A neuro-wavelet supervised classifier is proposed for land cover classification of multispectral remote sensing images. Features extracted from the original pixels using wavelet transform (WT) are fed as input to a feed forward multi-layer perceptron (MLP). A set of wavelets from different groups have been used and it is found that biorthogonal3.3 wavelet performs better. The performance is evaluated on a set of remote sensing images using two quantitative indices (\beta index of homogeneity and Davies-Bouldin (DB) index for compactness and separability of classes).