Abstract
Image segmentation is one of the main tasks for many computer vision problems. In this paper, a GPU acceleration for a Fractal features extraction method is proposed, followed by our neuro-morphological approach that will allow to segment the images based on the Fractal texture features. In the first step, we use the CUDA environment on an NVIDIA GPU to compute the Fractal features in parallel for each pixel of our image, this makes it possible to optimize the extraction phase before starting the image segmentation by using our approach which is divided into two main steps. Firstly, we train a Kohonen self-organized Map (KSOM) using the extracted features. In the final step, we use our watershed method to extract the modals regions from the KSOM, these regions define the final regions found in the segmented image. To highlight the effectiveness of our parallel implementation, the performance results of the GPU extraction method are compared to his sequential counterpart based on CPU. In addition, the segmentation rate of the proposed approach is compared to the K-means results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Salem, M.A.M., Atef, A., Salah, A., Shams, M.: Recent survey on medical image segmentation. In: Computer Vision: Concepts, Methodologies, Tools, and Applications, pp. 129–169 (2018)
Dhanachandra, N., Chanu, Y.J.: A survey on image segmentation methods using clustering techniques. Eur. J. Eng. Res. Sci. 2(1), 15–20 (2017)
Zaitoun, N.M., Aqel, M.J.: Survey on image segmentation techniques. Procedia Comput. Sci. 65, 797–806 (2015)
Salhi, K., Jaara, E.M., Alaoui, M.T.: Texture image segmentation approach based on neural networks. Int. J. Recent Contrib. Eng. Sci. 6(1), 19–32 (2018)
Salhi, K., Jaara, E.M., Alaoui, M.T., Alaoui, Y.T.: Color-texture image clustering based on neuro-morphological approach. IAENG Int. J. Comput. Sci. 46(1), 134–140 (2019)
Mandelbrot, B.B.: The Fractal Geometry of Nature/Revised and Enlarged Edition. WH Freeman and Co., New York (1983). 495 p.
Chaudhuri, B.B., Sarkar, N.: Texture segmentation using fractal dimension. IEEE Trans. Pattern Anal. Mach. Intell. 17(1), 72–77 (1995)
Nvidia, C. U. D. A. Programming guide (2010)
Sanders, J., Kandrot, E.: CUDA by Example: An Introduction to General-Purpose GPU Programming. Addison-Wesley Professional, Boston (2010)
Kohonen, T.: Essentials of the self-organizing map. Neural Netw. 37, 52–65 (2013)
Parzen, E.: On estimation of a probability density function and mode. Ann. Math. Stat. 33(3), 1065–1076 (1962)
Brodatz, P.: Textures: A Photographic Album for Artists and Designers. Dover Pubns, Mineola (1966)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Salhi, K., Jaara, E.M., Alaoui, M.T. (2020). CUDA Accelerating of Fractal Texture Features for a Neuro-morphological Image Segmentation Approach. In: El Moussati, A., Kpalma, K., Ghaouth Belkasmi, M., Saber, M., Guégan, S. (eds) Advances in Smart Technologies Applications and Case Studies. SmartICT 2019. Lecture Notes in Electrical Engineering, vol 684. Springer, Cham. https://doi.org/10.1007/978-3-030-53187-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-53187-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-53186-7
Online ISBN: 978-3-030-53187-4
eBook Packages: Computer ScienceComputer Science (R0)