Title :
Type 2 fuzzy sets and neuro-fuzzy clustering of radiographic tibia images
Author :
John, R.I. ; Innocent, P.R. ; Barnes, M.R.
Author_Institution :
De Montfort Univ., Leicester, UK
Abstract :
This paper is concerned with pre-processing of data for submission to neural networks. In particular the use of type 2 fuzzy sets to assist in this process is discussed and the results of using type 2 sets with FuzzyART is presented for clustering of radiographic tibia images. These results indicate that the approach outperforms a type 1 approach, for certain tibia problems, and that the type 2 solution assisted the expert in analysing a set of images that he/she was unable to classify originally
Keywords :
fuzzy neural nets; fuzzy set theory; image classification; medical image processing; radiography; FuzzyART; clustering; fuzzy neural networks; image analysis; neuro-fuzzy clustering; radiographic tibia images; tibia stress fractures; type 2 fuzzy sets; Biomedical imaging; Bones; Engines; Fuzzy sets; Image analysis; Injuries; Neural networks; Radiography; Stress; Torque;
Conference_Titel :
Fuzzy Systems, 1997., Proceedings of the Sixth IEEE International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7803-3796-4
DOI :
10.1109/FUZZY.1997.619744
