RGB Color Histogram Feature based Image Classification: An Application of Rough Reasoning
In this paper, we have proposed a novel rough set based image classification method which uses RGB color histogram as features to classify images of different themes. We have used the concept of discernibility to analyze RGB color values and finding optimum color intervals to discern images of different themes. We have shown how the set of optimum color intervals for training set of images can be used to construct a representative sieve for training set of images to classify new set of images. We have also proposed rough membership based formulation to classify new set of images using representative sieve. The outlines of the system has been implemented and presented along with some results on a set of new images of different themes.
KeywordsTraining Image Image Classification Decision Table Decision Class Optimum Color
Unable to display preview. Download preview PDF.
- 1.Chapelle, O., Haffner, P., Vapnik, V. N.: Support Vector machines for Histogram-Based Image Classification. IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 10(5). SEPTEMBER 1999Google Scholar
- 3.Komorowski, J., Polkowski, L., Andrzej, S.: Rough Sets: A Tutorial. http://www.let.uu.nl/esslli/Courses/skowron/skowron.psGoogle Scholar
- 4.Long, F., Zhang, H., and Feng, D.D.: Fundamentals of Content-based Image Retrieval, Microsoft Research Asia publication, available online at. http://research.microsoft.com/asia/dload_files/group/mcomputing/2003P/ch01_Long_v40-proof.pdf.Google Scholar
- 5.Mrowka, E., Dorado, A., Pedrycz, W., Izquierdo: Dimensionality Reduction for Content-Based Image Classification. Eighth International Conference on Information Visualisation, (IV’04) 435–438Google Scholar
- 6.Mohabey, A., Ray, A. K.: Rough set theory based segmentation of color images. Fuzzy Information Processing Society, 2000. NAFIPS. 19th International Conference of the North American, 338–342 (2000)Google Scholar
- 9.Sergyán, S.: Color Content-based Image Classification. 5th Slovakian-Hungarian Joint Symposium on Applied Machine Intelligence and Informatics, January 25–26, 2007Google Scholar
- 10.Shang, C., Shen, Q.: Aiding Neural Network Based Image Classification with Fuzzy-Rough Feature Selection. 2008 IEEE International Conference on Fuzzy Systems (FUZZ 2008)Google Scholar
- 14.Wang, S.L. Liew, A.W.C.: Information-Based Color Feature Representation for Image Classification. IEEE International Conference on Image Processing (ICIP 2007), Vol. 6. 353–356(Sept. 2007)Google Scholar
- 15.Yun. J., Zhanhuai, L., Yong W., Longbo Z.: A Better Classifier Based on Rough Set and Neural Network for Medical Images. Sixth IEEE International Conference on Data Mining — Workshops (ICDMW’06) 853–857(2006)Google Scholar