本文提出了用改进的Kohonen神经网络进行图像自动分割的方法。实验表明该方法不仅能使复杂背景中的目标被较好地提取出来,而且处理速度快,为图像序列分析中运动目标的实时提取工作奠定了良好的基础。 In this paper, a method of automatic image segmentation using improved Kohonen neural network is proposed. Experiments show that this method not only can make the target in complex background be well extracted, but also has a fast processing speed, which lays a good foundation for the real-time extraction of moving targets in image sequence analysis.