How to Normalize a Histogram in MATLAB?

Last Updated : 8 Dec, 2021

Histogram normalization is a technique to distribute the frequencies of the histogram over a wider range than the current range. This technique is used in image processing too. There we do histogram normalization for enhancing the contrast of poor contrasted images. 

Formula:

 New intensity= ((Intensity - minimum)                /(maximum-minimum))                *255;      

Here ./ and .* means operation has to be performed element-wise.

Steps:

  • Read the image.
  • Convert color image into grayscale.
  • Display histogram.
  • Observe maximum and minimum intensities from the histogram.
  • Change image type from uint8 to double.
  • Apply a formula for histogram normalization.
  • Convert back into unit format.
  • Display image and modified histogram.

Example: 

Matlab 
% MATLAB code for 
% Histogram normalisation.
% Read the image.
k=imread("lincoln.jfif");

% Convert into grayscale
k1=rgb2gray(k);

% Display the image and histogram.
imtool(k1,[]);
imhist(k1);

% Set the minimum and maximum
% Values from histogram.
min=45;
max=180;

% Convert image into double.
k2=double(k1);

% Apply the formula.
k3=(k2-min)./(max-min);

% Multiply with maximum possible value.
k4=k3.*255;

% Convert the final result into uint8.
k5=uint8(k4);

% Display the enhanced image and histogram.
imtool(k5,[]);
imhist(k5);

Output:

Figure: Original histogram
Figure: Normalized histogram
Figure: Images before and after normalization

Code Explanation: 

  • First, we read the image using imread( ) function.
  • After reading the image, we convert it into the grayscale format.
  • After converting it into grayscale, we displayed the image and its histogram.
  • Maximum and minimum intensity is noted from the histogram.
  • The image data type is changed from uint8 to double, to facilitate the calculation steps.
  • Apply the formula of normalization.
  • The image data type is changed back to uint8.
Comment

Explore