Character count determination for a digital image

• US 10,360,448 B1
• Filed: 01/31/2018
• Issued: 07/23/2019
• Est. Priority Date: 10/17/2013
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Newman, Adam S.
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US15/884,990
• Time in Patent Office: 538 Days
• Field of Search: 382137
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/2253 Recognition of characters printed with magnetic ink G06V30/2247 takes precedence
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: H01F 27/00 Details of transformers or inductances, in general
• CPC Class Codes: H01F 27/02 Casings
• CPC Class Codes: H01F 27/323 Insulation between winding turns, between winding layers
• CPC Class Codes: H01F 27/324 Insulation between coil and core, between different winding sections, around the coil; Other insulation structures
• CPC Class Codes: H01F 41/125 Other insulating structures; Insulating between coil and core, between different winding sections, around the coil
• CPC Class Codes: Y10T 428/249921 Web or sheet containing structurally defined element or component

Abstract

An image processing system or electronic device may implement processing circuitry. The processing circuitry may receive an image, such as financial document image. The processing circuitry may determine a character count for the financial document image or particular portions of the financial document image without recognizing any particular character in the financial document image. In that regard, the processing circuitry may determine a top left score for pixels in the financial document, the top left score indicating or representing a likelihood that a particular pixel corresponds to a top left corner of a text character. The processing circuitry may also determine top right score for image pixels. Then, the processing circuitry may identify one or more text chunks using the top left and top rights scores for pixels in the financial document image. The processing circuitry may determine a character count for the identified text chunks.

Claims

1. A method comprising:

receiving, by a processor, a digital image depicting a document including text;

storing, in a memory in communication with the processor, the digital image;

applying, by the processor, an image pre-processing function to the digital image;

storing, in the memory, a modified digital image based on the applying of the image pre-processing function to the digital image;

pixilating, by the processor, the modified digital image to be comprised of arrays including either a white pixel or a black pixel;

identifying, by the processor, a text chunk in the modified digital image;

determining, by the processor, a number of black pixels in the text chunk;

determining, by the processor, a number of white pixels in the text chunk; and

determining, by the processor, a character count for the text chunk based on the number of black pixels and the number of white pixels.

2. The method of claim 1, wherein determining the number of black pixels in the text chunk comprises:

identifying a character start column in the text chunk when the number of black pixels in a current column of the text chunk exceeds a black pixel column threshold;

wherein determining the number of white pixels in the text chunk comprises;

identifying a character end column in the text chunk when the number of white pixels in a current column of the text chunk exceeds a white pixel column threshold; and

wherein determining the character count for the text chunk comprises;

increasing a character count value for each identified character end column having a corresponding character start column in the text chunk.

3. The method of claim 1, wherein identifying the text chunk in the modified digital image comprises:

determining a first pixel in the modified digital image as a top left pixel of the text chunk based on a top left score of the first pixel; and

determining a second pixel of the modified digital image as a top right pixel of the text chunk based on a top right score of the second pixel; and

determining a row of pixels in the modified digital image as a bottom edge of the text chunk.

4. The method of claim 3, where determining the row of pixels in the modified digital image as the bottom edge of the text chunk comprises:

identifying a particular row of pixels with a proportion of white pixels exceeding a bottom edge threshold; and

identifying an upper edge of the particular pixel row as the bottom edge of the text chunk.

5. The method of claim 1, wherein the image pre-processing function is at least one of a de-skewing function, a contrast adjustment function, an image cleaning function, a de-blurring function, or an image size adjustment function.

6. The method of claim 1, further comprising:

receiving, by the processor, a character count parameter including dimension information for the text chunk; and

wherein identifying the text chunk in the modified digital image comprises identifying the text chunk according to the dimension information.

7. The method of claim 1, wherein identifying the text chunk in the modified digital image comprises identifying the text chunk to include a predetermined feature depicted in the modified digital image.

8. The method of claim 1, further comprising:

determining whether a threshold number of pixel columns comprised of all white pixels are adjacent to an edge of the text chunk; and

identifying a text chunk extension when at least the threshold number of pixel columns are determined to be comprised of all white pixels adjacent to the edge of the text chunk.

