Feature-based stereo correspondence techniques suffer from the major limitation that it is difficult to match along epipolar lines and this often results in a sparse set of depth points. Past researchers attempted to solve this problem through trinocular stereo. In this paper, a new method has been proposed for reducing the sparsity of depth points by orienting the epipolar line of the cameras in a direction that maximizes the number of feature points. The corresponding epipolar axis has been termed as the optimal axis. Our analytical as well as simulation results have established that for a limited edge scenario, the proposed approach can lead to considerable improvement in the number of feature points that can be matched. We have introduced a figure-of-merit for the optimal axis and discussed how it is qualitatively related to the variance of the probability density function (pdf). We have also presented the results of our simulation experiment, termed as the random stick experiment. Finally, we have also shown the results of improved reconstructed surface of a synthetic image using optimal axis alignment.