Image Conversion from Planar into Stereo: Random Variables

It´s significant to convert a planar image into a stereo one. In this paper we used a method which needs to segment an image into sub-blocks to realize this kind of conversion; parameters such as random variables were used to control the procedure. We presented two quantitative criterions, cross-entropy and root-mean-square error, to evaluate the stereo effect. Furthermore, the stereo effect that the random variables take on was thoroughly discussed. The results of the experiment show that, (i) when each random variable has the same distribution, different values of these random variables affect little the stereo effect; (ii) when different distributions are applied to the random variables, the cross-entropies or root-mean-square errors are slightly different, which indicate different distributions have a little influence on the stereo effect. Commonly, we recommend normal distribution for better stereo effect