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

• US 9,129,340 B1
• Filed: 12/30/2010
• Issued: 09/08/2015
• Est. Priority Date: 06/08/2010
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Medina, Reynaldo III, Prasad, Bharat
• Primary Examiner(s): Wong, Eric T
• Application Number:
  US12/982,494
• Time in Patent Office: 1,713 Days
• Field of Search: 705 35- 45
• US Class Current: 1/1
• 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 financial instrument image enhancement method for remote deposit implemented in a financial service computer system having a processor and a memory in communication with the processor, the method comprising:

receiving a request at the processor to deposit a financial instrument from a portable device associated with a depositor, the portable device remotely located from the financial service computer system and in communication with an image capture device;

the processor establishing a secure communications channel to the portable device using depositor identifying information;

the processor transmitting a remote deposit component to the portable device via the secure communications channel, where the remote deposit component is used by the portable device to control the image capture device;

the processor receiving an image of the financial instrument from the portable device via the secure communications channel;

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

dividing the image of the financial instrument image into sub-images;

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

determining the plurality of corners based on the anomaly scores;

the processor extracting deposit information from the rectangular financial instrument image; and

the processor depositing funds as indicated by the financial instrument based on the extracted deposit information.

2. The method of claim 1, where extracting the rectangular financial instrument image comprises the processor:

cropping the received image of the financial instrument based on the corners of the financial instrument in the received image.

3. The method of claim 1, wherein transmitting a remote deposit component to the portable device comprises the processor:

transmitting an image capture component to the portable device, wherein the portable device is disposed in communication with the image capture device, wherein the image capture component is configured to;

control the image capture device,

allow the depositor to capture the image of the financial instrument, and

send the image of the financial instrument across the secure communications channel.

4. The method of claim 3, further comprising the processor:

determining whether the image capture device is controllable by the remote deposit component;

in response to determining that the image capture device is not controllable by the remote deposit component, instructing the depositor via a user interface to;

obtain and save the image of the financial instrument from the image capture device via the user interface, and

send the image of the financial instrument to the receiving financial institution; and

in response to determining that the image capture device is controllable by the remote deposit component, controlling the image capture device to capture the image of the financial instrument.

5. The method of claim 1, wherein the image capture device comprises one of a scanner, a digital camera, a video camera, a facsimile machine, a mobile device with a built-in camera and a network device with a built-in camera.

6. The method of claim 1, further comprising the processor:

determining whether the image of the financial instrument satisfies usability and quality requirements, wherein the usability and quality requirements comprise a resolution requirement and an image format requirement.

7. The method of claim 6, further comprising the processor:

compressing the image of the financial instrument if a size of the image exceeds an image size limit.

8. The method of claim 7, wherein the image size limit is based on a format of the image file.

9. The method of claim 1, further comprising the processor:

converting the image of the financial instrument to a grayscale image if the image of the financial instrument is a color image.

10. The method of claim 1, wherein determining the plurality of corners of the financial instrument in the received image comprises the processor:

generating an enhanced black-white image of the financial instrument;

determining a likelihood of corner reflection of each corner of the enhanced black-white image of the financial instrument;

detecting at least one corner; and

determining a corner with reflection by symmetric projection based on the determined at least one corner.

11. The method of claim 10, wherein generating an enhanced black-white image of the financial instrument comprises the processor:

determining a number of sub-images of the image of the financial instrument;

generating a histogram for each determined sub-image;

determining a grayscale threshold value for the generated histogram for each sub-image;

converting each determined sub-image into a black-white only image based on the determined grayscale threshold value associated with each sub-image; and

applying a convolution filter matrix to each black-white sub-image.

12. The method of claim 11, wherein the determined grayscale threshold for each sub-image is a minimum fuzziness threshold.

13. The method of claim 11, wherein the determined grayscale threshold for a sub-image is based at least in part on statistical analysis of the histogram for the sub-Image.

14. The method of claim 11, wherein the convolution filter matrix is an edge-enhancing convolution filter matrix.

15. The method of claim 10, wherein determining the likelihood of corner reflection of each corner of the enhanced black-white image of the financial instrument comprises the processor:

dividing the enhanced black-white image into four quadrants;

calculating a reflection score for each corner associated with each quadrant; and

determining whether a corner associated with a quadrant has a tolerable reflection level by comparing the reflection score associated with the corner with a predetermined reflection threshold.

