Texture feature is a decisive factor in pattern classification problems because texture features are not deduced from the intensity of the current pixel but from the gray level intensity variations of current pixel with its neighbors. The proposed model uses five discrete levels such as -9,-1, 0, 1 and 9 for characterizing the gray level intensity variations of the center pixel with its neighbors in the local neighborhood of each band in a multispectral image. For land cover classification, the proposed model MBTP has been used along with fuzzy k-Nearest Neighbor (Fuzzy k-NN) classifier.