9. A system comprising:

a memory configured to store a digital image depicting a document including text; and

a processor in communication with the memory, wherein the processor is configured to;

receive the digital image depicting a document including text;

apply an image pre-processing function to the digital image;

store a modified digital image based on the application of the image pre-processing function to the digital image;

pixilate the modified digital image to be comprised of arrays including either a white pixel or a black pixel;

identify a text chunk in the modified digital image;

determine a number of black pixels in the text chunk;

determine a number of white pixels in the text chunk; and

determine a character count for the text chunk based on the number of black pixels and the number of white pixels.

10. The system of claim 9, wherein the processor, to determine the number of black pixels, is configured to identify a character start column in the text chunk when the number of black pixels in a current column of the text chunk exceeds a black pixel column threshold;

wherein the processor, to determine the number of white pixels, is configured to identify a character end column in the text chunk when the number of white pixels in a current column of the text chunk exceeds a white pixel column threshold; and

wherein the processor, to determine the character count for the text chunk, is configured to increase a character count value for each identified character end column having a corresponding character start column in the text chunk.

11. The system of claim 9, wherein the processor, to identify the text chunk in the modified digital image, is configured to:

determine a first pixel in the modified digital image as a top left pixel of the text chunk based on a top left score of the first pixel; and

determine a second pixel of the modified digital image as a top right pixel of the text chunk based on a top right score of the second pixel; and

determine a row of pixels in the modified digital image as a bottom edge of the text chunk.

12. The system of claim 11, wherein the processor, to determine the row of pixels in the modified digital image as the bottom edge of the text chunk, is configured to:

identify a particular row of pixels with a proportion of white pixels exceeding a bottom edge threshold; and

identify an upper edge of the particular pixel row as the bottom edge of the text chunk.

13. The system of claim 9, wherein the image pre-processing function is at least one of a de-skewing function, a contrast adjustment function, an image cleaning function, a de-blurring function, or an image size adjustment function.

14. The system of claim 9, wherein the processor is further configured to:

receive a character count parameter including dimension information for the text chunk; and

identify the text chunk in the modified digital image according to the dimension information.

15. The system of claim 9, wherein the processor is configured to identify the text chunk to include a predetermined feature depicted in the modified digital image.

16. The system of claim 9, wherein the processor is further configured to:

determine whether a threshold number of pixel columns comprised of all white pixels are adjacent to an edge of the text chunk; and

identify a text chunk extension when at least the threshold number of pixel columns are determined to be comprised of all white pixels adjacent to the edge of the text chunk.

17. A device comprising:

a machine-readable medium, other than a transitory signal; and

instructions stored on the machine-readable medium, the instructions configured to, when executed by a processor, cause the processor to;

receive a digital image depicting a document including text;

apply an image pre-processing function to the digital image;

store a modified digital image based on the application of the image pre-processing function to the digital image;

pixilate the modified digital image to be comprised of arrays including either a white pixel or a black pixel;

identify a text chunk in the modified digital image;

determine a number of black pixels in the text chunk;

determine a number of white pixels in the text chunk; and

determine a character count for the text chunk based on the number of black pixels and the number of white pixels.

18. The device of claim 17, wherein the instructions, when executed by the processor, cause the processor to:

identify a character start column in the text chunk when the number of black pixels in a current column of the text chunk exceeds a black pixel column threshold;

identify a character end column in the text chunk when the number of white pixels in a current column of the text chunk exceeds a white pixel column threshold; and

increase a character count value for each identified character end column having a corresponding character start column in the text chunk.

19. The device of claim 17, wherein the instructions, when executed by the processor, cause the processor to:

determine a first pixel in the modified digital image as a top left pixel of the text chunk based on a top left score of the first pixel; and

determine a second pixel of the modified digital image as a top right pixel of the text chunk based on a top right score of the second pixel; and

determine a row of pixels in the modified digital image as a bottom edge of the text chunk.

20. The device of claim 17, wherein the image pre-processing function is at least one of a de-skewing function, a contrast adjustment function, an image cleaning function, a de-blurring function, or an image size adjustment function.