image processing
LAB # 03: Transformation Operations
Lab Objective:
The objective of this lab is to implement thresholding on images to convert them to binary, perform
different transformation operations on images.
Lab Description:
Transformation operations help enhance the quality of the image by applying operations like
log, inverse log and power on the entire image. Different type of transformation yields different
results.
There are three basic gray level transformation.
I. Linear
II. Logarithmic
III. Power law
The overall graph of these transitions has been shown below.
Transformation curves
Power law transformations:It includes nth power and nth root transformation. These
transformations can be given by the expression:
Digital Image Processing Lab Manual
1
s=cr^
This symbol is called gamma, due to which this transformation is also known as gamma
transformation.
Variation in the value of varies the enhancement of the images. Different display devices /
monitors have their own gamma correction, thats why they display their image at different
intensity.
This type of transformation is used for enhancing images for different type of display devices.
The gamma of different display devices is different. For example Gamma of CRT lies in between
of 1.8 to 2.5, that means the image displayed on CRT is dark.
Correcting gamma.
s=cr^
s=cr^(1/2.5)
The same image but with different gamma values has been shown here.
ccccccGamma 8 Gamma 6 Gamma 10
Log transformations
The log transformations can be defined by this formula
s = c log(r + 1).
Where s and r are the pixel values of the output and the input image and c is a constant. The value
1 is added to each of the pixel value of the input image because if there is a pixel intensity of 0 in
the image, then log (0) is equal to infinity. So 1 is added, to make the minimum value at least 1.
During log transformation, the dark pixels in an image are expanded as compare to the higher
pixel values. The higher pixel values are kind of compressed in log transformation.
Digital Image Processing Lab Manual
2
Input image output of log transformation
.
Negative Transformation
The second linear transformation is negative transformation, which is invert of identity
transformation. In negative transformation, each value of the input
image is subtracted from the L-1 and mapped onto the output image.
This transformation is done by this formula
s = (L 1) r
So each value is subtracted by 255,so the lighter pixels become dark
and the darker picture becomes light. And it results in image negative.
Negative transformation
Thresholding is the operation through which an image can be converted into a binary image/black
& white i.e. having only two distinct levels. Threshold value can be the mean or median etc. of the
image.
Gray level Slicing is used to highlight a specific range of gray levels in an image
Some Useful Commands:
1. To calculate the mean of 2D array using NumPy: my_mean = numpy.mean (my_array)
2. To calculate min (or max) of an array: my_min = numpy.amin(my_array)
3. To calculate the power of an array using NumPy: array_power = numpy.power (my_array,
power)
4. To obtain percentile value. percentile_array = numpy.percentile(my_array, percentile)
5. To change data type of array. my_array = my_array.astype(numpy.uint16)
Digital Image Processing Lab Manual
3
Lab Tasks:
1: Apply following transformation techniques on image provided and observe the output image
of each transformation.
I. Negative transformation
II. Log transformation
2: Apply the following transformation on an image.
Pixel values range Output pixel value
a) Less than mean
Greater than mean
0
255
b) Less than mean
Greater than mean
255
0
c) 20 mean
Otherwise
0
255
3:Apply Power Law transformation for the following values of (0.2, 0.5, 1.2 and 1.8) . Make
sure to adjust data types accordingly.
4:Apply Gray level slicing using lower limit 100 and upper limit 200. Set all these values to 210.
Bit plane slicing
Bit plane slicing is a method of representing an image with one or more bits of the byte used for
each pixel. One can use only MSB to represent the pixel, which reduces the original gray level to
a binary image. Main objective of this technique is:
To highlight the contribution made to the total image appearance by specific bits.
a) Assuming that each pixel is represented by 8 bits, the image is composed
of 8 1-bit planes.
Digital Image Processing Lab Manual
4
b) Plane 1 contains the least significant bit and plane 8 contains most
significant
c) Useful for analyzing the relative importance played by each bit of the
image.
Fig: Bit plane slicing
Home Task:
Perform Bit Plane Slicing on given image. An application of this technique is data compression.
In general, 8-bit per pixel images are processed. Slice the provided image into following bit
planes (0,1,2,3,4,5,6,7). Save the output of each slicing.
Fig:coin img
Applications:
i. Enhancement of image for different type of display devices.
Digital Image Processing Lab Manual
5
ii. Power-law transformation for enhanced recognition of born-digital word images
iii. Image Enhancement by Adaptive Power-Law Transformations
References:
I. http://www.cs.uregina.ca/Links/class-info/425/Lab3/
II. https://www.tutorialspoint.com/dip/gray_level_transformations.htm
THINK!!
1) What is the difference between enhancing image using power law transformation and
contrast stretching?
2) If an image is dark what can be the gamma value to visualize it better?
3) If we want to enhance only a certain range of pixel values, which of the following above
mentioned methods can be used?
http://www.bing.com/search?q=ii.%09Power-law+transformation+for+enhanced+recognition+of+born-digital+word+images&src=IE-TopResult&FORM=IETR02&conversationid=
https://www.bahria.edu.pk/ojs/index.php/bujict/article/view/26
http://www.cs.uregina.ca/Links/class-info/425/Lab3/
https://www.tutorialspoint.com/dip/gray_level_transformations.htm
