International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 649...
International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 649...
International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 649...
International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 649...
International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 649...
International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 649...
International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 649...
Upcoming SlideShare
Loading in …5
×

A modified pso based graph cut algorithm for the selection of optimal regularizing

246 views

Published on

Published in: Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
246
On SlideShare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
7
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

A modified pso based graph cut algorithm for the selection of optimal regularizing

  1. 1. International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 6499(Online) Volume 4, Issue 3, April (2013), © IAEME273A MODIFIED PSO BASED GRAPH CUT ALGORITHM FOR THESELECTION OF OPTIMAL REGULARIZING PARAMETER INIMAGE SEGMENTATIONShameem Akthar1, Dr. D Rajaylakshmi2, Dr. Syed Abdul Sattar31(Computer Science & Engg., KBNCE, Karnataka, India)2(IT Department, JNTU University, Andhra Pradesh, India)3(EC Dept., Royal Institute of Tech., Andhra Pradesh, India)ABSTRACTImage segmentation is an important stage from the image processing to imageanalysis. According to the segmentation of image only, the target expression of originalimage will be transformed into more abstract and compact manner, which will lead to high-level analysis of the image and the understandability of image. In our paper, a modified PSObased Graph cut algorithm is proposed for the selection of the optimal regularizing parameterin the image. The raw image is pre-processed using filtering and applied to graph-cut afterregularizing the parameters using modified PSO. A proper selection of the parameter remainsa critical problem for practical image segmentation. Based on this optimized parameter valuethe important region and the boundary are detected in the given input image. The proposedmethod is implemented in MATLAB with various images.Keywords: Gaussian Filter, Graph cut Algorithm, Min-cut / Max-Flow Algorithm, ParticleSwarm Optimization, Segmentation.1. INTRODUCTIONImage segmentation is a complex and challenging task due to the intrinsicallyimprecise nature of the images [1]. In areas such as computer vision and Image Processing,image segmentation has been and still is a relevant research area due to its wide spread usageand application [7]. The segmentation of the target areas is an important aspect in imagesegmentation [5]. Generally, segmentation is a first step for a variety of image analysis andvisualization tasks. The steps or processes after segmentation rely on the segmentationINTERNATIONAL JOURNAL OF ADVANCED RESEARCH INENGINEERING AND TECHNOLOGY (IJARET)ISSN 0976 - 6480 (Print)ISSN 0976 - 6499 (Online)Volume 4, Issue 3, April 2013, pp. 273-279© IAEME: www.iaeme.com/ijaret.aspJournal Impact Factor (2013): 5.8376 (Calculated by GISI)www.jifactor.comIJARET© I A E M E
  2. 2. International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 6499(Online) Volume 4, Issue 3, April (2013), © IAEME274quality [4]. Segmentation is a process of partitioning an image space into some non-overlapping meaningful homogeneous regions. In general, these regions will have a strongcorrelation with the objects in the image. The success of an image analysis system dependson the quality of segmentation [1]. Segmentation is one of the popular methods used to detectflaws in weldmesh. Generally the flaws that occur are wormholes, inclusion, lack of fusion,porosity, incomplete penetrations, slag line and cracks [8].Image segmentation is used to locate and find objects and boundaries(lines,curvesetc.) of image. To perform it there are many ways[11].Region growing algorithms have been used mostly in the analysis of grayscale images[3]. The general procedure is to compare a specific feature of one pixel to its neighbor(s)feature. If a criterion of homogeneity is satisfied, the pixel is classified to the same class asone or more of its neighbors. The choice of the homogeneity criterion is critical for evenmoderate success and in all instances the results are upset by noise [2] [6]. Moreover,computational cost of segmentation algorithms increases while algorithmic robustnesstends to decrease with increasing feature space sparseness and solution spacecomplexity [4].2. PROPOSED METHODOLOGYOur proposed system comprises of three phases.1) Pre-processing2) Optimal parameter selection using PSO3) Segmentation using Graph Cut algorithm2.1 Pre-ProcessingInitially pre-processing is done through Gaussian filter, we apply a stepper Gaussianfield with less deviation value to remove the unwanted portions in the image such as noise,blur, reflections. A 5 x 5 Gaussian Filter is used with 4.1=σ .2.2 Optimal Parameter Selection Using Modified PsoThe regularizing parameters are selected and applied for Graph cut Algorithm. Theparameters that are given as the input for the graph cut are smallest size of area and smallestthreshold cut value.2.2.1 Modified Particle Swarm Optimization (PSO)Particle swarm optimization (PSO) is a population-based optimization algorithmmodeled after the simulation of social behavior of birds in a flock. The algorithm ofPSO is initialized with a group of random particles and then searches for optima byupdating generations. Each of the particles are flown through the search space having itsposition adjusted based on its distance from its own personal best position and the distancefrom the best particle of the swarm[10]. The performance of each particle, i.e. howclose the particles is from the global optimum, is measured using a fitness function whichdepends on the optimization problem. There are two position pbest and gbest . Also twobest values pbest value and gbest values [9].In our modified PSO, in addition with the pbest value, the personal worst locationof the particle is denoted as pworst is used. The previously seen worst locations of the
