Methods and systems for real-time image-capture feedback

• US 9,094,617 B2
• Filed: 04/01/2011
• Issued: 07/28/2015
• Est. Priority Date: 04/01/2011
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Chen, Lawrence Shao-hsien
• Primary Examiner(s): DAGNEW, MEKONNEN D
• Application Number:
  US13/078,052
• Publication Number:
  US 20120249837A1
• Time in Patent Office: 1,579 Days
• Field of Search: 348/333.01, 348/333.02, 348/333.04, 348/333.11, 348/333.12
• US Class Current: 1/1
• CPC Class Codes: H04N 1/00408 Display of information to the user, e.g. menus
• CPC Class Codes: H04N 1/00458 Sequential viewing of a plurality of images, e.g. browsing or scrolling
• CPC Class Codes: H04N 5/2625 for obtaining an image which is composed of images from a temporal image sequence, e.g. for a stroboscopic effect sequence generated by event triggered capturing H04N7/188

Abstract

Aspects of the present invention are related to systems and methods for providing real-time feed-back cues in an image acquisition process. An overlaid preview-frame image may be rendered comprising cues associated with acquisition factors. A cue may indicate whether, or not, an acquisition-factor value falls within a range of acceptable values. Image features may be extracted, from a preview-frame image, and interpreted to determine acquisition-factor values and their acceptability.

Claims

1. A method for image acquisition, said method comprising:

obtaining a preview-frame image;

extracting a first image feature from said preview-frame image, wherein said extracting said first image feature comprises;

determining a top-boundary line of a document region;

determining a bottom-boundary line of said document region;

determining a left-boundary line of said document region;

determining a right-boundary line of said document region;

determining a horizontal vanishing point;

determining a vertical vanishing point;

determining a first distance between said horizontal vanishing point and a center point associated with the center of said preview-frame image; and

determining a second distance between said vertical vanishing point and said center point;

interpreting said first image feature in relation to a first acquisition factor; and

rendering an overlaid preview-frame image comprising a first cue associated with said first acquisition feature.

2. A method as described in claim 1, wherein said first acquisition factor is a tilt factor.

3. A method as described in claim 1 further comprising:

extracting a second image feature from said preview-frame image;

interpreting said second image feature in relation to a second acquisition factor; and

rendering said overlaid preview-frame image to further comprise a second cue associated with said second acquisition feature.

4. A method as described in claim 3, wherein:

said second acquisition factor is a factor selected from the group consisting of exposure, size, contrast, camera motion and blur.

5. A method as described in claim 3 further comprising:

extracting a third image feature from said preview-frame image;

interpreting said third image feature in relation to a third acquisition factor; and

rendering said overlaid preview-frame image to further comprise a third cue associated with said third acquisition feature.

6. A method as described in claim 5, wherein:

said third acquisition factor is a factor selected from the group consisting of exposure, size, contrast, camera motion and blur; and

said third acquisition factor is not said second acquisition factor.

7. A method as described in claim 3, wherein said extracting a second image feature comprises computing an exposure metric.

8. A method as described in claim 7, wherein said interpreting said second image feature in relation to a second acquisition factor comprises:

comparing said computed exposure metric to an exposure threshold;

when said comparing meets a first criterion, rendering said second cue to indicate a satisfactory exposure value; and

when said comparing does not meet said first criterion, rendering said second cue to indicate an unsatisfactory exposure value.

9. A method as described in claim 3, wherein said extracting a second image features comprises computing a size metric.

10. A method as described in claim 9, wherein said computing a size metric comprises:

down-sampling said preview-frame image;

converting said down-sampled preview-frame image to a grayscale image;

binarizing said grayscale image;

determining a first number of pixels in said binarized image associated with a document region; and

dividing said first number of pixels by a total number of pixels in said binarized image.

11. A method as described in claim 10, wherein said interpreting said second image feature in relation to a second acquisition factor comprises:

comparing said computed size metric to a size threshold;

when said comparing meets a first criterion, rendering said second cue to indicate a satisfactory size value; and

when said comparing does not meet said first criterion, rendering said second cue to indicate an unsatisfactory size value.

