Normalize a Histogram in MATLAB

A histogram is nothing but a graphical representation that shows the distribution of a set of data points. The normalization of a histogram is a process of distributing its frequencies over a wide range.

Before discussing the implementation of histogram normalization in MATLAB, let us first get an overview of histogram normalization.

What is Histogram Normalization?

A histogram is a graphical way of representing the distribution of frequencies of a dataset. Sometimes, we see a histogram in which the frequencies are distributed in a small range. It results in producing poor contrast in a digital image.

• There is a technique called "histogram normalization" that is used to distribute the frequencies of datasets over a wide range.

• In digital image processing, histogram normalization is used to improve the contrast levels in an image.

Mathematically, the histogram normalization is performed using the following formula,

$$\mathrm{Hist. Norm=\frac{(Intensity Min value)}{(Max \:Value Min \:Value)}&times 255}$$

Now, let us discuss the process of histogram normalization in MATLAB.

Histogram Normalization in MATLAB

In MATLAB, the normalization of a histogram is performed as per the following steps

• Step (1) Read the digital image whose histogram is to be normalized. For this, use the "imread" function.

• Step (2) Convert the input image to gray scale if required. For this, use the "rgb2gray" function.

• Step (3) Convert the grayscale image to double data type for calculations. For this, use the "double" function.

• Step (4) Specify the minimum and maximum values required for histogram normalization.

• Step (5) Use the histogram normalization formula to perform the normalization of the histogram.

• Step (6) Display the result.

Example

Let us take an example to understand the implementation and execution of these steps to perform histogram normalization of an image.

% MATLAB code to perform histogram normalization
% Read the input image
img = imread('https://www.tutorialspoint.com/assets/questions/media/14304-1687425269.jpg');

% Convert the input image to grayscale
gray_img = rgb2gray(img);

% Convert the grayscale image to double datatype
double_img = double(gray_img);

% Specify the minimum and maximum values for histogram normalization
min_value = 50;
max_value = 170;

% Perform histogram normalization
norm_img = (double_img - min_value) / (max_value - min_value);

% Scale the normalized image
scaled_img = norm_img * 255;

% Convert the scaled image to uint8 to display
hist_norm_img = uint8(scaled_img);

% Display the input image, normalized image, and their histograms
figure;
subplot(2, 2, 1);
imshow(gray_img);
title('Input Image');

subplot(2, 2, 2);
imhist(gray_img);
title('Input Image Histogram');

subplot(2, 2, 3);
imshow(hist_norm_img);
title('Normalized Image');

subplot(2, 2, 4);
imhist(hist_norm_img);
title('Normalized Histogram');

Output

When you run this code, it will produce the following output

Conclusion

In conclusion, the histogram normalization is a technique of distributing the frequencies of a dataset over a wide range to improve contrast levels. In this tutorial, I explained the stepbystep process of histogram normalization of an image with the help of an example in MATLAB.