Processing methods combining multiple frames of image data

• US 7,346,184 B1
• Filed: 05/02/2000
• Issued: 03/18/2008
• Est. Priority Date: 05/02/2000
• Status: Expired due to Term

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Bradley, Brett Alan, Rhoads, Geoffrey B., Carr, J. Scott
• Primary Examiner(s): Bella; Matthew C.
• Assistant Examiner(s): Lu; Tom Y.
• Application Number:
  US09/563,663
• Time in Patent Office: 2,877 Days
• Field of Search: 382/100, 382/232, 382/284, 380/51
• US Class Current: 382/100
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1448 based on markings or identifiers characterising the document or the area
• CPC Class Codes: G07D 7/0047 using checkcodes, e.g. coded numbers derived from serial number and denomination
• CPC Class Codes: G07D 7/005 Testing security markings invisible to the naked eye, e.g. verifying thickened lines or unobtrusive markings or alterations

Abstract

A document authentication station, for use with passports or the like, includes a 2D image sensor (e.g., CCD- or CMOS-based video camera), and a computer device. The image sensor produces produce image data corresponding to a presented document. From this image data, the computer extracts two or more identification data. One is a digital watermark. The other can be a bar code, data glyphs, OCR data, etc. The processor then proceeds to check that the two identification data correspond in an expected fashion. If not, the document is flagged as suspect or fake. Reliability of detection may be enhanced by processing plural frames of data from the image sensor before issuing a result.

Claims

1. A method for checking an identity document comprising:

(a) capturing a frame of image data corresponding to an identity document;

(b) capturing another frame of image data corresponding to said identity document;

(c) combining data from the captured frames, including less than the entirety of one of the captured frames, to yield a composite frame;

(d) checking the composite frame to determine if it is suitable for decoding for information;

(e) if so, decoding information from said composite frame; and

(f) if not, repeating (b), (c), (d) and—

if appropriate—

(e);

wherein part of one of said captured frames is not combined due to being out of focus.

2. A method for checking an identity document comprising:

(a) capturing a frame of image data corresponding to an identity document;

(b) capturing another frame of image data corresponding to said identity document;

(c) combining data from the captured frames, including less than the entirety of one of the captured frames, to yield a composite frame;

(d) checking the composite frame to determine if it is suitable for decoding for information;

(e) if so, decoding information from said composite frame; and

(f) if not, repeating (b), (c), (d) and—

if appropriate—

(e);

wherein part of one of said captured frames is not combined due to having glare.

3. A method for checking an identity document comprising:

(a) capturing a frame of image data corresponding to an identity document;

(b) capturing another frame of image data corresponding to said identity document;

(c) combining data from the captured frames to yield a composite frame;

(d) checking the composite frame to determine if it is suitable for decoding for information;

(e) if so, decoding information from said composite frame; and

(f) if not, repeating (b), (c), (d) and—

if appropriate—

(e);

wherein the method further includes decoding first and second machine readable data from said composite image frame, and checking said first and second data for expected correspondence, and wherein one of said machine readable data comprises digital watermark data.

4. A method for checking an identity document comprising:

capturing plural frames of image data corresponding to an identity document;

compositing a first portion of one of said frames with a different portion of another of said frames;

decoding first and second machine readable data from said composition; and

checking said first and second data for expected correspondence;

wherein one of said machine readable data comprises digital watermark data.

5. A method for decoding a machine-readable identifier from image data, comprising:

at a first time, capturing a first frame of image data from a subject;

at a second, subsequent, time, capturing a second frame of image data from said subject;

identifying a region in the first frame that is relatively more reliable for decoding of said identifier than another region thereof;

identifying a region in the second frame that is relatively more reliable for decoding of said identifier than another region thereof;

combining image data from the reliable region in the first frame with image data from the reliable region in the second frame; and

decoding a machine-readable identifier from said combined image data.

6. The method of claim 5 wherein the identifier comprises a steganographic watermark that includes unknown payload bits and known reference bits, and said identifying comprises checking regions in said first and second frames to determine if the known reference bits can be reliably decoded therefrom.

7. A method comprising the acts:

acquiring a first image of a subject at a first time;

acquiring a second image of the same subject at a second, later, time;

identifying a region in one of said first or second images suffering from glare;

identifying a corresponding region in the other of said first or second images, said corresponding region not suffering from glare;

assembling a composite image from said first and second images, wherein said identified region suffering from glare is omitted in the composite image, and the corresponding region not suffering from glare is included in the composite image;

wherein the composite image depicts a person'"'"'s face, and the method further includes deriving information from the composite image to identify the person whose face is depicted.

8. The method of claim 7 in which the deriving comprises recognizing features in the composite image.

9. The method of claim 8 in which the deriving comprises recognizing OCR text in the composite image.

10. The method of claim 7 that further includes querying a database using said derived information, to obtain additional information relating to said person.

11. The method of claim 7 that further includes comparing said derived information against other information, obtained from a database record, to determine if the derived and obtained information match.

12. The method of claim 7 wherein said subject comprises an identification document.

13. A method comprising the acts:

acquiring a first image of a subject at a first time;

acquiring a second image of the same subject at a second, later, time;

identifying a region in one of said first or second images suffering from glare;

identifying a corresponding region in the other of said first or second images, said corresponding region not suffering from glare;

assembling a composite image from said first and second images, wherein said identified region suffering from glare is omitted in the composite image, and the corresponding region not suffering from glare is included in the composite image;

wherein said composite image comprises first data representing pixels depicting a person'"'"'s face, and the method further includes applying an automated recognition process to said composite image to generate second data therefrom, and querying a database using said second data.

14. The method of claim 13 wherein said second data does not represent pixels.

15. The method of claim 13 wherein said automated recognition process comprises an optical character recognition process.

16. The method of claim 13 wherein said subject comprises an identification document.