Name
Abstract | ||
|---|---|---|
An unsupervised classification technique conceptualized in terms of neural and fuzzy disciplines for the segmentation of remotely sensed images is presented. The process consists of three major steps: 1) pattern transformation; 2) neural classification; 3) fuzzy grouping. In the first step, the multispectral patterns of image pixels are transformed into what we call coarse patterns. In the second step, a delicate classification of pixels is attained by applying an ART neural classifier to the transformed pixel patterns. Since the resultant clusters of pixels are usually too keen to be of practical significance, in the third step, a fuzzy clustering algorithm is invoked to integrate pixel clusters. A function for measuring clustering validity is defined with which the optimal number of classes can be automatically determined by the clustering algorithm. The proposed technique is applied to both synthetic and real images. High classification rates have been achieved for synthetic images. We also feel comfortable with the results of the real images because their spectral variances are even smaller than the spectral variances of the synthetic images examined |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/78.650090 | IEEE Transactions on Signal Processing |
Keywords | Field | DocType |
remote sensing,fuzzy set theory,unsupervised classification technique,coarse patterns,clustering validity,pixel clusters,remotely sensed images,spectral variances,image segmentation,segmentation,art neural nets,fuzzy grouping,neural classification,pattern transformation,image classification,synthetic images,fuzzy clustering algorithm,art neural classifier,geophysical signal processing,multispectral patterns,image pixels,real images,unsupervised learning,fuzzy clustering,heart rate variability,clustering algorithms,neural networks,fuzzy classification,satellites,indexing terms,artificial neural networks | Fuzzy clustering,Computer vision,Pattern recognition,Fuzzy classification,Computer science,Image processing,Image segmentation,Fuzzy set,Pixel,Artificial intelligence,Contextual image classification,Cluster analysis | Journal |
Volume | Issue | ISSN |
45 | 11 | 1053-587X |
Citations | PageRank | References |
3 | 0.88 | 16 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sei-Wang Chen | 1 | 311 | 29.23 |
| Chi-Farn Chen | 2 | 4 | 1.91 |
| Meng-Seng Chen | 3 | 3 | 0.88 |
| Shen Cheng | 4 | 4 | 1.23 |
| Chiung-yao Fang | 5 | 106 | 8.22 |
| Kuo En Chang | 6 | 707 | 70.59 |