Exercise 1: Write a function named transform to
implement intensity transformations: INPUTS: 1) Image, 2) Transformation name i.e. inverse, power, or log. OUTPUTS: Show your results for each of the transformations and give a comparison between log and power transformations with reference to your findings/observations.
Solution:
M File:
function transform(name,img) if(strcmp(name,'inverse')==1) [m n]=size(img); for i=1:m for j=1:n img1(i,j)=255-img(i,j); end end imshow(img),figure,imshow(img1) end if(strcmp(name,'power')==1) img1=mat2gray(img); disp('Power Law Transformation Formula is c*(img(x,y))^r'); c=input('Enter Constant c :'); r=input('Enter Gamma Correction value r (gamma):'); [m n]=size(img1); for i=1:m for j=1:n img2(i,j)=c*img1(i,j)^(r); end end imshow(img),figure,imshow(img2) end if(strcmp(name,'log')==1) img2=mat2gray(img); [m n]=size(img2); c=input('Log Transformation formula is c*log(1+img(x,y)), Enter constant c :'); for i=1:m for j=1:n img1(i,j)=c*log(1+img2(i,j)); end end imshow(img),figure,imshow(img1) end
Functional Call from Command Window for inverse: >> img=imread('rice.png'); >> transform('inverse',img)
Fig 1 Result of inverse transformation on rice.png
Functional Call from Command Window for power: >> transform('power',img) Power Law Transformation Formula is c*(img(x,y))^r Enter Constant c :1 Enter Gamma Correction value r (gamma):0.3
Fig 2 Result of power transformation on rice.png
Functional Call from Command Window for log: >> transform('log',img) Log Transformation formula is c*log(1+img(x,y)), Enter constant c :2
Fig 3 Result of log transformation on rice.png
Comparison between power and log transformation results: As we can see from the log and power transformation results that in both the cases low range of input intensities are mapped to higher range of output intensities but in the power transformation there is a slight wash out effect on the output image and in the log output image a little bit sharpness is there. When using power transformation value of gamma greater then 1 would result in a darker image and value less then 0 would result in a brighter image.
Exercise
LAB:
2: Write
function
named
myhist
to
MANUALLY compute image histogram as described in the
Solution:
M File:
function imhist1(img) [m n]=size(img); k=0:1:255; k(1:256)=0; for i=1:m for j=1:n if(j==img(i,j)) k(j)=k(j)+1; end end end for h=1:255 title('Bar Graph'); xlabel('gray-levels', 'fontsize', 10); ylabel('frequescy', 'fontsize', 10); bar(h,k(h),'b') % plot(h,k(h),'-') hold on; end l=imhist(img); ,figure,bar(l); ,figure, for h=1:255 title('Stem Graph'); xlabel('gray-levels', 'fontsize', 10); ylabel('frequescy', 'fontsize', 10); stem(h,k(h),'r') % plot(h,k(h),'-') hold on; end ,figure,stem(l);
Functional Call from Command Window: >> img=imread('rice.png'); >> imhist1(img)
Output: Bar graph:
Fig 1 Histogram of rice.png on bar graph
Stem Graph:
Fig 2 Histogram of rice.png on stem graph
Comparison between imhist() graphs and our algorithm graphs:
Figure 3
imhist () bar graph
algorithm bar graph
Figure 4
imhist () stem graph
algorithm stem graph
Exercise 3: Consider a function f(x) defined over an image
cameraman.tif with the intensities in the range [0 1], as defined below: 1x f(x) = x a). b). image intensities. Write a MATLAB program to implement f(x) on an input image. Also, show your results after transformation. 1 0 < x 0.25 0.25 < x 0.5 x > 0.5
Draw a graph for f(x) to show its influence on
Solution:
a). Graph:
Figure 1: Graph showing the influence of the function on intensities
b).
M File:
function slicing1(img1) [m n]=size(img1); img=im2double(img1); for i=1:m for j=1:n if(img(i,j)>0 && img(i,j)<=0.25) img2(i,j)=1-img(i,j); end if(img(i,j)>0.25 && img(i,j)<=0.5) img2(i,j)=1; end if(img(i,j)>0.5) img2(i,j)=img(i,j); end end end imshow(img),impixelinfo,figure,imshow(img2)
Functional Call from Command Window: >> img=imread('cameraman.tif'); >> slicing1(img) Output:
Figure 2
Original Image
Transformed Image
Exercise 4: Write a MATLAB program for the function shown in
figure 2, on an input image cameraman.tif. Also show your results.
Solution:
M File:
function slicing1(img1) [m n]=size(img1); img=im2double(img1); for i=1:m for j=1:n if(img(i,j)>0 && img(i,j)<=0.25) img2(i,j)=1-img(i,j); end if(img(i,j)>0.25 && img(i,j)<=0.5) img2(i,j)=1; end if(img(i,j)>0.5)
end
img2(i,j)=2*img(i,j)-1;
end end imshow(img),impixelinfo,figure,imshow(img2)
Functional Call from Command Window: >> img=imread('cameraman.tif'); >> slicing2(img)
Output:
Figure 1
Original Image
Transformed Image
