基于BP神经网络图像分割算法研究

摘要

In this paper,a new image segmentation method based on BP neural network is proposed.The basic idea of BP neural network is to determine the connection between nodes and weights.And then the new input image data is seg-mented by the trained neural network.Experiments show that the proposed algorithm can segment the image effectively and improve the segmentation speed compared with other image segmentation methods.%传统的图像分割算法提取的图像质量差,提出了一种基于BP神经网络的图像分割方法.BP神经网络的图形分割方法的基本思想是通过训练,以确定节点间的连接和权值.再用训练好的神经网络对新输入的图像数据进行分割.实验表明:相对于其它图像分割方法,该算法能有效地分割图像,提高了分割速度.