结果证明，本文的算法具有良好的视差计算准确性和较低的计算时间复杂度。
The experiment result proves that this strategy can get good accuracy disparity image.
一般采用缺陷边缘或缺陷形状中心作为匹配点进行视差计算，实验表明此类方法具有很大误差。
The edge or shape center of the defect is often adopted as matching points. But experimental results show that the methods can bring great errors.
并针对图像的深度连续性约束，定义了一个反映图像自身特征的新能量函数，应用于图割算法，提高了视差计算精度。
Moreover, to improve the disparity accuracy, a novel energy function is well designed to restrict the depth-continuity of an image and applied to the Graph Cut algorithm to describe the image feature.
应用推荐