Calculated histogram equalization and MATLAB implementation

Histogram equalization, there is no written formula, just look at how to count

A. Histogram equalization hand count

For example, a matrix
\ [active matrix = \ left [\ begin {matrix
} 4 & 4 & 4 & 4 & 4 & 4 & 4 & 0 \\ 4 & 5 & 5 & 5 & 5 & 5 & 4 & 0 \\ 4 & 5 & 6 & 6 & 6 & 5 & 4 & 0 \\ 4 & 5 & 6 & 7 & 6 & 5 & 4 & 0 \\ 4 & 5 & 6 & 6 & 6 & 5 & 4 & 0 \\ 4 & 5 & 5 & 5 & 5 & 5 & 4 & 0 \\ 4 & 4 & 4 & 4 & 4 & 4 & 4 & 0 \\ 4 & 4 & 4 & 4 & 4 & 4 & 4 & 0 \\ \ end {matrix} \ right] \] meaning of the questions or matrix analysis, matrix gray value range is [0,7]
now, the number of gradation values statistical calculation, probability, cumulative probability

Gradation values mapped calculated difference * = the maximum tone value of the current cumulative probability
due to the gradation value is positive, the final to rounding

grayscale value Quantity Probability Cumulative probability Gradation values ​​mapped ToSei
P(h=0) 8 0.125 0.125 7*0.125=0.875 1
P(h=1) 0 0 0.125 7*0.125=0.875 1
P(h=2) 0 0 0.125 7*0.125=0.875 1
P(h=3) 0 0 0.125 7*0.125=0.875 1
P(h=4) 31 0.484375 0.609375 7*0.609375=0.4.265625 4
P(h=5) 16 0.25 0.859375 7*0.859375=6.015625 6
P(h=6) 8 0.125 0.984375 7*0.125=6.890625 7
P(h=7) 1 0.015625 1 7*1=7 7

\[直方图均衡化后= \left[ \begin{matrix} 4&4&4&4&4&4&4&1\\ 4&6&6&6&6&6&4&1\\ 4&6&7&7&7&6&4&1\\ 4&6&7&7&7&6&4&1\\ 4&6&7&7&7&6&4&1\\ 4&6&6&6&6&6&4&1\\ 4&4&4&4&4&4&4&1\\ 4&4&4&4&4&4&4&1\\ \end{matrix} \right] \]

Two .matlab histogram equalization

method one

  • histeq (mat): matrix histogram equalization
  • hist (mat): histogram display matrix
  • imhist (mat): histogram display matrix

    For hist and differences imhist not currently know, just when the custom with imhist small matrix display histogram is not successful, success can be displayed with hist

Method Two

  • imadjust(img,[low_in,high_in],[low_out,high_out],gamma)
  • - [low_in, high_in]: need to expand the range of the normalized value, i.e. [0,1]
  • - [low_out, high_out]: to extend the range, ibid
  • -gamma: mapping method (coefficient)

    <1 brighter;
    1: darken;
    = 1] Default);

Guess you like

Origin www.cnblogs.com/thgpddl/p/12523173.html