Feature extraction for neural network classifiers using wavelets and tree structured filter banks

Two feature extraction methods are considered for neural network classifiers. The first feature extraction method is based on translation-invariant wavelet transformation. The wavelet transformation transforms a signal from the time domain to the scale-frequency domain and is computed at levels with different time/scale-frequency resolution. The second feature extraction method is based on tree structured multirated filter banks. The tree structured filter banks can be tailored for multisource remote sensing and geographic data. In experiments, the proposed feature extraction methods for neural networks performed well in classification of multisource remote sensing and geographic data.