Systems and methods for mobile image capture and processing of documents

• US 10,558,972 B2
• Filed: 12/11/2017
• Issued: 02/11/2020
• Est. Priority Date: 01/18/2008
• Status: Active Grant

• Current Assignee: Mitek Systems Incorporated
• Original Assignee: Mitek Systems Incorporated
• Inventors: Nepomniachtchi, Grisha, Kliatskine, Vitali
• Primary Examiner(s): Motsinger, Sean T
• Application Number:
  US15/838,088
• Publication Number:
  US 20180101836A1
• Time in Patent Office: 792 Days
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• 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: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1475 Inclination or skew detection or correction of characters or of image to be recognised
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: G06V 30/166 Normalisation of pattern dimensions
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: G06V 30/42 based on the type of document
• CPC Class Codes: H04N 1/00244 with a server, e.g. an internet server fax-servers or the like for store and forward H04N1/324
• CPC Class Codes: H04N 1/00307 with a mobile telephone apparatus constructional features of portable telephone sets H04M1/0202; mobile radio systems H04W84/00
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 2201/001 Sharing resources, e.g. processing power or memory, with a connected apparatus or enhancing the capability of the still picture apparatus
• CPC Class Codes: H04N 2201/0084 Digital still camera

Abstract

Techniques for processing images of documents captured using a mobile device are provided. The images can include different sides of a document from a mobile device for an authenticated transaction. In an example implementation, a method includes inspecting the images to detect a feature associated with a first side of the document. In response to determining an image is the first side of the document, a type of content is selected to be analyze on the image of the first side and one or more of regions of interests (ROIs) are identified on the image of the first side that are known to include the selected type of content. A process can include receiving a sub-image of the image of the first side from the preprocessing unit, and performing content detection test on the sub-image.

Claims

1. A mobile device, comprising:

a preprocessing unit in the mobile device and which is configured to;

receive images of different sides of a document from a camera included in the mobile device for an authenticated transaction;

inspecting the images to detect a feature associated with a first side of the document;

in response to determining an image is the first side of the document, select a type of content to be analyze on the image of the first side;

identify a plurality of regions of interests (ROIs) on the image of the first side that are known to include the selected type of content; and

transmit a sub-image of the image of the of the first side to a testing unit, wherein the sub-image is an extracted portion smaller than the image of the first side including at least one of the identified ROIs;

the testing unit in the mobile device and which is configured to;

receive the sub-image of the image of the first side from the preprocessing unit; and

perform at least one content detection test on the sub-image which includes at least one of the identified ROIs to test the quality of the selected type of content in the image of the first side; and

a feedback unit in the mobile device and which is configured to;

generate a message to notify a user of the mobile device when the selected type of content is fails the at least one content detection test.

2. The mobile device of claim 1, wherein to inspect the images is based on a bitonal image generated from the received images.

3. The mobile device of claim 2, wherein extracted subimage is converted to a bitonal snippet.

4. The mobile device of claim 1, wherein the preprocessing unit is further configured to compute a confidence value for the sub-image.

5. The mobile device of claim 1, wherein the preprocessing unit is further configured to conduct geometric correction on the sub-image.

6. The mobile device of claim 1, the feature associated with the first side is a Magnetic Ink Character Recognition (MICR)-line is identified on the received image.

7. The mobile device of claim 1, wherein at least one ROI corresponds to an endorsement region on a first side of the document.

8. The mobile device of claim 7, wherein the selected type of content is an endorsement.

9. A method of processing a mobile-captured image of a document, comprising:

in a mobile device, running a preprocessing process comprising;

receiving images of different sides of a document from a camera included in the mobile device for an authenticated transaction;

inspecting the images to detect a feature associated with a first side of the document;

in response to determining an image is the first side of the document, select a type of content to be analyze on the image of the first side;

identify a plurality of regions of interests (ROIs) on the image of the first side that are known to include the selected type of content; and

transmitting a sub-image of the image of the of the first side to a testing process run within the mobile device, wherein the sub-image is an extracted portion smaller than the image of the first side including at least one of the identified ROIs;

the testing process comprising;

receiving the sub-image of the image of the first side from the preprocessing process; and

performing at least one content detection test on the sub-image which includes at least one of the identified ROIs to test the quality of the selected type of content in the image of the first side; and

a feedback process run within the mobile device comprising;

generating a message to notify the mobile device when the selected type of content is fails the at least one content detection test.

