Identifying regions characterized by labeled measurements
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.
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.