Mixed pixels, which do not follow a known statistical distribution that could be parameterized, are a major source of inconvenience in classification of remote sensing images. This paper reports on an experimental study designed for the in-depth investigation of how and why two neuro-fuzzy classification schemes, whose properties are complementary, estimate sub-pixel land cover composition from remotely sensed data. The first classifier is based on the fuzzy multilayer perceptron proposed by Pal and Mitra: the second classifier consists of a two-stage hybrid (TSH) learning scheme whose unsupervised first stage is based on the fully self- organizing simplified adaptive resonance theory clustering network proposed by Baraldi. Results of the two neuro-fuzzy classifiers are assessed by means of specific evaluation tools designed to extend conventional descriptive and analytical statistical estimators to the case of multi-membership in classes. When a synthetic data set consisting of pure and mixed pixels is processed by the two neuro-fuzzy classifiers, experimental result show that: i) the two neuro- fuzzy classifiers perform better than the traditional MLP; ii) classification accuracies of the two neuro-fuzzy classifiers are comparable; and iii) the TSH classifier requires to train less background knowledge than FMLP.
[1]
Sankar K. Pal,et al.
Multilayer perceptron, fuzzy sets, and classification
,
1992,
IEEE Trans. Neural Networks.
[2]
A. Karnieli,et al.
A review of mixture modeling techniques for sub‐pixel land cover estimation
,
1996
.
[3]
Ethem Alpaydin,et al.
Simplified ART: A new class of ART algorithms
,
1998
.
[4]
Giles M. Foody,et al.
Estimation of the Areal Extent of Land Cover Classes that Only Occur at a Sub-Pixel Level
,
1996
.
[5]
Robert A. Schowengerdt,et al.
On the estimation of spatial-spectral mixing with classifier likelihood functions
,
1996,
Pattern Recognit. Lett..