10. The method of claim 9, wherein inspecting the images is based on a bitonal image generated from the received images.

11. The method of claim 10, wherein extracted subimage is converted to a bitonal snippet.

12. The method of claim 9, wherein the preprocessing further computes a confidence value for the sub-image.

13. The method of claim 9, wherein the preprocessing comprises conducting geometric correction on the sub-image.

14. The method of claim 9, wherein the feature associated with the first side is a Magnetic Ink Character Recognition (MICR)-line is identified on the received image.

15. The method of claim 9, wherein at least one ROI corresponds to an endorsement region on a first side of the document, and wherein the selected type of content is an endorsement.

16. A non-transitory computer readable medium on a mobile device comprising instructions, that when executed by a processor, cause the instructions to:

perform a preprocessing process configured to;

receive images of different sides of a document from a camera included in the mobile device for an authenticated transaction;

inspecting the images to detect a feature associated with a first side of the document;

in response to determining an image is the first side of the document, select a type of content to be analyze on the image of the first side;

identify a plurality of regions of interests (ROIs) on the image of the first side that are known to include the selected type of content; and

transmit a sub-image of the image of the of the first side to a testing process, wherein the sub-image is an extracted portion smaller than the image of the first side including at least one of the identified ROIs;

the testing process configured to;

receive the sub-image of the image of the first side from the preprocessing process; and

perform at least one content detection test on the sub-image which includes at least one of the identified ROIs to test the quality of the selected type of content in the image of the first side; and

a feedback process configured to;

generate a message to notify the mobile device when the selected type of content is fails the at least one content detection test.

17. The non-transitory computer readable medium of claim 16, wherein to inspect the images is based on a bitonal image generated from the received images, and wherein extracted subimage is converted to a bitonal snippet.

18. The non-transitory computer readable medium of claim 16, wherein the preprocessing further computes a confidence value for the sub-image.

19. The non-transitory computer readable medium of claim 16, wherein the preprocessing further conducts geometric correction on the sub-image.

20. A mobile device, comprising:

a camera configured to capture images of a document;

a processor and a memory couple with the processor, the memory configured to store executable instructions that when run by the processor cause the processor to implement a preprocessing unit, a testing unit and a feedback unit, wherein;

the preprocessing unit is configured to execute algorithms stored in a ROI program database such that the preprocessing unit will;

receive images of different sides of a document from a mobile device for an authenticated transaction;

inspecting the images to detect a feature associated with a first side of the document;

in response to determining an image is the first side of the document, select a type of content to be analyze on the image of the first side;

identify a plurality of regions of interests (ROIs) on the image of the first side that are known to include the selected type of content; and

transmit a sub-image of the image of the of the first side to a testing unit, wherein the sub-image is an extracted portion smaller than the image of the first side including at least one of the identified ROIs;

the testing unit is configured to execute algorithms stored in a tests and rules database such that the testing unit will;

receive the sub-image of the image of the first side from the preprocessing unit; and

perform at least one content detection test on the sub-image which includes at least one of the identified ROIs to test the quality of the selected type of content in the image of the first side; and

the feedback unit is configured to execute algorithms stored in a feedback and rules database such that the feedback unit will;

generate a message to notify a user of the mobile device when the selected type of content is fails the at least one content detection test.

21. The mobile device of claim 20, wherein to inspect the images is based on a bitonal image generated from the received images.

22. The mobile device of claim 21, wherein extracted subimage is converted to a bitonal snippet.

23. The mobile device of claim 20, wherein the preprocessing unit is further configured to compute a confidence value for the sub-image.

24. The mobile device of claim 20, wherein the preprocessing unit is further configured to conduct geometric correction on the sub-image.

25. The mobile device of claim 20, the feature associated with the first side is a Magnetic Ink Character Recognition (MICR)-line is identified on the received image.

26. The mobile device of claim 20, wherein at least one ROI corresponds to an endorsement region on a first side of the document.

27. The mobile device of claim 26, wherein the selected type of content is an endorsement.