IDENTIFYING REGIONS CHARACTERIZED BY LABELED MEASUREMENTS

• US 20140270522A1
• Filed: 03/15/2013
• Published: 09/18/2014
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Rae, Adam, Thomee, Bart
• Granted Patent: US 9,235,890 B2
• Time in Patent Office: Days
• US Class Current: 382/168
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30181 Earth observation
• CPC Class Codes: G06T 3/4038 Image mosaicing, e.g. composing plane images from plane sub-images
• CPC Class Codes: G06T 5/40 using histogram techniques
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• 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

Abstract

Briefly, the disclosure describes embodiments of methods or apparatuses for processing, such as smoothing, a set of labeled measurements at a variety of scale levels.

Claims

1. A method comprising:

smoothing a set of labeled measurements at a variety of scale levels and in a manner at least approximately consistent with said measurement labels across said variety of scale levels.

2. The method of claim 1, wherein said smoothing a set of labeled measurements comprises identifying label region boundaries at said variety of scale levels.

3. The method of claim 2, wherein said smoothing comprises:

using an image processing technique to assist in forming at least one region boundary, said image processing technique comprising one or more of the following;

filling, closing, contour tracing, dilation, erosion, or any combination thereof.

4. The method of claim 2, wherein said identifying label region boundaries comprises identifying sub-regions characterized by conforming labels of said labeled measurements.

5. The method of claim 4, wherein said identifying label region boundaries comprises identifying sub-regions characterized by prominent labels of said labeled measurements.

6. The method of claim 1, wherein said smoothing of a set of labeled measurements comprises identifying iso-contours at said variety of scale levels.

7. The method of claim 6, wherein said identifying iso-contours at said variety of scale levels is at least partially in response to constructing a plurality of histograms from said set of labeled measurements.

8. The method of claim 7, wherein said identifying iso-contours is at least partially in response to subtracting a first of said plurality of histograms from a second of said plurality of histograms

9. The method of claim 1, wherein said smoothing comprises:

using a Gaussian function having a kernel size consistent with said set of labeled measurements at said variety of scale levels.

10. The method of claim 9, wherein said smoothing comprises using a spatial bandpass filter to filter spatial frequencies between at least two scale levels of said variety of scale levels.

11. The method of claim 10, wherein using said spatial bandpass filter comprises scaling said set of label measurements from a current to a different level in response to receiving a zoom command from a user interface.

12. An apparatus, comprising:

one or more processing units to;

construct a variety of histograms from a set of labeled measurements at a corresponding variety of scale levels; and

smooth at least some of said histograms in a manner at least approximately consistent with said measurement labels across said corresponding variety of scale levels.

13. The apparatus of claim 12, wherein said one or more processing units additionally to:

identify label region boundaries at said variety of scale levels.

14. The apparatus of claim 13, wherein said one or more processing units is additionally to:

employ an image processing technique to assist in forming at least one region boundary, said image processing technique comprising one or more of the following;

filling, closing, contour tracing, dilation, erosion, or any combination thereof.

15. The apparatus of claim 13, wherein said one or more processing units to:

identify label region boundaries comprises to additionally identify sub-regions characterized by conforming labels of said labeled measurements.

16. An article comprising:

a non-transitory storage medium comprising machine-readable instructions stored thereon which are executable by a special purpose computing apparatus to;

smooth a set of labeled measurements at least approximately consistently across a variety of scale levels.

17. The article of claim 16, wherein said non-transitory storage medium additionally comprises machine-readable instructions stored thereon which are executable by said special purpose computing apparatus to:

identify iso-contours at said variety of scale levels.

18. The article of claim 17, wherein said non-transitory storage medium additionally comprises machine-readable instructions stored thereon which are executable by said special purpose computing apparatus to:

construct a plurality of histograms from said set of labeled measurements.

19. The article of claim 17, wherein said non-transitory storage medium additionally comprises machine-readable instructions stored thereon which are executable by said special purpose computing apparatus to:

use a Gaussian function having a first kernel size with said set of labeled measurements at a first of said variety of scale levels; and

use a Gaussian function having a second kernel size with said set of labeled measurements at a second of said variety of scale levels.

20. The article of claim 17, wherein said non-transitory storage medium additionally comprises machine-readable instructions stored thereon which are executable by said special purpose computing apparatus to:

identify label region boundaries wherein identifying of sub-regions is characterized by conforming labels of said labeled measurements.