Apparatuses, methods, and systems for remote deposit capture with enhanced image detection

• US 9,779,452 B1
• Filed: 09/04/2015
• Issued: 10/03/2017
• Est. Priority Date: 06/08/2010
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Medina, Reynaldo, Prasad, Bharat
• Primary Examiner(s): Wong, Eric T
• Application Number:
  US14/846,586
• Time in Patent Office: 760 Days
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• CPC Class Codes: G06Q 20/0425 the cheque being electronic only
• CPC Class Codes: G06Q 20/1085 involving automatic teller machines [ATMs]
• CPC Class Codes: G06Q 20/3276 using a pictured code, e.g. barcode or QR-code, being read by the M-device
• CPC Class Codes: G06Q 20/386 using messaging services or messaging apps using mobile network messaging services for payment, e.g. SMS G06Q20/3255
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06T 2207/20132 Image cropping
• CPC Class Codes: G06T 5/40 using histogram techniques
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 10/10 Image acquisition document image scanning and transmission H04N1/00; control of digital cameras H04N23/60
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/16 Image preprocessing
• CPC Class Codes: G06V 30/18019 by matching or filtering
• 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: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
• CPC Class Codes: H04N 1/40012 : Conversion of colour to monochrome
• CPC Class Codes: H04N 23/00 : Cameras or camera modules comprising electronic image sensors; Control thereof

Abstract

The APPARATUSES, METHODS AND SYSTEMS FOR REMOTE DEPOSIT CAPTURE WITH ENHANCED IMAGE DETECTION (hereinafter “RDC-Detection”) provides a platform for remote deposit by submitting captured images of a check via a user device, wherein the RDC-Detection transforms captured check images and/or entered check deposit information inputs via RDC-Detection components into deposit confirmation outputs. For example, in one embodiment, a financial institution may receive a check image captured by a scanner, a camera, and/or the like, and process the check image to extract deposit information to process the deposit request.

Claims

1. A system comprising:

a memory;

an image capture device; and

a processor in communication with the memory and the image capture device, the processor configured to;

capture an image of a financial instrument associated with a depositor using the image capture device;

extract a rectangular financial instrument image from the captured image by determining a plurality of corners of the financial instrument in the captured image, wherein in determining the plurality of corners of the financial instrument in the captured image, the processor is further configured to;

divide the captured image into sub-images;

determine anomaly scores for each of the sub-images, the anomaly scores being indicative of an anomaly in a respective sub-image; and

determine a corner for each sub-image having an anomaly score below a predetermined anomaly threshold; and

transmit the rectangular financial instrument image to a remote financial institution server to deposit funds into an account associated with the depositor.

2. The system of claim 1, wherein the processor is configured to extract the rectangular financial instrument image by cropping the captured image based on the determined corners of the sub-images.

3. The system of claim 1, wherein the image capture device comprises one of a scanner, a digital camera, a video camera, a facsimile machine, a built-in camera of a portable device, and a built-in camera of a network device.

4. The system of claim 1, wherein the processor is further configured to:

convert the captured image of the financial instrument to a grayscale image if the captured image is a color image; and

extract the rectangular financial instrument image from the grayscale image.

5. The system of claim 1, wherein in determining the plurality of corners of the financial instrument in the captured image, the processor is further configured to:

when there are a sufficient number of determined corners, calculate a predicted corner by symmetric projection for each of the sub-images that has an anomaly score above the predetermined anomaly threshold.

6. The system of claim 5, wherein in determining the plurality of corners of the financial instrument in the captured image, the processor is further configured to:

when there are an insufficient number of determined corners, calculate an approximate corner for each of the sub-images that has an anomaly score above the predetermined anomaly threshold.

7. The system of claim 1 wherein the processor is configured to divide the captured image into four sub-images.

8. The system of claim 1 wherein the processor is configured to divide the captured image into a number of sub-images that is proportional to the size of the captured image.

9. The system of claim 1, wherein the processor is further configured to:

generate an enhanced black-white image of the captured image, wherein the processor is configured to;

divide the captured image into intermediate sub-images;

generate a histogram for each of the intermediate sub-images;

determine a grayscale threshold value for each generated histogram;

convert each intermediate sub-image into a black-white sub-image based on the grayscale threshold value determined for the respective intermediate sub-image;

combine the black-white sub-images to form the enhanced black-white image of the captured image; and

extract the rectangular financial instrument image from the enhanced black-white image of the captured image.

10. The system of claim 9, wherein in generating the enhanced black-white image of the captured image, the processor is further configured to apply a convolution filter matrix to each black-white sub-image.

11. The system of claim 9, wherein in determining the grayscale threshold value for each generated histogram, the processor is configured to perform a statistical analysis of the generated histogram.

12. The system of claim 9, wherein in determining the grayscale threshold value for each generated histogram, the processor is configured to use a minimum fuzziness threshold.

13. The system of claim 9, wherein in determining the grayscale threshold value for each generated histogram, the processor is configured to apply an Otsu algorithm.

14. The system of claim 10, wherein the convolution filter matrix is an edge-enhancing convolution filter matrix.

15. The system of claim 10, wherein the convolution filter matrix is a blurring convolution filter matrix.

16. The system of claim 1, wherein in determining anomaly scores for each of the sub-images, the processor is configured to:

generate a histogram for each of the sub-images;

determine grayscale bin values N1 and N2 based on a predetermined bin count limit;

determine a minimum bin count vale M and an average bin count value AVG within a grayscale bin value range N1+1 to N2−

1; and

calculate the anomaly score based on anomaly score=(AVG−

M)/(AVG+M).

17. The system of claim 1, wherein in determining the corner for each sub-image having an anomaly score below a predetermined anomaly threshold, the processor is configured to use at least one of a Moravec corner detection algorithm, multi-scale Harris operator, Shi and Tomasi corner detection algorithm, level curve curvature approach, LoG, DoG, and DoH feature detection, Wang and Brady corner detection algorithm, SUSAN corner detector, Trajkovic and Hedley corner detector, FAST feature detector, automatic synthesis of point detectors with Genetic Programming, or affine-adapted interest point operators.

18. A method comprising:

capturing an image of a financial instrument associated with a depositor using an image capture device;

extracting a rectangular financial instrument image from the captured image by determining a plurality of corners of the financial instrument in the captured image, wherein determining the plurality of corners of the financial instrument in the captured image further comprises;

dividing the captured image into sub-images;

determining anomaly scores for each of the sub-images, the anomaly scores being indicative of an anomaly in a respective sub-image; and

determining a corner for each sub-image having an anomaly score below a predetermined anomaly threshold; and

transmitting the rectangular financial instrument image to a remote financial institution server to deposit funds into an account associated with the depositor.

19. The method of claim 18, wherein extracting the rectangular financial instrument image from the captured image further comprises cropping the captured image based on the determined corners of the sub-images.

20. A non-transitory computer-readable medium comprising computer executable instructions that when executed cause a processor to:

capture an image of a financial instrument associated with a depositor using the image capture device;

extract a rectangular financial instrument image from the captured image by determining a plurality of corners of the financial instrument in the captured image, wherein to determine the plurality of corners of the financial instrument in the captured image, the instructions further comprise instructions to cause the processor to;

divide the captured image into sub-images;

determine anomaly scores for each of the sub-images, the anomaly scores being indicative of an anomaly in a respective sub-image; and

determine a corner for each sub-image having an anomaly score below a predetermined anomaly threshold; and

transmit the rectangular financial instrument image to a remote financial institution server to deposit funds into an account associated with the depositor.