Sei sulla pagina 1di 4

Pemrosesan Citra Page 1 of 4

Copyright JTEUS, 2005 D:\My Documents\JTEUS\Citra\BookOrg\Modul1 Hist\Modul1.doc


By Nemuel Daniel Pah 14/11/05
Module 1
Image Histogram & Black-white conversion

Class
Image enhancement/Restoration

Description
Image histogram is the distribution graph of gray level pixels in an image. It
provides graphical representation of how many pixels within an image fall into
the various gray-level steps.


image of F16


there are about 1700 pixels in lena.jpg with intensity 100


Histogram of the image

Threshold value
Pemrosesan Citra Page 2 of 4
Copyright JTEUS, 2005 D:\My Documents\JTEUS\Citra\BookOrg\Modul1 Hist\Modul1.doc
By Nemuel Daniel Pah 14/11/05
Image Histogram
1 1 1 1 5 1 1 1
1 1 1 1 1 1 1 1
1 1 5 1 1 1 5 1
1 1 1 1 1 1 1 1
1 1 22 22 22 1 1 1
1 1 22 22 22 1 1 1
1 1 22 22 22 1 5 1
1 1 1 1 1 1 1 1
1 1 1 5 1 5 1 1
1 5 1 1 1 1 1 1


The normal histogram has at least two humps representing bright objects in
the image and dark objects. The valley between the two humps is the
threshold value between dark and bright object. The threshold in the F16
histogram happens at gray level 90.

A gray level image can be converted to black & white image by setting all
pixels with gray level above threshold to white and all pixels with values below
threshold to black.

Application
Image segmentation. Segmenting objects in an image.


Implementation (black-white conversion)
Calculate histogram of gray level image.
Locate the valley between two main humps to define threshold gray
level.
Set
Image(x,y) = 255 if Image(x,y) > threshold

Image(x,y) = 0 if Image(x,y) < threshold

In binary image (black & white), white pixels are represented by 1
while black pixels by 0.



1 5 22 .. 255
7
9
64
Pemrosesan Citra Page 3 of 4
Copyright JTEUS, 2005 D:\My Documents\JTEUS\Citra\BookOrg\Modul1 Hist\Modul1.doc
By Nemuel Daniel Pah 14/11/05

The black &white image of F16 with threshold = 90


Matlab Script
The above histogram and black & white conversion was created using the
following script:

A=imread('f16.jpg','jpg');

figure(1);
imshow(A);

figure(2);
imhist(A);
axis([0 255 0 2000]);

Ad=double(A);

[y,x]=size(Ad);

for Y=1:y,
for X=1:x,
if Ad(Y,X)>90,
ImOut(Y,X)=1;
else
ImOut(Y,X)=0;
end
end
end

ImOut=logical(ImOut);

figure(3);
imshow(ImOut);






Pemrosesan Citra Page 4 of 4
Copyright JTEUS, 2005 D:\My Documents\JTEUS\Citra\BookOrg\Modul1 Hist\Modul1.doc
By Nemuel Daniel Pah 14/11/05
Exercise
1. Refer to Matlab manual to understand each line in the above script.
2. Observe the histogram of images in im1.jpg, im9.jpg, im10.jpg, and
lena.jpg.
3. Select proper threshold values for each image and convert to black &
white image.

File Provided
Modul1.doc (this file)
Modul1.m
im1.jpg
im9.jpg
im10.jpg
f16.jpg
lena.jpg

Potrebbero piacerti anche