Document image orientation assessment and correction

• US 10,181,077 B1
• Filed: 03/06/2018
• Issued: 01/15/2019
• Est. Priority Date: 10/06/2017
• Status: Active Grant

• Current Assignee: Vertifi Software, LLC
• Original Assignee: Vertifi Software, LLC
• Inventors: Smith, Christopher Edward
• Primary Examiner(s): Krasnic, Bernard
• Application Number:
  US15/913,639
• Time in Patent Office: 315 Days
• Field of Search: None
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06Q 40/128 Check-book balancing, updating or printing arrangements
• CPC Class Codes: G06T 1/0007 Image acquisition
• CPC Class Codes: G06T 3/40 Scaling of whole images or parts thereof, e.g. expanding or contracting
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

The present invention relates to methods and systems for automated processing of document images using mobile and desktop communications devices. Systems and methods are provided for expediting analysis of the accuracy and quality of captured images by such devices before transmission to a server for processing. The processes use on-device software to provide immediate feedback to the user as to whether the quality of the document photograph is sufficient for processing, without the need for intermediate communication with a server. The processes utilize component labeling, MICR character recognition methods, automatic image rotation, and weighted image scaling. The invention increases speed of processing, reduces rates of rejection, increases processor efficiency, limits memory use, identifies images with likely errors, and provides the opportunity for correction of errors at the earliest possible time.

Claims

1. A method for determining a proper orientation of a static image of a document consisting of a plurality of pixels within a viewfinder of an image capturing device controlled by a processor, comprising:

a. acquiring on the device the static image of the document consisting of a plurality of pixels;

b. locating a specified subregion of the image;

c. selecting a specified set of known characters of a defined font, each said known character comprising a single set of contiguous character defining pixels of known relative location and known luminosity or luminosity range;

d. determining a luminosity or luminosity range of a plurality of pixels within the subregion;

e. creating a matrix of the locations of pixels that are within said subregion;

f. selecting a first specified luminosity or luminosity range;

g. identifying the locations of pixels within said subregion that are of said first specified luminosity;

h. assigning in said matrix a unique label to each location of a pixel with said first specified luminosity;

i. merging the labels assigned to pixel locations to a common distinctive label group if said pixel locations in said matrix are 8-connected;

j. selecting a second specified luminosity or luminosity range, wherein said second specified luminosity or luminosity range may be the same as or different from said first specified luminosity or luminosity range;

k. for each pixel location within each said distinctive label group, determining the luminosity or luminosity range of the character defining pixel at the similar relative pixel location within each set of character defining pixels;

l. for each pixel location within each said distinctive label group and for each set of character defining pixels, determining whether each said pixel location matches the similar relative pixel location of a character defining pixel of the second specified luminosity or luminosity range within each set of character defining pixels;

m. determining a number of said matches for each distinctive label group and each known character;

n. identifying each distinctive label group with said matches in excess of a second threshold number as a known character;

o. calculating a number of known characters in the subregion;

p. determining proper orientation of the static image of the document if the number of known characters in the subregion exceeds a first threshold number; and

q. concluding that the orientation of the static image of the document has not been determined if the number of known characters in the subregion does not exceed the first threshold number.

2. The method of claim 1, wherein said determining whether a pixel location within a distinctive label group matches the similar relative pixel location of a character defining pixel of the second specified luminosity or luminosity range within each set of character defining pixels comprises:

a. adjusting at least one of a height and a width of the pixel'"'"'s distinctive label group matrix to match an aspect ratio of a matrix of each set of character defining pixels;

b. for each set of character defining pixels, comparing a relative coordinate location of the pixel within the adjusted distinctive label group matrix to a corresponding relative coordinate location of a pixel within the set of character defining pixels;

c. determining whether the pixel at the corresponding relative coordinate location within the set of character defining pixels is a pixel of said second specified luminosity or luminosity range; and

d. concluding that there is a match between the pixel location within the distinctive label group and the corresponding location of the character defining pixel if said character defining pixel is of said second specified luminosity or luminosity range.

3. The method of claim 1, wherein identifying each distinctive label group with said matches in excess of a second threshold number as a known character further comprises assigning to the distinctive label group the known character with a highest number of said matches.

4. The method of claim 1, wherein distinctive label groups are eliminated from consideration as a known character on a basis of one or more size criteria.

5. The method of claim 4, wherein said eliminating a distinctive label group for consideration as a known character based upon one or more size criteria comprises:

a. determining a label height for the distinctive label group by determining a maximum vertical distance between any two pixel locations assigned the unique label of said distinctive label group; and

b. discarding the distinctive label group if said label height is in excess of a first limit number or less than a second limit number.

6. The method of claim 4, wherein said eliminating a distinctive label group for consideration as a known character based upon one or more size criteria comprises:

a. determining a label width for the distinctive label group by determining a maximum horizontal distance between any two pixel locations assigned the unique label of said distinctive label group; and

b. discarding the distinctive label group if said label width is in excess of a third limit number or less than a fourth limit number.