392 | P a g e
IDENTIFYING EDGES OF AN IMAGE BY DESIGNING AN IMPROVED ALGORITHM
IMPLEMENTED IN MATLAB
Anshu Mehta
1, Kapil Kaswan
2M.Tech (CSE), Chaudhary Devi Lal University, Sirsa, (India)
Assistant Professor, Deptt. Of CSA, Chaudhary Devi Lal University, Sirsa,(India)
ABSTRACT
Edge detection is the process of extracting edges from a digital image. Its aim is to identify pixel in the image where discontinuities occurs or there are sharp changes in the intensity. This process is crucial to understanding the content of an image and has its applicataions in image analysis and machine vision. It is usually applied in initial stages of computer vision applications edge is an important feature in an image and carries important information about the objects present in the image. Edge detection mainly aims to restrict boundaries of objects in an image and significantly reduces the amount of data to be processed.
Keywords:Ant Colony Optimization, MATLAB, Image Edge Detection
I. INTRODUCTION
Ant colony optimization (ACO) is an optimization algorithm which is designed by studying the natural behavior of the ants that deposit pheromone on the ground for foraging. It is used to resolve edge detection problem for digital images. Edge detection technique proposed by us is able to establish a pheromone matrix that mainly represents the edge information presented at each pixel position of the image which is according to the movement of the ants, which are dispatched to move on digital image. The movements of these ants are driven by the local variation in the image pixels intensity values.Edge detecting algorithm leads to a set of connected curves that represent boundaries of the objects as well as boundaries of markings, and discontinuities occurring in surface orientation. Thus, applying an edge detection algorithm to a digital image may reduce the amount of data to be processed and also filter out less relevant information, and also preserve the important structural properties of an image.
II.PROPOSEDALGORITHM
The Edge Detection process has been implemented by using the following steps:
1. Select the image and taken it as input.
2. Save image in a 256 Color bitmap format.
3. Calculate edge pixel values and generated the edges in image.
4. Generate the results with Improved Quality Edges.
393 | P a g e for each iteration n = 1:N do
for each construction_step l = 1:L do for each ant k = 1:K do
Select and go to next pixel Update pixel’s pheromone (local) End
End
Update visited pixels’ pheromones (global) End
Figure 1: Pheromone Matrix Generation by moving ants v = zeros(size(img));
v_norm = 0;
forrr =1:nrow for cc=1:ncol
temp1 = [rr-2 cc-1; rr-2 cc+1; rr-1 cc-2; rr-1 cc-1; rr-1 cc; rr-1 cc+1; rr-1 cc+2; rr cc-1];
temp2 = [rr+2 cc+1; rr+2 cc-1; rr+1 cc+2; rr+1 cc+1; rr+1 cc; rr+1 cc-1; rr+1 cc-2; rr cc+1];
temp0 = find(temp1(:,1)>=1 & temp1(:,1)<=nrow& temp1(:,2)>=1 & temp1(:,2)<=ncol& temp2(:,1)>=1 &
temp2(:,1)<=nrow& temp2(:,2)>=1 & temp2(:,2)<=ncol);
temp11 = temp1(temp0, :);
temp22 = temp2(temp0, :);
temp00 = zeros(size(temp11,1));
forkk = 1:size(temp11,1)
temp00(kk) = abs(img(temp11(kk,1), temp11(kk,2))-img(temp22(kk,1), temp22(kk,2)));
394 | P a g e end
if size(temp11,1) == 0 v(rr, cc) = 0;
v_norm = v_norm + v(rr, cc);
else
lambda = 10;
temp00 = sin(pi .* temp00./2./lambda);
v(rr, cc) = sum(sum(temp00.^2));
v_norm = v_norm + v(rr, cc);
end end end
v = v./v_norm;
v = v.*100;
p = 0.0001 .* ones(size(img));
III. RESULTS & DISCUSSIONS
Input Image Existing Edge Detection Proposed Edge Detection
395 | P a g e
Table 1: Image Edge Detection with Existing & Proposed Algorithm
Image No. Existing PSNR Proposed PSNR Existing RMSE Proposed RMSE
I1 36.4161160 36.6263267 3.87 3.78
I2 40.5390375 41.6538727 2.41 2.12
I3 40.0714472 42.7474690 2.54 1.87
I4 37.2514985 38.5225269 3.51 3.03
I5 38.0248807 38.7341159 3.21 2.96
I6 34.3791793 34.8345380 4.89 4.64
I7 34.4393919 35.5751656 4.86 4.26
Table 2: PSNR & RMSE Values for Existing & Proposed Algorithm
396 | P a g e Figure 2: Comparison of PSNR & RMSE Values for Existing & Proposed Algorithm
IV. CONCLUSION& FUTURE SCOPE
In our proposed algorithm we clearly see that we automatically obtain a relatively complete edge profile as compared to the traditional image edge detection methods like Sobel, Prewitt, Roberts and Canny.Our proposed algorithm generates a relatively complete edge profile as compared to the traditional method. But it is also visible that our proposed algorithm leaves some of the true edges with very low intensity which should have been highlighted otherwise. So, future scope of our research work will be to study the main reasons for this and improve our Ant Colony Optimization based algorithm method, so that we get better results without affecting the real highlighting of image edges.
REFERENCES
[1.] AnandNayyar, Rajeshwar Singh, “ANT COLONY OPTIMIZATION (ACO) BASED ROUTING PROTOCOLS FOR WIRELESS SENSOR NETWORKS (WSN): A SURVEY”, International Journal of Advanced Computer Science and Applications, Vol. 8, No. 2, 2017.
[2.] KavitaKhanna and ShaifaliMadanArora, “ANT COLONY OPTIMIZATION TOWARDS IMAGE PROCESSING”, Indian Journal of Science and Technology, Vol 9, Issue 8, December 2016.
[3.] N.Senthilkumaran and S.Keerthana, “DNA IMAGE SEGMENTATION – A COMPARISON OF EDGE DETECTION TECHNIQUES”, International Journal on Bioinformatics & Biosciences, Vol.6, No.2, June 2016.
[4.] Prof. DivyanshuRao, SapnaRai, “ANT COLONY OPTIMIZATION ALGORITHM FOR IMPROVING EFFICIENCY OF CANNY EDGE DETECTION TECHNIQUE FOR IMAGES”, International Journal of Scientific Research in Science, Engineering and Technology, Volume 2, Issue 6, 2016.
[5.] Ritisharaval, Divyesh Patel, “ADVANCED EDGE DETECTION USING ANT COLONY OPTIMIZATION”, Journal of Emerging Technologies and Innovative Research, Volume 2, Issue 9, September 2015.
[6.] GurpreetKaur Gill and Parminder Singh Saini, “A SURVEY ON ADAPTIVE EDGE DETECTION TECHNIQUES USING ANT COLONY OPTIMIZATION TECHNIQUES”, International Journal of Applied Engineering and Technology, Vol. 4, Issue 3, July-September 2014, pp.28-31.
0 10 20 30 40 50
I1 I2 I3 I4 I5 I6 I7 Old PSNR New PSNR
0 1 2 3 4 5 6
I1 I2 I3 I4 I5 I6 I7
Old RMSE New RMSE
397 | P a g e EDGE DETECTION OF IMAGES”, International Journal of Emerging Technology and Advanced Engineering, Volume 3, Issue 4, April 2013.
[8.] Jeetu Singh, AnkitVidyarthi, “DIGITAL IMAGE EDGE DETECTION USING ENHANCED ANT COLONY OPTIMIZATION TECHNIQUE”, International Journal of Computer Applications, Volume 67– No.16, April 2013.