Hard and soft classifications by a neural network with a non-exhaustively defined set of classes
Hard and soft classifications by a neural network with a non-exhaustively defined set of classes
Many assumptions are typically made in the course of a supervised digital image classification. The focus of this paper is the commonly made assumption of an exhaustively defined set of classes. This assumption is often unsatisfied, with the imagery containing regions of classes that were not included in training the classification. The failure to satisfy the assumed condition was investigated with reference to hard and soft land cover classifications by a feedforward neural network. The accuracy of these classifications was decreased if a non-exhaustively defined set of classes was used. The exclusion of a class from the training stage resulted in a decrease in the accuracy of a hard classification of agricultural crops of up to 21.2%. Moreover, there were marked differences between the 'real' and 'apparent' accuracies of classifications of up to 15.4%. With soft classifications of urban land cover, the presence of an untrained class also degraded classification accuracy. In the soft classification output, the correlation between the actual and estimated proportional cover of a class declined from r =0.97 to r =0.76 when another class was excluded from the training stage of the classification. Possible means to reduce the negative impacts of untrained classes are considered briefly. Post-classification thresholding of the neural network's output unit activation levels may form the basis of a method to identify and remove cases of an untrained class from a hard classification. Alternatively, supporting information on the typicality of class membership may be used to identify cases representing an area containing an untrained class in both hard and soft classifications and this is illustrated with reference to a soft classification.
3853 -3864
Foody, G.M.
06e50027-603d-4a5b-88f5-af2bb6235a37
2002
Foody, G.M.
06e50027-603d-4a5b-88f5-af2bb6235a37
Foody, G.M.
(2002)
Hard and soft classifications by a neural network with a non-exhaustively defined set of classes.
International Journal of Remote Sensing, 23 (18), .
(doi:10.1080/01431160110109570).
Abstract
Many assumptions are typically made in the course of a supervised digital image classification. The focus of this paper is the commonly made assumption of an exhaustively defined set of classes. This assumption is often unsatisfied, with the imagery containing regions of classes that were not included in training the classification. The failure to satisfy the assumed condition was investigated with reference to hard and soft land cover classifications by a feedforward neural network. The accuracy of these classifications was decreased if a non-exhaustively defined set of classes was used. The exclusion of a class from the training stage resulted in a decrease in the accuracy of a hard classification of agricultural crops of up to 21.2%. Moreover, there were marked differences between the 'real' and 'apparent' accuracies of classifications of up to 15.4%. With soft classifications of urban land cover, the presence of an untrained class also degraded classification accuracy. In the soft classification output, the correlation between the actual and estimated proportional cover of a class declined from r =0.97 to r =0.76 when another class was excluded from the training stage of the classification. Possible means to reduce the negative impacts of untrained classes are considered briefly. Post-classification thresholding of the neural network's output unit activation levels may form the basis of a method to identify and remove cases of an untrained class from a hard classification. Alternatively, supporting information on the typicality of class membership may be used to identify cases representing an area containing an untrained class in both hard and soft classifications and this is illustrated with reference to a soft classification.
This record has no associated files available for download.
More information
Published date: 2002
Identifiers
Local EPrints ID: 14893
URI: http://eprints.soton.ac.uk/id/eprint/14893
ISSN: 0143-1161
PURE UUID: 20f21adf-5d29-4d49-a528-21c0ea297aff
Catalogue record
Date deposited: 09 Mar 2005
Last modified: 15 Mar 2024 05:32
Export record
Altmetrics
Contributors
Author:
G.M. Foody
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics