Authors:
Shubhajoy Das,Debashis Das,DOI NO:
https://doi.org/10.26782/jmcms.2020.07.00009Keywords:
Magnetic Resonance Imaging,K-means algorithm,Genetic Algorithms,Ant Colony Optimization ,Image segmentation,unsupervised classification,support vector machine,Medical Image processing,Abstract
The main purpose of segmentation is to partition an image based on features into different regions. Unsupervised classification algorithms K means, K-nearest neighbor, neural networks can be used to perform efficient image segmentation. Image segmentation is an important step to perform classification of images. Segmentation algorithms such as watershed segmentation, support vector machines can be used to find the region of interest. A genetic algorithm based image segmentation algorithm, ant colony optimization algorithm is proposed and we compare it with k-means segmentation. We apply some segmentation algorithms in industry standard datasets and view the results of our segmentation algorithms. Segmentation is a basic task in image processing and can be applied in large number of domains. We emphasize on how a segmentation algorithm can be developed to segment out tum ours from medical magnetic resonance images. We have used the open CV python package for our image processing tasks.Refference:
I A Markov random field image segmentation model for color textured images Zoltan Kato a,*, Ting-Chuen Pong b,1
II Bradski, G., 2000. The Open CV Library. Dr. Dobb Journal of Software Tools.
III Colour Image Segmentation Using SVM Pixel Classification Image K. Sakthivel, R. Nallusamy, C. Kavitha TW World Academy of Science, Engineering and Technology International Journal of Computer, Electrical, Automation, Control and Information Engineering Vol:8, No:10, 2014
IV Dorigo, Marco & Birattari, Mauro & Stützle, Thomas. (2006). Ant Colony Optimization. Computational Intelligence Magazine, IEEE. 1. pp 28-39. 10.1109/MCI.2006.329691.
V Digital Image Processing and Analysis by Bhabatosh Chanda and Dwijesh Dutta Majumder PDF Online. ISBN 9788120343252 from PHI Learning.
VI Gonzalez, Rafael C., and Richard E. Woods. Digital Image Processing. Upper Saddle River, N.J.: Prentice Hall, 2002.pp700-809
VII M. Haseyama, M. Kumagai and H. Kitajima, “A genetic algorithm based image segmentation for image analysis,” 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258), Phoenix, AZ, USA, 1999,
VIII Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011