Selecting Optimal RBF Kernel with Machine Learning for Feature Extraction and Classification in SAR Images

P. Deepthi Jordhana; K.Soundararajan

Selecting Optimal RBF Kernel with Machine Learning for Feature Extraction and Classification in SAR Images

P. Deepthi Jordhana * §

Contact

K.Soundararajan §

Contact

§ Intell Engineering College

Selecting Optimal RBF Kernel with Machine Learning for Feature Extraction and Classification in SAR Images

Article Fingerprint

ReserarchID

CSTGV2X89J

Selecting Optimal RBF Kernel with Machine Learning for Feature Extraction and Classification in SAR Images Banner

Key Research Insights

Synthesized scholarly intelligence & interactive research assistant

This converted HTML version may contain rendering inconsistencies. Please refer to the PDF for the authoritative version, or click here to provide feedback.

Abstract

Kernel methods are gaining popularity in image processing applications. The accuracy of feature extraction and classification on image data for a given application is greatly influenced by the choice of kernel function and its associated parameters. As on today there existing no formal methods for selecting the kernel parameters. The objective of the paper is to apply machine learning techniques to arrive at suitable kernel parameters and improvise the accuracy of kernel based object classification problem. The graph cut method with Radial Basis function (RBF) is employed for image segmentation, by energy minimization technique. The region parameters are extracted and applied to machine learning algorithm along with RBF’s parameters. The region is classified to be man made or natural by the algorithm. Upon each iteration using supervised learning method the kernel parameters are adjusted to improve accuracy of classification. Simulation results based on Matlab are verified for Manmade classification for different sets of Synthetic Aperture RADAR (SAR) Images.

References

25 Cites in Article

Reference Format

1. Mohammed Ben,Salah (2011). Multiregion Image Segmentation by Parametric Kernel Graph cuts. IEEE Trans on Image Processing, 20(2)
2. J Shi,J Malik (2000). Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell, 22(8), 888-905.
3. I Ayed,A Mitiche,Z Belhadj (2005). Multiregion level-set partitioning of synthetic aperture radar images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(5), 793-800.
4. Y Boykov,O Veksler,R Zabih (2001). Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell, 23(11), 1222-1239.
5. A Jain,P Duin,J Mao (2000). Statistical pattern recognition: A review. IEEE Trans. Pattern Anal. Mach. Intell, 22(1), 4-37.
6. J Morel,S Solimini (1995). Variational Methods in Image Segmentation. Variational Methods in Image Segmentation
7. G Aubert,P Kornprobst (2006). Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations. Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations
8. Daniel Cremers,Mikael Rousson,Rachid Deriche (2007). A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape. International Journal of Computer Vision, 72(2), 195-215.
9. David Mumford,Jayant Shah (1989). Optimal approximations by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, 42(5), 577-685.
10. S Zhu,A Yuille (1996). Region competetion: Unifying snakes, region growing, and bayes/MDL for multiband image segmentation. IEEE Trans. Pattern Anal. Mach. Intell, 18(6), 884-900.
11. T Chan,L Vese (2001). Active contours without edges. IEEE Transactions on Image Processing, 10(2), 266-277.
12. L Vese,T Chan (2002). Amultiphase level set framework for image segmentation using the Mumford ans Shahmodel. Int. J. Comput. Vis, 50(3), 271-293.
13. V Caselles,R Kimmel,G Sapiro (1995). Geodesic active contours. Proc. Int. Conf. Comput. Vis, 694-699.
14. J Shi,J Malik (2000). Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell, 22(8), 888-905.
15. Y Boykov,M-P Jolly (2001). Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 1, 105-112.
16. P Felzenszwalb,D Huttenlocher (2004). Efficient graph-based image segmentation. Int. J. Comput. Vis, 59(2), 167-181.
17. Allen Yang,John Wright,Yi Ma,S Sastry (2008). Unsupervised segmentation of natural images via lossy data compression. Computer Vision and Image Understanding, 110(2), 212-225.
18. F Destrempes,M Mignotte,J.-F Angers (2005). A stochastic method for Bayesian estimation of hidden Markov random field models with application to a color model. IEEE Trans. Image Process, 14(8), 1096-1124.
19. C Vazquez,A Mitiche,I Ayed (2004). Image segmentation as regularized clustering: a fully global curve evolution method. 2004 International Conference on Image Processing, 2004. ICIP '04., 5, 3467-3470.
20. Yvan Leclerc (1989). Constructing simple stable descriptions for image partitioning. International Journal of Computer Vision, 3(1), 73-102.
21. Andrew Blake,Carsten Rother,M Brown,Patrick Perez,Philip Torr (2004). Interactive Image Segmentation Using an Adaptive GMMRF Model. Lecture Notes in Computer Science, 428-441.
22. A Doerry,D Dubbert A portfolio of fine resolution Ka-band SAR images: part I. A portfolio of fine resolution Ka-band SAR images: part I
23. R Unnikrishnan,C Pantofaru,M Hebert (2005). A measure for objective evaluation of image segmentation algorithms. Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations, 3
24. Nhat Vu,B Manjunath (2008). Shape prior segmentation of multiple objects with graph cuts. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 1-8.
25. Mohamed Salah,Amar Mitiche,Ismail Ayed (2008). A Continuous Labeling for Multiphase Graph Cut Image Partitioning.

Download References

Funding

No external funding was declared for this work.

Conflict of Interest

The authors declare no conflict of interest.

Ethical Approval

No ethics committee approval was required for this article type.

Data Availability

Not applicable for this article.

