Image match algorithm through correlation coefficient computation in micro stereovision

Abstract

In this paper, an algorithm through correlation coefficient computation is proposed for stereo matching of color images in micro stereovision. In this algorithm, the samples of matching output are acquired by the statistics of multi similarity measurements and multi-matching areas. On the other hand, the false matching results and the wrong matching results are partially filtered by performing the mean-square error statistics of matching output samples. Further more, a sub-pixel matching accuracy is expected by calculating the average values of two new samples derived from the mean-square error statistics. Another problem correlative with stereo matching algorithms, the performance evaluation of algorithms, is also discussed by considering the following parameters, CMSE value, valid scale, accuracy and single-pixel accuracy, etc al. The experiment results show that the stability and accuracy of stereo matching are partially improved after using multi similarity measurements and multi-matching areas, and an accurate degree 80% is obtained when mean-square error of noise is less than the value 20.