System and method for low light document capture and binarization with multiple flash images

• US 9,807,269 B2
• Filed: 05/15/2015
• Issued: 10/31/2017
• Est. Priority Date: 08/27/2013
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Kumar, Jayant, Bala, Raja, Maltz, Martin S., Emmett, Phillip J
• Primary Examiner(s): Lee, Cheukfan
• Application Number:
  US14/713,077
• Publication Number:
  US 20160337545A1
• Time in Patent Office: 900 Days
• Field of Search: 358473, 358474, 358450, 358453, 358463, 358538, 358522, 358527, 382282, 382284, 382168
• CPC Class Codes: G06T 2207/20221 Image fusion; Image merging
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/90 Dynamic range modification of images or parts thereof
• CPC Class Codes: H04N 1/00997 Light control, e.g. shielding from ambient light or preventing light leakage
• CPC Class Codes: H04N 1/028 for picture information pick-up

Abstract

The embodiments include systems and methods for guiding a user to capture two flash images of a document page, and selectively fuse the images to produce a binary image of high quality and without loss of any content. Each individual image may have an FSR where the content is degraded/lost due to the flash light. The idea is to first guide the user to take two images such that there is no overlap of flash-spots in the document regions. The flash spots in both images are detected and assessed for quality and extent of degradation in both images. The image with lower degradation is chosen as the primary image and the other image as secondary, to minimize fusing artifacts. The region in secondary image corresponding to the FSR in the primary is aligned to the primary region using a multiscale alignment technique. The primary image and aligned FSR are binarized and fused in the vicinity of the flashspot in the primary using an intelligent technique that minimizes fusion boundary artifacts such as cutting of characters and words.

Claims

1. A method for low light image capture of a document image using a plurality of flash images from a single supplemental light source, the method comprising:

first capturing a first image of a document with the supplemental light source wherein the first image has a first flash spot in a first flash spot region;

second capturing a second image of the document with the supplemental light source wherein the second image has a second flash spot spaced from a position in the document of the first flash spot by a movement of the supplemental light source from a first position to a second position; and

fusing the first and second images for an alignment of the first and second images to form a fused image, wherein the first flash spot region is replaced in the fused image with a corresponding portion of the second image wherein a boundary of the corresponding portion of the second image is selectively expanded to avoid splitting of characters and words by the fusing.

2. The method of claim 1 wherein the first and second capturing includes guiding the capturing to suggest a sufficient spacing of the first flash spot from the second flash spot.

3. The method of claim 2 wherein the guiding includes translating, rotating or augmented reality spacing of the first and second capturings, respectively.

4. The method of claim 3 wherein the guiding further includes previewing a preview display disposed to suggest the sufficient spacing.

5. The method of claim 1 further including detecting a first flash spot region and a second flash spot regions corresponding to the first and second flash spots, respectively, and assessing image degradation in the first flash spot region and a second flash spot region.

6. The method of claim 5 wherein the assessing includes determining the first image as a one of the first and second images having a lower image degradation;

and the second image as having a higher image degradation.

7. The method of claim 6 wherein the fusing includes aligning a portion of the second image, corresponding to the flash spot region of the first image, with the first image.

8. The method of claim 7 wherein the aligning includes using a multi-scale alignment.

9. The method of claim 8 further including binarizing and fusing the first image and the aligned portion of the second image in an image area of the flash spot region of the first image.

10. A low light image capture system for capturing a document image using a plurality of flash images, the system comprising:

a capture device including a single supplemental light source for first capturing a first image of a document wherein the first image has a first flash spot in a first flash spot region, and for second capturing a second image of the document with the supplemental light source upon a movement of the supplemental light source from a first position to a second position wherein the second image has a second flash spot spaced from a position in the document of the first flash spot; and

a processor for fusing the first and second images for an alignment of the first and second images to form a fused image, wherein the first flash spot region is replaced in the fused image with a corresponding portion of the second image and wherein a boundary of the second image is selectively expanded to avoid splitting of characters and words by the fusing.

11. The system of claim 10 wherein the capture device includes a guide to suggest a sufficient spacing of the first flash spot from the second flash spot.

12. The system of claim 11 wherein the guide includes a user assist for translating, rotating or augmented reality spacing of the first and second capturings, respectively.

13. The system of claim 12 wherein the guide comprises a preview display disposed to suggest the sufficient spacing.

14. The system of claim 10 wherein the processor detects a first flash spot region and a second flash spot region corresponding to the first and second flash spots, respectively, and assesses image degradation in the first flash spot region and a second flash spot region.

15. The system of claim 14 wherein the processor assessing includes determining the first image as a one of the first and second images having a lower image degradation, and the second image as having a higher image degradation.

16. The system of claim 15 wherein the processor fusing includes aligning a portion of the second image, corresponding to the flash spot region of the first image, with the first image.

17. The system of claim 16 wherein the processor aligning includes using a multi-scale alignment.

18. The system of claim 17 wherein the processor aligning further includes binarizing for fusing the first image and the aligned portion of the second image in an image area of the flash spot region of the first image.