How to Cite This Article

P. Deepthi Jordhana, K.Soundararajan. 2014. "Selecting Optimal RBF Kernel with Machine Learning for Feature Extraction and Classification in SAR Images". Global Journal of Computer Science and Technology - F: Graphics & Vision GJCST-F Volume 14 (GJCST Volume 14 Issue F4).

More Citation Formats

Select Citation Style:

Download Citation

GJCST Volume 14 Issue F4

Explore Journals Explore Volume Read This Issue

Journal Specifications

Crossref Journal DOI 10.17406/gjcst

Print ISSN 0975-4350

e-ISSN 0975-4172

Keywords

graph cut kernel Image Segmentation Machine Learning RBF kernel

Classification

I.4.0

H.1.2

Submission ReceivedDecember 7, 2013
Peer Review Double Blind
Handling Editor
Accepted December 31, 2013
Published September 30, 2014

Version of record

v1.2

Issue date

September 30, 2014

Language

English

Order Article Reprint

Experience in AR

Explore published articles in an immersive Augmented Reality environment. Our platform converts research papers into interactive 3D books, allowing readers to view and interact with content using AR and VR compatible devices.

View in VR

Read in 3D

Your published article is automatically converted into a realistic 3D book. Flip through pages and read research papers in a more engaging and interactive format.

View in 3D

Article Matrices

Total Score: 102

Country: India

Subject: Global Journal of Computer Science and Technology - F: Graphics & Vision

Authors: P. Deepthi Jordhana, K.Soundararajan (PhD/Dr. count: 0)

View Count (all-time): 514

Total Views (Real + Logic): 2268

Total Downloads (simulated): 93

Publish Date: 2014 01, Wed

Monthly Totals (Real + Logic):

Month 1: 60 views
Month 2: 31 views
Month 3: 54 views
Month 4: 49 views
Month 5: 37 views
Month 6: 46 views
Month 7: 30 views
Month 8: 29 views
Month 9: 38 views
Month 10: 39 views
Month 11: 31 views
Month 12: 27 views
Month 13: 32 views
Month 14: 17 views
Month 15: 24 views
Month 16: 25 views
Month 17: 28 views
Month 18: 25 views
Month 19: 19 views
Month 20: 24 views
Month 21: 21 views
Month 22: 34 views
Month 23: 26 views
Month 24: 34 views
Month 25: 18 views
Month 26: 40 views
Month 27: 20 views
Month 28: 30 views
Month 29: 35 views
Month 30: 25 views
Month 31: 15 views
Month 32: 17 views
Month 33: 15 views
Month 34: 34 views
Month 35: 42 views
Month 36: 46 views
Month 37: 36 views
Month 38: 15 views
Month 39: 43 views
Month 40: 28 views
Month 41: 22 views
Month 42: 30 views
Month 43: 27 views
Month 44: 35 views
Month 45: 33 views
Month 46: 34 views
Month 47: 20 views
Month 48: 31 views
Month 49: 30 views
Month 50: 13 views
Month 51: 27 views
Month 52: 40 views
Month 53: 14 views
Month 54: 25 views
Month 55: 45 views
Month 56: 32 views
Month 57: 40 views
Month 58: 12 views
Month 59: 33 views
Month 60: 30 views
Month 61: 45 views
Month 62: 30 views
Month 63: 16 views
Month 64: 46 views
Month 65: 19 views
Month 66: 26 views
Month 67: 29 views
Month 68: 29 views
Month 69: 12 views
Month 70: 25 views
Month 71: 31 views
Month 72: 31 views
Month 73: 20 views
Month 74: 21 views
Month 75: 24 views
Month 76: 32 views
Month 77: 28 views
Month 78: 44 views
Month 79: 43 views
Month 80: 25 views
Month 81: 24 views
Month 82: 23 views
Month 83: 20 views
Month 84: 21 views
Month 85: 33 views
Month 86: 36 views
Month 87: 49 views
Month 88: 35 views
Month 89: 46 views
Month 90: 34 views
Month 91: 33 views
Month 92: 23 views
Month 93: 16 views
Month 94: 36 views
Month 95: 27 views
Month 96: 16 views
Month 97: 16 views
Month 98: 31 views
Month 99: 37 views
Month 100: 17 views
Month 101: 21 views
Month 102: 14 views
Month 103: 28 views
Month 104: 37 views
Month 105: 35 views
Month 106: 35 views
Month 107: 40 views
Month 108: 16 views
Month 109: 43 views
Month 110: 40 views
Month 111: 35 views
Month 112: 45 views
Month 113: 46 views
Month 114: 21 views
Month 115: 43 views
Month 116: 37 views
Month 117: 21 views
Month 118: 38 views
Month 119: 31 views
Month 120: 31 views
Month 121: 40 views
Month 122: 35 views
Month 123: 24 views
Month 124: 28 views
Month 125: 26 views
Month 126: 16 views
Month 127: 43 views
Month 128: 32 views
Month 129: 46 views
Month 130: 45 views
Month 131: 35 views
Month 132: 26 views
Month 133: 46 views
Month 134: 36 views
Month 135: 33 views
Month 136: 49 views
Month 137: 26 views
Month 138: 40 views
Month 139: 31 views
Month 140: 37 views
Month 141: 43 views
Month 142: 30 views
Month 143: 27 views
Month 144: 46 views
Month 145: 36 views
Month 146: 36 views
Month 147: 31 views
Month 148: 33 views
Month 149: 29 views
Month 150: 46 views
Month 151: 39 views
Month 152: 37 views
Month 153: 59 views
Month 154: 36 views

Total Views: 2.3K

Total Downloads: 93

All Trends