Title :
Adaptive fuzzy Kohonen clustering network for image segmentation
Author :
Lei, Wang ; Qi Feihu
Author_Institution :
Dept. of Comput. Sci. & Eng., Shanghai Jiaotong Univ., China
Abstract :
Fuzzy Kohonen clustering network (FKCN) is a kind of self-organizing fuzzy neural network. It shows great superiority in processing the ambiguity and uncertainty of image, but it encounters some difficulties when used for image segmentation. To overcome these defects, an adaptive FKCN model is presented in this paper, which can determine the network structure automatically according to the gray level distribution of the image. By using the new fuzzy intensification operator and implementing a sample space transition in the network learning procedure, the network convergence speed is greatly improved and the computation cost of image segmentation is significantly decreased
Keywords :
convergence; fuzzy neural nets; image segmentation; learning (artificial intelligence); self-organising feature maps; adaptive model; convergence; fuzzy Kohonen clustering network; fuzzy neural network; gray level distribution; image segmentation; learning; sample space transition; self-organizing feature maps; Clustering algorithms; Computational efficiency; Computer networks; Convergence; Fuzzy neural networks; Image analysis; Image segmentation; Neurons; Pattern recognition; Uncertainty;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.833498
