简体   繁体   中英

The effect of image arithmetic on histograms

There are two images f(x,y) and g(x,y) and their histograms hf and hg .

If I do image arithmetic and name the result z(x,y) and its histogram hz , how can I determine hz as a function of hf and hg ?

As far as I have found :

z(x,y)=f(x,y)+g(x,y) => hz = hf *(convolution) hg (it needs to be scaled)

How about the other arithmetic calculations? How can I determine it on Matlab?

The short answer is you cannot. The histogram hz of a combined image

z(x,y)=f(x,y)+g(x,y)

cannot be uniquely determined from the histograms hf and hg of the individual images.

Example why not:

Suppose f is binary and zero whereever g (also binary) is one. The combined histogram will most likely have a smaller variance than the single histograms. If however now the pixels in g are rearranged so that its histogram hg stays the same but correlation between f and g is maximal then the variance of the combined histogram will be larger.

The result depends on the exact images f(x,y) and g(x,y) and the histograms alone do not contain enough information.

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM