to crop the detected and localized plurality of barcode candidate regions to generate one or more respective sub-images of the captured image including images of the one or more barcode candidate regions;
the processor configured to process each sub-image using two or more independent image quality improvement processes to generate modified versions of each of the plurality of barcode candidate regions;
the processor configured to process the modified versions of each of the plurality of barcode candidate regions to decode readable barcodes included in the modified versions of each of the candidate barcode regions; and
for each of the plurality of barcode candidate regions including a nondecodable barcode,
the processor configured to process the captured image of the plurality of product labels to determine auxiliary product information regions including a greater number of pixels than the respective barcode candidate region including a nondecodable barcode;
the processor configured to determine a price-tag layout associated with each of the auxiliary product information regions by matching the auxiliary product information regions with one or more reference price-tag templates including the physical layout of the other non-barcode related product information associated with each price-tag template;
the processor configured to extract the other non-barcode related product label information from the auxiliary product information regions based on a matched price-tag template; and
the processor configured to determine a numerical representation of the nondecodable barcodes associated with each auxiliary product information region based on the extracted other non-barcode related product label information of the respective auxiliary product information region.

9. The image processing system according to claim 8 , wherein the two or more independent image quality improvement processes include one or more of contrast enhancement, tone-curve reshaping, gamma-correction, sharpening, de-blurring and morphological filtering.

10. The image processing system according to claim 8 , wherein the two or more independent image quality improvement processes are performed in serial or parallel.

11. The image processing system according to claim 8 , wherein the barcode is one of a 1D (Dimensional) and 2D barcode.

12. The image processing system according to claim 8 , further comprising:
associating each of the plurality of product labels including the respective barcode with a physical location in a retail environment.

13. The image processing system according to claim 12

Assignees

• Xerox Corp
• Conduent Business Services Llc

Inventors

• Wu Wencheng
• Venable Dennis L
• Moore Steven R
• Wade Thomas F
• Paul Peter
• Côté Adrien P

Classifications

• G06K7/1447

  extracting optical codes from image or text carrying said optical code · CPC title

• G06K7/146 Primary

  the method including quality enhancement steps · CPC title

• G06K7/1443

  locating of the code in an image · CPC title

• G06V10/225

  based on a marking or identifier characterising the area · CPC title

• G06K9/46

  Physics · mapped topic