摘要
通过构造不同的统计量定量描述了边缘点邻域灰度的分布特征,并将4个统计量组成统计向量.计算训练图像的统计向量作为样本对BP神经网络训练,然后将训练的BP网络直接用于边缘检测.新方法在统计向量的构造上充分考虑了边缘点和噪声点的区别,具有较好的抗噪性能;BP网络的结构和训练都比较简单;而且不需要设定阈值检测边缘.实验表明,新方法抗噪性能好,达到了令人满意的边缘检测效果.
A new edge detector based on the statistical vector and neural network is Firstly, based on the distribution characters of intensities in the neighborhood of an vector composed of 4 components is proposed. Then through the training with the s presented in the paper. edge pixel, a statistical tatistical vector samples calculated from training images, the BP neural network acquires the function of a desired edge detector. Finally, the trained BP neural network is used for edge detection directly. Experiments are carried out with both noisy artificial and natural images. The proposed edge detector proves robust against noise. Besides, both the architecture and training of the BP neural network are simple. Moreover, the proposed edge detector needs no thresholds for conventional edge detection methods.
出处
《计算机研究与发展》
EI
CSCD
北大核心
2006年第5期920-926,共7页
Journal of Computer Research and Development
基金
国家自然科学基金项目(60172022)~~
关键词
边缘检测
统计向量
统计方法
BP神经网络
神经网络
edge detection
statistical vector
statistical method
BP neural network
neural network
