Title :
Fuzzy K-NN algorithm using modified K-selection
Author :
Kim, Yoon K. ; Han, Joon H.
Author_Institution :
Dept. of Comput. Sci., Pohang Inst. of Sci. & Technol., South Korea
Abstract :
In this paper, a new K selection method in fuzzy K-NN (nearest-neighbor) algorithm, called the “updated fuzzy K-NN”, is proposed. The main idea of this method is in the selection of K neighbors by considering the distance difference and the membership grade each neighbor has. The classification results of 32 classes of complex images are given. Compared to K-NN, and fuzzy K-NN algorithm, our method showed improved classification rate
Keywords :
fuzzy set theory; image classification; complex images; distance difference; image classification; membership grade; modified K-selection; updated fuzzy K-NN algorithm; Decision theory; Feature extraction; Humans; Nearest neighbor searches; Neural networks; Pixel;
Conference_Titel :
Fuzzy Systems, 1995. International Joint Conference of the Fourth IEEE International Conference on Fuzzy Systems and The Second International Fuzzy Engineering Symposium., Proceedings of 1995 IEEE Int
Conference_Location :
Yokohama
Print_ISBN :
0-7803-2461-7
DOI :
10.1109/FUZZY.1995.409901
