本文构造了不同的信息测度来定量描述阶跃边缘的三个本质特征,并给出由相应的三个分量组成的特征向量.用人工得到的样本对一BP神经网络进行训练,将训练后的神经网络直接用于图像的边缘检测.本文方法无需定阈值 在特征的选取上充分考虑了边缘和噪声的本质区别,具有优异的抗噪性能.实验证明本文方法具有令人满意的效果。-In this paper ,from the natural characters of step edge of image, we proposed a feature vector that consists of 3 com2

ponents based on the information measure accordingly. Firstly.a BP neural network is trained with some samples that have been classi2

fied by manual work,and then extract edge proints in a new image using the trained neural network.