Method and image processing apparatus for performing optical character recognition (OCR) of an article

Patent metadata

Field	Value
Publication number	US-9984287-B2
Application number	US-201514746198-A
Country	US
Kind code	B2
Filing date	Jun 22, 2015
Priority date	Mar 5, 2015
Publication date	May 29, 2018
Grant date	May 29, 2018

Abstract

Embodiments of the present disclosure disclose a method for performing Optical Character Recognition (OCR) of an article. The method comprises acquiring an image of the article. The image of the article is scanned using predetermined scan settings. Then, textual regions of the scanned image of the article are identified. The OCR of the at least one of the textual regions is performed using predetermined OCR settings. One or more textual regions of the textual regions are marked upon determining an error in performing the OCR of the one or more textual regions. The OCR of the one or more textual regions is iterated as per one or more predefined OCR scanning parameters based on an OCR quality of the one or more textual regions upon marking the one or more textual regions.

First claim

We claim:

1. A method for performing Optical Character Recognition (OCR) of an article, the method comprising:
acquiring, by an image processing apparatus, an image of the article;
scanning, by the image processing apparatus, the image of the article using predetermined scan settings;
identifying, by the image processing apparatus, textual regions of the scanned image of the article by:
segregating the scanned image of the article into the textual regions and image regions, wherein the segregation is based on a boundary detection technique comprising:
performing block segmentation and block identification on the scanned image,
wherein the block segmentation comprises segmenting the image of the article into a plurality of non-overlapping blocks based on performing recursive segmentation on the image of the article, and
wherein the block identification comprises extracting connected components and image boundary features from the non-overlapping blocks,
 wherein a verification is performed to determine whether the connected components and the image boundary features characterize the non-overlapping blocks of the image of the article, and
 wherein each of the non-overlapping blocks is segregated into the textual region and image region based on the verification; and

marking, upon segregating the scanned image, the textual regions and the image regions based on a scan quality of the scanned image of the article;

performing, by the image processing apparatus, the OCR of the textual regions using predetermined OCR settings;
marking, by the image processing apparatus, one or more textual regions of the textual regions upon determining an error in performing the OCR of the one or more textual regions; and
iterating, by the image processing apparatus, the OCR of the one or more textual regions as per one or more predefined OCR scanning parameters based on an OCR quality of the one or more textual regions upon marking the one or more textual regions, wherein iterating the OCR comprises scanning the one or more textual regions with a pre-determined resolution quality.

2. The method as claimed in claim 1 further comprising displaying by the image processing apparatus, at least one of the marked textual regions and the marked image regions on a display unit associated to the image processing apparatus.

3. The method as claimed in claim 1 , wherein the one or more predefined OCR scanning parameters comprise at least one of predefined number of iterations of the OCR and an amount of the OCR of the one or more textual regions.

4. The method as claimed in claim 3 further comprising indicating by the image processing apparatus, at least one of the predefined number of iterations of the OCR and the amount of the OCR of the one or more textual regions on the display unit while iterating the OCR.

5. The method as claimed in claim 1 further comprising modifying by the image processing apparatus, the predetermined OCR settings for performing the OCR of the one or more textual regions using the predetermined resolution quality of the one or more textual regions in each iteration.

6. An image processing apparatus for performing Optical Character Resolution (OCR) of an article comprising:
a processor;
a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, cause the processor to:
acquire an image of the article;
scan the image of the article using predetermined scan settings;
identify textual regions of the scanned image of the article by:
segregating the scanned image of the article into the textual regions and image regions, wherein the segregation is based on a boundary detection technique comprising:
performing block segmentation and block identification on the scanned image,
wherein the block segmentation comprises segmenting the image of the article into a plurality of non-overlapping blocks based on performing recursive segmentation on the image of the article, and
wherein the block identification comprises extracting connected components and image boundary features from the non-overlapping blocks,
 wherein a verification is performed to determine whether the connected components and the image boundary features characterize the non-overlapping blocks of the image of the article, and
 wherein each of the non-overlapping blocks is segregated into the textual region and image region based on the verification; and

marking, upon segregating the scanned image, the textual regions and the image regions based on a scan quality of the scanned image of the article;

perform the OCR of the textual regions using predetermined OCR settings;
mark one or more textual regions of the textual regions upon determining an error in performing the OCR of the one or more textual regions; and
iterate the OCR of the one or more textual regions as per one or more predefined OCR scanning parameters based on an OCR quality of the one or more textual regions upon marking the one or more textual regions, wherein iterating the OCR comprises scanning the one or more textual regions with a predetermined resolution quality.

7. The image processing apparatus as claimed in claim 6 is communicatively connected to one or more computing devices, wherein the article is acquired from the one or more computing devices.

8. The image processing apparatus as claimed in claim 6 is associated to a display unit configured to display at least one of the marked textual regions and the marked image regions on the display unit.

9. The image processing apparatus as claimed in claim 6 , wherein the one or more predefined OCR scanning parameters comprise at least one of predefined number of iterations of the OCR and an amount of the OCR of the one or more textual regions.

10. The image processing apparatus as claimed in claim 9 , wherein the processor is further configured to indicate at least one of the predefined number of iterations of the OCR and the amount of the OCR of the one or more textual regions.

11. The image processing apparatus as claimed in claim 6 , wherein the processor is further configured to modify the predetermined OCR settings for performing the OCR of the one or more textual regions using the predetermined resolution quality of the one or more textual regions in each iteration.

12. A non-transitory computer readable medium including instructions stored thereon that when processed by a processor cause an image processing apparatus to perform acts of:
acquiring an image of the article;
scanning the image of the article using predetermined scan settings;
identifying textual regions of the scanned image of the article by:
segregating the scanned image of the article into the textual regions and image regions, wherein the segregation is based on a boundary detection technique comprising:
performing block segmentation and block identification on the scanned image,
wherein the block segmentation comprises segmenting the image of the article into a plurality of non-overlapping blocks based on performing recursive segmentation on the image of the article, and
wherein the block identification comprises extracting connected components and image boundary features from the non-overlapping blocks,
 wherein a verification is performed to determine whether the connected components and the image boundary features characterize the non-overlapping blocks of the image of the article, and
 wherein each of the non-overlapping blocks is segregated into the textual region and image region based on the verification; and

marking, upon segregating the scanned image, the textual regions and the image regions based on a scan

Assignees

• George Tomson Ganapathiplackal
• Joseph Sudheesh
• Wipro Ltd

Inventors

• George Tomson Ganapathiplackal
• Joseph Sudheesh

Classifications

• G06V30/147

  Determination of region of interest · CPC title

• G06V30/133

  Evaluation of quality of the acquired characters · CPC title

• G06V30/12

  Detection or correction of errors, e.g. by rescanning the pattern · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/036

  Physics · mapped topic