  3. 3. International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 6499(Online) Volume 4, Issue 3, April (2013), © IAEME275particle are represented by this pworst value. While updating the velocity, pworst value isalso taken into consideration along with the difference between the personal best position ofthe particle and the current location of the particle. By including pworst value, the particlecan detour its previous worst location and try to select the better position.2.2.1.1. Modified PSO Algorithm StepsStep 1: Initialize a population of i particles with each particle’s position ix and velocity ivon a problem space nR of dimension n .Step 2: Compute the fitness function for each particle i in d variables.Step 3: Make comparison between the particle’s fitness value, fitnessx and particle’s pbestfitness value, fitnessp . If the current fitness value of particle is better than the particle’spbest fitness value, then set the pbest value into current position in the d thdimension.Step 4: Check out all of the particle’s pbest fitness value, fitnessp with value of gbest . Ifthe current value, pbest is better than the gbest value means, then set the gbest value intocurrent particle’s array index and value.Step 5: Update the velocity and position of the particles given as in equations (1) and (2).)()()(322111idididididbidididaididxgbestrpworstpworstxrpbestxpbestrvv−××+×−××+×−××+×=ϕϕϕω(1)ididid vxx += (2)Step 6: Repeat step 2, until a better fitness or maximum number of iterations are met.Process of Merging: After getting the values of gbest , the Merging Process is used to mergethe regions. The input for the Merging Process is all these obtained gbest values. At each andevery step, the adjusted regions are merged one by one, with the gbest values. As a result,the boundary of the objects is obtained from the images which are not smooth. In order toobtain the refined boundary, boundary refinement technique is used.Refinement of Boundaries: If an image pixel presents on the boundary of at least twodistinct regions means, then a discrete disk with the radius 3 will be placed on it. For therefinement of jagged boundaries, the similarity between these two regions is evaluatedindividually.2.3. Segmentation Using Minimum-Cut/Maximum-Flow Graph Cut AlgorithmA graph is represented as },,{ WEVG = , where V represents finite set of nodes(vertices); E is a set of unordered pairs edges from V ; and W denotes the affinity matrix thatassociates a weight to each edge in E . There are two special nodes called as terminals assource, Vs∈ and sink, Vt∈ . Other nodes are non-terminal nodes. There are two types ofedges linkt − and linkn − . linkn − connect the non-terminal nodes and linkt − connects anon-terminal node with a terminal node. linkn − indicates a neighborhood system in theimage. Each of the edges E is associated with weight or cost W .
  4. 4. International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 6499(Online) Volume 4, Issue 3, April (2013), © IAEME276The Minimum-Cut of a graph G is the cut that partitions the graph into disjointsubsets, such that the sum of the weights W associated with the edges E of the graph Gbetween the different subsets X andY is minimized. In graph theoretic language, the cut isrepresented as,∑∈∈=YvXuvuWYXCut,),(),( (3)The parameters of energy in our work is smallest size of area and smallest threshold cutvalue, the edge weights are appropriately set. If the weights of edge are set, then a minimumcut will correspond to a labeling with the minimum value of this energy.3 RESULTS AND DISCUSSIONSOur proposed work is implemented in MATLAB platform. The images are collectedfrom various databases and given for the implementation. The results for the segmentedimages are shown in figure 1, 2 and 3.ImagesOriginal imageSegmented non-tumorregionSegmented tumorregion12Fig.1: Segmented output for normal MRI brain images using our proposed method
  5. 5. International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 6499(Online) Volume 4, Issue 3, April (2013), © IAEME277ImagesOriginal image Segmented WM region Segmented GM region1Fig. 2 : Segmented output for abnormal brain MRI images using our proposed methodOriginalimageSegmentedFlowerregionSegmentedLeafRegionFig. 3: Segmented output for Flower images using our proposed methodIn our implementation work, some of the samples are given in our discussion. Infigure 1,2,3 first column shows original images, the second and third column shows thesegmented non-tumor & tumor region for figure 1, WM & GM region for figure 2 andflower and leaf regions, for figure 3 respectively. From the columns 2 and 3 in figures 1, 2and 3, it is noted that our proposed method effectively segment the given input images.
