Character count determination for a digital image

• US 9,286,514 B1
• Filed: 10/17/2013
• Issued: 03/15/2016
• 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:
  US14/056,565
• Time in Patent Office: 880 Days
• Field of Search: 382/135, 382/136, 382/137, 382/138, 382/139, 382/140, 235/5, 235/17, 235/462.11, 235/462.24, 235/462.41, 194/209, 194/212, 194/290, 194/342
• US Class Current: 1/1
• 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:

in an electronic device comprising a memory for holding document image data and processor in communication with the memory, the processor;

receiving a financial document image;

identifying a text chunk in the financial document image by;

determining a first pixel of the financial document image as top left pixel of the text chunk based on a top left score of the first pixel; and

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

determining a character count for the text chunk without recognizing any particular character in the text chunk.

2. The method of claim 1, where identifying the text chunk in the financial document image further comprises:

determining a bottom edge of the text chunk.

3. The method of claim 2, where determining the bottom edge of the text chunk comprises:

identifying a particular pixel row 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.

4. The method of claim 1, where the top left score of the first pixel represents a likelihood that the first pixel corresponds to a top left corner of a text character.

5. The method of claim 4, where the top left score of the first pixel represents a likelihood that the first pixel is a particular pixel distance from the top left corner of the text character.

6. The method of claim 1, where the top right score of the second pixel represents a likelihood that the second pixel corresponds to a top right corner of a text character.

7. The method of claim 1, where determining a character count for the text chunk comprises:

processing pixel columns in the text chunk to determine a first character start column and a corresponding character end column; and

incrementing a counter after determining the corresponding character end column.

8. The method of claim 7, further comprising:

processing each of the pixels columns in the text chunk; and

determining the character count as a value of the counter after processing each of the pixel columns.

9. The method of claim 1, further comprising:

determining a character count for the financial image document by summing character counts of text chunks in the financial document image.

10. The method of claim 9, further comprising:

determining whether the character count for the financial image document meets a minimum character count threshold; and

when the character count for the financial image document meets the minimum character count threshold;

performing further image processing on the financial document image; and

when the character count for the financial image document does not meet the minimum character count threshold;

rejecting the financial document image.

11. The method of claim 10, where performing further image processing on the financial document image when the character count for the financial image document meets the minimum character count threshold comprises:

performing Optical Character Recognition (OCR) on the financial document image.

12. The method of claim 10, where rejecting the financial document image when the character count for the financial image document does not meet the minimum character count threshold comprises:

instructing recapture of the financial document image.

13. The method of claim 1, where identifying the text chunk in the financial document image further comprises:

adjusting an edge of the text chunk to include an additional row or column of white pixels based on a padding parameter value.

14. A system comprising:

a memory for storing document image data; and

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

receive a financial document image;

identify a text chunk in the financial document image by;

determining a first pixel of the financial document image as top left pixel of the text chunk based on a top left score of the first pixel; and

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

determine a chunk extension for the text chunk;

add the chunk extension to the text chunk so the text chunk includes the chunk extension; and

after adding the chunk extension to the text chunk;

determine a character count for the text chunk without recognizing any particular character in the text chunk.

15. The system of claim 14, where the processing processor is configured to determine the chunk extension for the text chunk by:

identifying a threshold number of consecutive columns positioned left or right of the text chunk, where each of the consecutive columns have a proportion of white pixels that exceed an extension threshold.

16. The system of claim 15, where the processor is further configured to determine the chunk extension for the text chunk by:

determining the chunk extension as a section of pixels between an edge of the text chunk and a first column of the consecutive columns.

17. A non-transitory computer readable medium comprising:

instructions that, when executed by a processor, cause the processor to;

receive a financial document image;

identify an interest region in the financial document image;

identify a text chunk in the interest region of the financial document image by;

determining a first pixel of the financial document image as top left pixel of the text chunk based on a top left score of the first pixel;

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

determine a character count for the text chunk in the interest region of the financial document image without recognizing any particular character in the text chunk;

determine a character count for the interest region by summing the character count for the text chunk with a character count of any additional text chunks in the interest region; and

determine whether the character count for the interest region exceeds a minimum character count threshold specifically for the interest region.

18. The non-transitory computer readable medium of claim 17, where the interest region comprises a high priority field of the financial document image.

19. The non-transitory computer readable medium of claim 17, where the interest region comprises a Magnetic Ink Character Recognition (MICR) portion of a check.

20. The non-transitory computer readable medium of claim 17, where the instructions cause the process to reject the financial document image when the character count for the interest region does not meet the minimum character count threshold.