Abstract
Recent advances in information sciences are extending classical set theory frontiers into new domains of uncertainty perception, incompleteness, vagueness of knowledge—giving new mathematical approach to development of intelligent information systems. The paper addresses the problem of construction of rough measures in generalized approximation spaces introducing a new method of rough feature thresholding. The algorithm creates rough feature blocks and assigns them image blocks from the block min, avg, max statistics. The algorithm converts data blocks into rough approximations of feature blocks. The introduced solution contributes to the highly precise internal data structure descriptors on one side and constitutes the algorithmic base for rough data analysis entirely embedded in generalized approximation spaces at the same time. The scope of possible applications includes image descriptors, image thresholding, image classifications.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chan, Y.K., Ho, Y.A., Liu, Y.T., Chen, R.C.: A ROI image retrieval method based on CVAAO. Image Vis. Comput. 26(11), 1540–1549 (2008)
Ghali, N., Abd-Elmonim, W., Hassanien, A.: Object-based image retrieval system using rough set approach. In: Kountchev, R., Nakamatsu, K. (eds.) Advances in reasoning-based image processing intelligent systems, intelligent systems reference library, vol. 29, pp. 315–329. Springer, Berlin (2012)
GTSRB: Road signs database. http://benchmark.ini.rub.de/
Lingras, P., Butz, C.: Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification. Inf. Sci. 177(18), 3782–3798 (2007)
Malyszko, D., Stepaniuk, J.: Adaptive rough entropy clustering algorithms in image segmentation. Fundam. Inf. 98(2–3), 199–231 (2010)
Malyszko, D., Stepaniuk, J.: Granular multilevel rough entropy thresholding in 2D domain. In: IIS 2008. pp. 151–160. Zakopane, Poland (2008)
Malyszko, D., Stepaniuk, J.: Adaptive multilevel rough entropy evolutionary thresholding. Inf. Sci. 180(7), 1138–1158 (2010)
Pal, S.K., Peters, J.: Rough fuzzy image analysis: foundations and methodologies. CRC Press Inc, Boca Raton, FL 33487, USA (2010)
Qiang, S., Wangli, C., Qianqing, Q., Guorui, M.: Gaussian kernel-based fuzzy rough set for information fusion of imperfect image. In: ICSP 2014. vol. 284 (2014)
Restrepo, M., Cornelis, C.G.J.: Partial order relation for approximation operators in covering based rough sets. Inf. Sci. 284, 44–59 (2014)
Yao, Y., Yao, B.: Covering based rough set approximations. Inf. Sci. 200, 91–107 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Małyszko, D. (2016). Feature Thresholding in Generalized Approximation Spaces. In: Gruca, A., Brachman, A., Kozielski, S., Czachórski, T. (eds) Man–Machine Interactions 4. Advances in Intelligent Systems and Computing, vol 391. Springer, Cham. https://doi.org/10.1007/978-3-319-23437-3_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-23437-3_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23436-6
Online ISBN: 978-3-319-23437-3
eBook Packages: EngineeringEngineering (R0)