12. A method as described in claim 1, wherein said interpreting said first image feature in relation to a first acquisition factor comprises:

comparing said first distance to a horizontal-distance threshold;

comparing said second distance to a vertical-distance threshold;

when said comparing said first distance to said horizontal-distance threshold meets a first criterion and said comparing said second distance to said vertical-distance threshold meets a second criterion, rendering said first cue to indicate a satisfactory tilt value; and

when said comparing said first distance to said horizontal-distance threshold does not meet a first criterion or said comparing said second distance to said vertical-distance threshold does not meet a second criterion, rendering said first cue to indicate an unsatisfactory tilt value.

13. A method as described in claim 1 further comprising:

down-sampling said preview-frame image;

converting said down-sampled preview-frame image to a grayscale image;

binarizing said grayscale image;

computing a horizontal gradient image from said binarized image;

computing a vertical gradient image from said binarized image;

labeling a plurality of vertical edges based on said horizontal gradient image and said vertical gradient image;

labeling a plurality of horizontal edges based on said horizontal gradient image and said vertical gradient image;

forming a top-boundary point set from said labeled edges;

forming a bottom-boundary point set from said labeled edges;

forming a left-boundary point set from said labeled edges;

forming a right-boundary point set from said labeled edges;

fitting a first line to said top-boundary point set, wherein said top-boundary line is said first line;

fitting a second line to said bottom-boundary point set, wherein said bottom-boundary line is said second line;

fitting a third line to said left-boundary point set, wherein said left-boundary line is said third line; and

fitting a fourth line to said right-boundary point set, wherein said left-boundary line is said fourth line.

14. A method as described in claim 13, wherein:

determining said horizontal vanishing point comprises determining the intersection of said top-boundary line and said bottom-boundary line; and

determining said vertical vanishing point comprises determining the intersection of said left-boundary line and said right-boundary line.

15. A method as described in claim 13, wherein:

said overlaid preview-frame image comprises said top-boundary line overlaid on said preview-frame image;

said overlaid preview-frame image comprises said bottom-boundary line overlaid on said preview-frame image;

said overlaid preview-frame image comprises said left-boundary line overlaid on said preview-frame image; and

said overlaid preview-frame image comprises said right-boundary line overlaid on said preview-frame image.

16. A method as described in claim 1, wherein:

determining said horizontal vanishing point comprises determining the intersection of said top-boundary line and said bottom-boundary line; and

determining said vertical vanishing point comprises determining the intersection of said left-boundary line and said right-boundary line.

17. A method as described in claim 1, wherein said first cue comprises an icon.

18. A method as described in claim 17, wherein:

said icon comprises a first color when said first cue indicates a satisfactory value; and

said icon comprises a second color when said first cue indicates an unsatisfactory value.

19. A method as described in claim 1, wherein said first cue comprises a text string.

20. A method as described in claim 19, wherein:

said text string comprises a first color when said first cue indicates a satisfactory value; and

said text string comprises a second color when said first cue indicates an unsatisfactory value.

21. A method as described in claim 1, wherein said first cue comprises an icon and a text string.

22. A method as described in claim 1, further comprising acquiring a first image when a first acquisition-factor value associated with said first acquisition factor is satisfactory.

23. A method as described in claim 1, further comprising displaying said overlaid preview-frame image on an image-acquisition device associated with said preview-frame image.

24. A method for image acquisition, said method comprising:

obtaining a preview-frame image;

extracting a plurality of image features from said preview-frame image, wherein said extracting said plurality of image feature from said preview-frame image comprises;

determining a top-boundary line of a document region;

determining a bottom-boundary line of said document region;

determining a left-boundary line of said document region;

determining a right-boundary line of said document region;

determining a horizontal vanishing point;

determining a vertical vanishing point;

determining a first distance between said horizontal vanishing point and a center point associated with the center of said preview-frame image; and

determining a second distance between said vertical vanishing point and said center point;

interpreting said plurality of image features in relation to a plurality of acquisition factors, thereby determining an acquisition-factor value for each of said acquisition factors in said plurality of acquisition factors;

determining, for each of said acquisition-factor values, if said acquisition-factor value is satisfactory;

when each of said acquisition-factor values is satisfactory, acquiring a first image; and

when, at least one of said acquisition-factor values is not satisfactory, rendering an overlaid preview-frame image comprising a plurality of cues associated with said acquisition-factor values.

25. A method as described in claim 24, further comprising displaying said overlaid preview-frame image on an image-acquisition device associated with said preview-frame image.