  6. 6. International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 6499(Online) Volume 4, Issue 3, April (2013), © IAEME278Performance EvaluationTo evaluate our work, Jaccard Similarity evaluation, Dice Co-efficient evaluation andAccuracy are considered as measure of metric.Jaccard similarity(JS)Dice coefficient (DS) AccuracyaoaoRRRRJS∪∩=FNFPTPTPRRRRDCaoao++××=+∩=)2(22FNFPTNTPTNTPAcc++++=Table 1: JC,DC and Accuracy equationsUsing table 1 equations of JS, DS and Accuracy the performance for our proposed method isevaluated. In these equations, the values are True Positive (TP), True Negative (TN), FalsePositive (FP), and False Negative (FN) for tumor part correctly, non-tumor part correctly,none—tumor part incorrectly, and tumor part incorrectly for figure 1.Likewise, we have taken all these values according to the segmentation regions for figure 2and figure 3. In table 2, the JS and DC values are tabulated for the conventional method andfor the proposed method.Images Proposed method Existing methodJS DC JS DC1 0.919612 0.958123 0.930397 0.9639442 0.853747 0.921104 0.76172 0.8647463 0.847663 0.917551 0.747444 0.8554714 0.726466 0.841564 0.691094 0.822275Table 2: JC and DC values for existing and proposed methodTable 3, gives the accuracy measure for the proposed PSO and Graph Cut algorithm andexisting conventional.Images Proposed method Conventional PSOConventional Graphcut1 95.3 92.13 93.22 95.12 92 93.43 95.2 92.61 934 94.99 92.3 93.55Table 3: Accuracy measure comparison for both Proposed and conventional methods (in %)4 CONCLUSIONIn this paper, a modified PSO based graph cut segmentation, was presented. We haveused smallest size area and smallest threshold cut value as regularizing parameter. Along withthis, we found the worst position of the particle so that the particle can move away from thatposition to the best position, which reduces the time taken for convergence of the searchspace, with better achievement of an optimal solution when compared with the conventionalPSO and Graph Cut approaches. Thus our modified PSO with Graph Cut provides betteraccuracy value than the conventional method with 95.1525% .
  7. 7. International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN0976 – 6480(Print), ISSN 0976 – 6499(Online) Volume 4, Issue 3, April (2013), © IAEME279REFERENCES[1] Sriparna Saha, and Sanghamitra Bandyopadhyay, "MRI Brain Image Segmentation byFuzzy Symmetry Based Genetic Clustering Technique", In Proceedings of IEEE Conferenceon Evolutionary Computation, pp. 4417-4424, September, 2007.[7] P.Raja Sekhar Reddy, N.Naga Lakshmi, and Thandu Ashalatha, "Image SegmentationUsing A Region Growing Method – A Comparative Study", International Journal ofEngineering and Social Studies, Vol. 2, No. 7, pp. 62-69, 2012.[5] Dongwei Guo, Bo Zhang, and Yunna Wu, Lisai Cao, "The Man-made AreasSegmentation Based on Region Growing Method Using Local Fractal Dimension", Journal ofInformation and Computational Science, Vol. 10, No. 3, pp. 659–667, 2013.[4] Nazahah Mustafa, Nor Ashidi Mat Isa and Mohd Yusoff Mashor, "Automated MulticellsSegmentation of ThinPrep Image Using Modified Seed Based Region Growing Algorithm",Biomedical Soft Computing and Human Sciences, Vol.14, No.2, pp.41-47, 2009.[8] B.Karthikeyan, V.Vaithiyanathan, B.Venkatraman, and M.Menaka, "Analysis of ImageSegmentation for Radiographic Images", Vol. 5, No. 11, pp. 3660-3664, November 2012.[2] M. M. Abdelsamea, "An Automatic Seeded Region Growing for 2D Biomedical ImageSegmentation", In Proceedings of International Conference on Environment and Bio-Science,2011.[3] Yongming Li, Dongming Lu, Xiqun Lu, and Jianming Liu, "Interactive Color ImageSegmentation by Region Growing Combined with Image Enhancement Based on BezierModel", In Proceedings of IEEE Conference on Multi-Agent Security and Survivability, pp.96-99, 2004.[4] J.Leela Mahendra Kumar, A.Vasavi , and B.Praveena, "Semantic Region Growing ForMultivariate Image Segmentation Using Adaptiver Edge Penality", International Journal ofEngineering Research & Technology, Vol.1, No. 4, June 2012.[6] Rolf Adams and Leanne Bischof, “Seeded Region Growing”, IEEE Transactions onPattern Analysis and Machine Intelligence, Vol. 16, No. 6, June 1994.[9] Fahd M. A. Mohsen, Mohiy M. Hadhoud, and Khalid Amin, "A new Optimization-BasedImage Segmentation method By Particle Swarm Optimization", International Journal ofAdvanced Computer Science and Applications, Vol. 7, No. 4, pp. 10-18, 2010.[10] Shameem Akthar, Dr.D.Rajaylakshmi, Dr.Syed Abdul Sattar, “Contour Detection UsingPSO and Graph Cut”,IJARCSEE Volume 1, Issue 1.[11] Shameem Akthar, Dr.D. Rajaylakshmi, Dr.Syed Abdul Sattar, “A theoretical survey foredge detection technique and watershed transformation”, IJCTEE Volume. 2, Issue 1.[12] Gaganpreet Kaur and Dr. Dheerendra Singh, “Pollination Based Optimization for ColorImage Segmentation”, International journal of Computer Engineering & Technology(IJCET), Volume 3, Issue 2, 2012, pp. 407 - 414, ISSN Print: 0976 – 6367, ISSN Online:0976 – 6375.[13] Ankit Vidyarthi and Ankita Kansal, “A Survey Report on Digital Images SegmentationAlgorithms”, International journal of Computer Engineering & Technology (IJCET),Volume 3, Issue 2, 2012, pp. 85 - 91, ISSN Print: 0976 – 6367, ISSN Online: 0976 – 6375.

×