16. The method of claim 15, wherein calculating a reflection score for each corner associated with each quadrant comprises the processor:

generating a histogram for each quadrant;

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

determining 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

calculating the reflection score based on reflection score=(AVG−

M)/(AVG+M).

17. The method of claim 10, further comprising the processor detecting edges of the financial instrument on the enhanced black-white image, wherein the edge detection may adopt any of 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, and affine-adapted interest point operators.

19. The method of claim 1, wherein the anomaly score is indicative of one of reflections or lighting condition anomalies.

20. The method of claim 1, wherein, in response to determining that the anomaly score for a respective sub-image is greater than a predetermined score, the processor is configured to detect a corner in the respective sub-image;

and

wherein, in response to determining that the anomaly score for a respective sub-image is less than the predetermined score, the processor is configured to determine a corner in the respective sub-image based on symmetric projection of a detected corner of the respective sub-image.

18. A financial instrument image enhancement non-transitory processor-readable medium for remote deposit, storing a plurality of processing instructions, comprising issuable instructions by a processor to:

receive a request to deposit a financial instrument from a portable device associated with a depositor, the portable device remotely located from the processor and in communication with an image capture device;

establish a secure communications channel to the portable device;

transmit a remote deposit component to the portable device via the secure communications channel, where the remote deposit component is used by the portable device to control the image capture device;

receive an image of the financial instrument from the portable device via the secure communications channel;

extract a rectangular financial instrument image from the image of the financial instrument by determining a plurality of corners of the financial instrument in the received image, wherein determining the plurality of corners of the financial instrument in the received image comprises;

dividing the image of the financial instrument image into sub-images;

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

determining the plurality of corners based on the anomaly scores;

extract deposit information from the rectangular financial instrument image; and

deposit funds as indicated by the financial instrument based on the extracted deposit information.

21. A financial instrument image enhancement system for remote deposit, comprising:

means for receiving a request to deposit a financial instrument from a portable device associated with a depositor, the portable device remotely located from the financial instrument image enhancement system and in communication with an image capture device;

means for establishing a secure communications channel to the portable device using depositor identifying information;

means for transmitting a remote deposit component to the portable device via the secure communications channel, where the remote deposit component is used by the portable device to control the image capture device;

means for receiving an image of the financial instrument from a portable device via the secure communications channel;

means for extracting a rectangular financial instrument image from the image of the financial instrument by determining a plurality of corners of the financial instrument in the received image, wherein determining the plurality of corners of the financial instrument in the received image comprises;

dividing the image of the financial instrument image into sub-images;

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

determining the plurality of corners based on the anomaly scores;

wherein, in response to determining that the anomaly score for a respective sub-image is greater than a predetermined score, the processor is configured to detect a corner in the respective sub-image; and

wherein, in response to determining that the anomaly score for a respective sub-image is less than the predetermined score, the processor is configured to determine a corner in the respective sub-image based on symmetric projection of a detected corner of the respective sub-image;

means for extracting deposit information from the rectangular financial instrument image; and

means for depositing funds as indicated by the financial instrument based on the extracted deposit information.

22. A financial instrument image enhancement apparatus for remote deposit, comprising:

a memory;

a processor disposed in communication with said memory, and configured to issue a plurality of processing instructions stored in the memory, wherein the processor issues instructions to;

receive a request at the processor to deposit a financial instrument from a portable device associated with a depositor, the portable device remotely located from the financial instrument image enhancement apparatus and in communication with an image capture device;

establish a secure communications channel to the portable device using depositor identifying information;

transmit a remote deposit component to the portable device via the secure communications channel, where the remote deposit component is used by the portable device to control the image capture device;

receive an image of the financial instrument from a portable device via the secure communications channel;

extract a rectangular financial instrument image by determining a plurality of corners of the financial instrument in the received image wherein determining the plurality of corners of the financial instrument in the received image comprises;

dividing the image of the financial instrument image into sub-images;

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

determining the plurality of corners based on the anomaly scores;

extract deposit information from the rectangular financial instrument image; and

deposit funds as indicated by the financial instrument based on the extracted deposit information.