The purpose of image segmentation is to partition an image into homogeneous regions. Features are of major importance in image segmentation. In this work, a new method is proposed in which features used for segmentation are reflection coefficients of the two-dimensional(2-D) orthogonal lattice filters. Principal Component Analysis (PCA) is applied to the features for reducing the complexity of the work. A minimum distance classifier is used in the classification algorithms. The proposed method is compared with the discrete wavelet transform which is a common segmentation algorithm. In our work, selected image is a monospectral optical image.