HistConnect

Smooth histograms for sparse sampled signals and images, using low-frequency assumption.

This Function HistConnect will make a smooth histogram for a signal or image consisting of a few samples. The function assumes correlation between the samples, and implicitly generates new linear-interpolated samples between the originate samples. Thus makes the assumption of continuity between samples and low-frequency signal.

note : If your samples are spatial uncorrelated, use X=sort(X) before using this function

H=HistConnect(X,B,R)

X : A 1D vector or 2D matrix (image) with sample values
B : The number of histogram bins (default 256)
R : A vector [1 x 2], with the min and max histogram boundary,
(default R=getrangefromclass(X))

Example how it works,
- You want 3 bins
- Measured samples [0 0.3 0.7 1]
- Histogram edges [0 1/3] [1/3 2/3] [2/3 1];
A normal histogram function will return:
H= [2 0 2]

This histogram function makes histogram-blocks between two
values in the sample vector
sample value 0 connect with 0.3 : [1.33 0.00 0.00]
sample value 0.3 connect with 0.7 : [0.11 1.11 0.11]
sample value 0.7 connect with 1.0 : [0.00 0.00 1.33]
---------------------
H = [1.44 1.11 1.44]