基于粒子群优化方法的2维Otsu快速图像分割算法

经典的2维Otsu算法在对图像进行分割时能不依赖于图像的内容，具有较好的适应性，但有着计算复杂度过高和实时性较差的缺点。针对这一问题，提出一种将粒子群算法应用于Otsu图像分割以提高分割速度的方法。实验结果表明，该方法不仅能获得较好的分割效果，而且极大地降低分割时间，能够适应实时性应用的要求。

A fast 2D Otsu image segmentation algorithm based on particle swam optimization algorithm

The classic two-dimensional Otsu image segmentation algorithm is applied widely due to its content-independent characteristic. However, it cannot be applied to real-time system for its high computation complexity. To solve this problem, we present a fast two-dimensional Otsu algorithm, in which particle swarm algorithm is adopted to reduce the computing time. Extensive experiments using real-world images show that our method evidently outperforms the classic Otsu algorithm in segmentation time, while of comparable segmentation performance with the Otsu algorithm. Thus, the improved algorithm satisfies the requirements for real-time applications.