摘要
图像分割是计算机视觉领域中的经典问题之一,基于图论的分割算法因其良好的时间性能与分割效果成为众研究者新的关注点。论文在对图像分割算法综述的基础上,重点介绍了基于图论的分割算法并且通过实际仿真分别从时间性能与分割效果上对Grab Cut与One Cut算法进行了比较。最后对当前该领域存在的问题与发展方向进行了总结。
In the field of computer vision, image segmentation is one of the classical problems. Because of its good time performance and segmentation results, the segmentation algorithm based on graph theory has become a new focus for the researchers. On the basis of the summary of image segmentation algorithm, this paper focuses on the segmentation algorithm based on graph theory and compares the Grab Cut and One Cut algorithms from the time performance and the segmentation results. Finally, the existing problems and the development direction of this field are summarized.
出处
《计算机与数字工程》
2016年第10期2043-2047,共5页
Computer & Digital Engineering
关键词
图像分割
能量优化
迭代最小化
最优二元分割
image segmentation, energy optimization, iterative minimization, optimal two partition
