The week's pick
Random Articles
Reseach Article
Segmentation of Images Containing Multiple Intensity Levels using Genetic Algorithms
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 126 - Number 9 |
| Year of Publication: 2015 |
| Authors: B.D. Phulpagar, R.S. Bichkar |
10.5120/ijca2015906186
|
B.D. Phulpagar, R.S. Bichkar . Segmentation of Images Containing Multiple Intensity Levels using Genetic Algorithms. International Journal of Computer Applications. 126, 9 ( September 2015), 29-39. DOI=10.5120/ijca2015906186
Abstract
Image segmentation technique is the process of separating the foreground objects of different intensities from the background. Several authors have proposed different methods for segmentation of images into two classes, each one having different quality of segmentation. Yu et al [1]. used a GA approach to segmentation of 2-D images into two classes. We have extended this method to segment the images into multiple classes or multiple intensity levels (Four, Eight, Twelve and Sixteen greay Levels). The proposed GA-based approach gives us good results for original synthetic images and noisy images containing rectangular, elliptical and irregular-objects using morphological operations upto sixteen classes. The results obtained give 81% to 100% pixel classification accuracy for different types of noise (Gaussian, Speckle, salt and pepper and Poisson) and high noise levels (SNR ranging between 2.18 dB to 6.97 dB). The segmentation results obtained by using proposed GA-based method are good as compared to standard image segmentation FCM method with the increasing noise density of salt and pepper and Gaussian noises.
References
- M. Yu, N. Eua-anant, A. Saudagar, and L. Udpa, “Genetic Algorithm Approach to Image Segmentation Using Morphological Operations,” IEEE International Conference on Image Processing, vol. 3, pp. 775 - 779, October - 1998.
- D. E. Goldberg, Genetic Algorithm in Search, Optimization and Machine Learning, Pearson, Delhi, 2004, 7th Edition.
- M. Zhang and V. Ciesielski, “Genetic Programming for Multiple Class Object Detection,” Proceeding of the 12th Australian Joint Conference on Artificial Intelligence Springer, Heidelberg, pp. 180 - 191, 1999.
- S. Chabrier, C. Rosenberger, and B. Emile, “Optimization Based Image Segmentation by Genetic Algorithms,” EURASIP Journal on Video and Image Processing, vol. 1, pp. 1 - 23, February - 2008.
- S. Nath, S. Agarwal, and Q. Kazmi, “Image Histogram Segmentation by Multi-Level Thresholding using Hill Climbing Algorithm,” IJCA, vol. 35, no. 1, pp. 63 - 72 , December - 2011.
- O. Banimelhem and Y. Yahya, “Multi-Thresholding Image Segmentation using Genetic Algorithm,” Jordan University of Science and Technology, , Irbid, Jordan, pp. 1 - 6.
- R. Kumar, T. Parashar, and G. Verma, “A Multilevel Automatic Thresholding for Image Segmentation using Genetic Algorithm and DWT,” International Journal of Electronics and Computer Science Engineering , vol. 1, no. 1, pp. 153 - 160, 2013.
- P. Liao, T. Chen, and P. Chung, “A Fast Algorithm for Multilevel Thresholding,” Journal of Information Science and Engineering, pp. 712 - 727, 2001.
- S. Samanta, N. Dey, and S. Acharjee, “Multilevel Threshold Based Greay Scale Image Segmentation using Cuckoo Search,” Elsevier, pp. 27 - 34 , 2012.
- H. Rawi, Dr. Jane, and J. Stephan, “Histogram-Based Optimal Multiple Thresholding using Genetic Algorithm,” University of Bahrain, pp. 1 - 8
- B. D. Phulpagar and R. S. Bichkar, “Segmentation of Noisy Binary Images Containing Circular and Elliptical Objects using Genetic Algorithms”, International Journal of Computer Applications, vol. 66, no. 22, PP. 1 – 7, March – 2013.
- R. C. Gonzalez, R. E. Woods, Digital Image Processing, Pearson, Delhi, 2008, 3rdEdition.
- A. K. Jain, Fundamental of Digital Image Processing, Pearson, Delhi, 1989, 2nd Edition.
- E. Gose, R. C. Johnsonbaugh, Pattern Recognition and Image Analysis, PrenticeHall, Delhi, 2000, 2ndEdition.
Index Terms
Keywords