Title :
Classifier performance for SAR image classification
Author :
Manian, Vidya ; Hernandez, Roger ; Vasquez, Ramon
Author_Institution :
Dept. of Electr. & Comput. Eng., Puerto Rico Univ., Mayaguez, Puerto Rico
Abstract :
Classifier robustness is important for classification of remote sensing images. This paper investigates the use of the supervised maximum likelihood (ML) classifier and the unsupervised K-means algorithm. Classifier adaptability to other data sets is considered. Also, a method is presented to fuse classifiers for better performance with application to SAR images. The performance of neural network classifier such as the learning vector quantization (LVQ) technique is also studied and is used in the classifier integration algorithm. The paper presents results with SAR images
Keywords :
geophysical signal processing; geophysical techniques; geophysics computing; image classification; maximum likelihood estimation; neural nets; radar imaging; remote sensing by radar; synthetic aperture radar; terrain mapping; SAR; classifier integration algorithm; classifier performance; geophysical measurement technique; image classification; land surface; learning vector quantization; neural net; neural network; radar remote sensing; robust method; robustness; supervised maximum likelihood classifier; synthetic aperture radar; terrain mapping; unsupervised K-means algorithm; Artificial neural networks; Clustering algorithms; Image classification; Iterative algorithms; Machine learning algorithms; Maximum likelihood estimation; Neural networks; Oceans; Sea measurements; Vector quantization;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2000. Proceedings. IGARSS 2000. IEEE 2000 International
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-6359-0
DOI :
10.1109/IGARSS.2000.860453
