Region-based techniques have been scarcely used in stereo vision compared with edge-based techniques or area-based techniques. This is due mainly to the fact that the results of segmentation methods may vary significantly from one image to another, which makes the matching of regions more difficult. We present a novel matching technique where only one of the images is segmented, and correspondences are searched in the other image by means of the minimization of an energy function and the application of some constraints on the depth of the regions. In this technique, correspondences, three-dimensional reconstruction and occlusions are obtained in an only cooperative process. Results using a constant depth constraint are presented, which encourage us to generalize the method to other cases (any type of planar surfaces, curved surfaces) in the near future.