Image Segmentation is an immensely important task in Digital Image Processing. It is used in many fields including Medical Imaging, Machine vision, recognition tasks, etc. Many techniques have been proposed to carry out segmentation. Some of them are K Means, Image segmentation using Arithmetic Mean method, Segmentation via Entropy & histogram, Image segmentation using Maximum Between-cluster Variance and so on. This work proposes a novel Genetic Algorithms based image segmentation technique which may produce better results. A new Fitness function based on Entropy has been introduced. In order to check quality of segmented image, a performance evaluation measure is also presented. The proposed technique has been implemented on various images. Two existing approaches K Means and Arithmetic Mean have been thoroughly studied and implemented on same images. The results of proposed technique are then compared by the results of existing approaches using the introduced performance measure Entropy. Entropy measures the image information content. Greater the entropy, more information can be obtained from image. In comparison to the existing techniques, the proposed approach gives encouraging results.

Image Segmentation, Genetic Algorithms

[1] Shapiro and Stockman, “Computer vision”, Pearson publication, 1st edition, 2001.
[2] P. Umorya1 , R. Singh, “A Comparative Based Review on Image Segmentation of Medical Image and its Technique”, International Journal of Computer Sciences and Engineering, Vol.5, Issue.2, pp.71-76, 2017.
[3] Pham, Dzung L.; Xu, Chenyang; Prince, Jerry L, "Current Methods in Medical Image Segmentation", Annual Review of Biomedical Engineering, 2000, pp: 315–337.
[4] Mihai Ivanovici Ivanovici, Noël Richard and Dietrich Paulus, “Advanced Color Image Processing and Analysis”, Springer, 2012, pp 219-277.
[5] Mathew, J., & Vijayakumar, R, “Scalable parallel clustering approach for large data using parallel K means and firefly algorithms”, International Conference on High Performance Computing and Applications (ICHPCA) (pp. 1–8). IEEE, 2014.
[6] Kuo, R. J., Syu, Y. J., Chen, Z.-Y., & Tien, F., “Integration of particle swarm optimization and genetic algorithm for dynamic clustering” Information Sciences, 2012, pp.124–140.
[7] Padhy, N.P. and Simon, S.P., “Soft Computing: With Matlab Programming”, Oxford, 2015, ISBN: 9780199455423, 0199455422. Edition: 1st Edition.
[8] Ketna Khanna, Naresh Chauhan and Vedpal, “Genetic Algorithms based Black Box Testing”, International Journal of Emerging Technologies and Innovative Research, 2018, pp. 537- 544.
[9] Dorigo, M. and Krzysztof Socha, “Approximation Algorithms and Metaheuristics”, IRIDIA Institut de Recherches Interdisciplinaires et de Du00b4eveloppements en Intelligence Artiufb01cielle publisher, 2006, pp. 1-25.
[10] Goldberg, D., “Genetic Algorithms in search, Optimization and Machine Learning”, Addison-Wesley publishing co., 1989, pp.1-21.
[11] S. Josephine,” Brain Tumor MRI Image Detection and Segmentation Using Genetic Algorithm”, International Journal of Computer Sciences and Engineering, Vol.6, Issue.2, pp.358-364, 2018.
[12] Ya Wang, “Improved OTSU and Adaptive Genetic Algorithm for Infrared Image Segmentation”, The 30th Chinese Control and Decision Conference, 2018, pp. 5644-5648.
[13] Pathak S, “Optimized Noisy Image Segmentation Using Genetic Algorithm”, International Conference on Intelligent Computing and Control Systems ICICCS, 15-16 June 2017, Madurai, India, pp. 1311-1316.
[14] Maulik U, “Medical Image Segmentation Using Genetic Algorithms”, IEEE Transactions on Information Technology in Biomedicine ( Volume: 13 , Issue: 2 , March 2009 ), 2009, pp. 166-173.
[15] Yide Ma, Kun Zhan and Zhaobin Wang,“Applications of Pulse-Coupled Neural Networks”, Higher Education Press, Beijing and Springer-Verlag Berlin Heidelberg, 2010, pp.1-9.
[16] Brzoza A et. al, “An approach to image segmentation based on shortest paths in graphs”, IEEE, 2017.
[17] Akinina A et. al., “Multiscale Image Segmentation using Normalized Cuts in Image Recognition on Satellite Images”, IEEE, 2018.
[18] Li Y et. Al, “Grab Cut Image Segmentation Based on Image Region”, IEEE, 2018.
[19] Wilhelm T et. al., “Boundary aware image segmentation with unsupervised mixture models”, IEEE, 2017.
[20] Sui H et. al., “Automatic Image Registration Based on Shape Features and Multi-Scale Image Segmentation”, IEEE, 2017.
[21] Zhang R et. al., “The Development of Markov Random Field Theory and Applications on Image Segmentation Algorithm”, IEEE, 2016.
[22] Meinhold R et. al., “Efficiently Computing Piecewise Flat Embeddings for Data Clustering and Image Segmentation”, IEEE, 2016.
[23] Xu W et. al., “Ensemble of active contour based image segmentation”, IEEE, 2017.
[24] Krishna T et. al., “Three Phase Segmentation Algorithm for High Resolution Satellite Images”, IEEE, 2016.
[25] Ahmadi S et. al., “Enhance Support Relation Extraction Accuracy Using Improvement Of Segmentation In RGB-D Images”, IEEE, 2017.
[26] H. T. T. Binh, M. D. Loi and N. T. Thuy, "Improving Image Segmentation Using Genetic Algorithm", 11th International Conference on Machine Learning and Applications, Boca Raton, pp.18-23, 2012
[27] Gao H., “The applications of image segmentation techniques in medical CT images”, IEEE, 2011.
[28] Dhiraj Kumar, M. Tech Thesis, National Institute of Technology, Rourkela, 2009.
[29] Last, M. et. al., “Effective black box testing via genetic algorithms”, Springer-Verlag Berlin Heidelberg, 2006.
[30] Malhotra, R. et. al., “Genetic Algorithms: Concepts, Design for Optimization of Process Controllers”, 2011, Vol. 4, No. 2.
[31] Stender, J., “Introduction to genetic algorithms”, IEEE, 2004.
[32] Fischer, M. and Tonjes, R., “Generating test data for black box testing using Genetic Algorithm”, Conference: Emerging Technologies & Factory Automation (ETFA). IEEE 17th Conference, 2012. [33] Hatem, M., “Solving large problems with heuristic search: general-purpose parallel external-memory search”, Journal of Artificial Intelligence Research 62, 2018.