Identifying regions characterized by labeled measurements

• US 9,235,890 B2
• Filed: 03/15/2013
• Issued: 01/12/2016
• 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
• Primary Examiner(s): Liu, Li
• Application Number:
  US13/844,760
• Publication Number:
  US 20140270522A1
• Time in Patent Office: 1,033 Days
• Field of Search: None
• US Class Current: 1/1
• 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. In one or more non-limiting embodiments purely for illustrative purposes, relatively fine details of labeled measurements may be displayed utilizing a relatively low-scale map, such as a map showing individual towns and/or villages. For display utilizing a relatively higher scale map, such as a map showing larger geopolitical areas, for example, relatively fine details may be omitted.

Claims

1. A method comprising:

smoothing one or more two-dimensional histograms comprising a set of labeled measurements to form one or more regions, the smoothing being performed at a variety of scale levels, the smoothing being increased responsive to a command from a user interface to decrease resolution of a displayed map, the smoothing being decreased responsive to a command from the user interface to increase resolution of the displayed map.

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

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

using an image processing technique to assist in forming at least one region boundary, the 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 the identifying label region boundaries comprises identifying sub-regions characterized by conforming labels of the set of labeled measurements.

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

6. The method of claim 1, wherein the smoothing of a set of labeled measurements comprises identifying iso-contours of the one or more regions at the variety of scale levels.

7. The method of claim 6, wherein the identifying iso-contours at the variety of scale levels is at least partially in response to constructing the one or more two-dimensional histograms from the set of labeled measurements.

8. The method of claim 7, wherein the identifying iso-contours is at least partially in response to subtracting a first of the one or more two-dimensional of histograms from a second of the one or more two-dimensional histograms.

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

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

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

11. The method of claim 10, wherein using the spatial bandpass filter comprises scaling the set of labeled measurements from a current to a different level in response to receiving the command from the user interface to increase resolution of the displayed map.

12. An article comprising:

a non-transitory storage medium storing instructions executable by a special purpose computing apparatus to;

smooth one or more two-dimensional histograms to comprise a set of labeled measurements to form one or more regions, in which region resolution is increased responsive to a command from a user interface to increase resolution of a displayed map, or in which region resolution is decreased responsive to a command from the user interface to decrease resolution of the displayed map.

13. The article of claim 12, wherein the non-transitory storage medium additionally stores instructions executable by the special purpose computing apparatus to:

identify iso-contours at a variety of scale levels.

14. The article of claim 13, wherein the non-transitory storage medium additionally stores instructions executable by the special purpose computing apparatus to:

construct one or more two-dimensional histograms from the set of labeled measurements.

15. The article of claim 13, wherein the non-transitory storage medium additionally stores instructions executable by the special purpose computing apparatus to:

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

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

16. The article of claim 13, wherein the non-transitory storage medium additionally stores instructions executable by the special purpose computing apparatus to:

identify label region boundaries to further identify sub-regions characterized by conforming labels of the labeled measurements.