摘要： 提出了一种基于图割理论和极几何约束的图像匹配算法。利用极几何约束对两幅待匹配图像进行矫正，使得它们的极线处在同一扫描线上，从而将二维匹配简化成一维匹配；利用基于图割的一维匹配算法获取视差数据，此时匹配中能量函数的标号是一维的，大大减少了搜索范围，并且提高了匹配的速度。

关键词: 图割, 极几何约束, 标号, 视差

Abstract: An algorithm for images matching based on graph cut and epipolar geometric constraint is proposed. The two original images are rectified by epipolar geometric constraint to make their epipolar lines parallel to the scan-lines. So the 2D matching of images is simplified to that of 1D. Then the matching disparities can be gained by the 1D matching algorithm based on graph cut. The label is 1D in the energy function. Therefore, the searching range is greatly decreased, and the rate of matching is improved.

Key words: Graph cut, Epipolar geometric constraint, Label, Disparity