Learning OpenCV

Some More Complicated Stuff

Everything we've discussed so far was reasonably basic. Each of the functions provided for a relatively obvious need. Collectively, they form a good foundation for much of what you might want to do with histograms in the context of computer vision (and probably in other contexts as well). At this point we want to look at some more complicated routines available within OpenCV that are extremely useful in certain applications. These routines include a more sophisticated method of comparing two histograms as well as tools for computing and/or visualizing which portions of an image contribute to a given portion of a histogram.

Earth Mover's Distance

Lighting changes can cause shifts in color values (see Figure 7-5), although such shifts tend not to change the shape of the histogram of color values, but shift the color value locations and thus cause the histogram-matching schemes we've learned about to fail. The difficulty with histogram match measures is that they can return a large difference in the case where two histograms are similarly shaped, but only displaced relative to one another. It is often desirable to have a distance measure which performs like a match, except which is less sensitive to such displacements. Earth mover's distance (EMD) [Rubner00] is such a metric; it essentially measures how much work it would take to "shovel" one histogram shape into another, including moving part (or all) of the histogram to a new location. It works in any number ...