基于BP网络的工业CT图像边缘检测  

Edge Detection of Industrial Computerized Tomography Based on BP Neural Network

作　　者：刘长江[1] 吴旭凌[2] 

机构地区：[1]四川理工学院数学系,四川自贡643033 [2]四川理工学院外文系,四川自贡643033

出　　处：《四川理工学院学报（自然科学版）》2008年第1期47-49,共3页Journal of Sichuan University of Science & Engineering(Natural Science Edition)

摘　　要：采用改进的BP算法,实现工业CT图像的边缘检测。本文构造了学习样本,可以在较短时间内训练得到权值矩阵,从而实现二值图像边缘检测。并在此基础上,综合灰度图像各位面的边缘提取结果,实现对灰度图像的边缘检测。通过对发动机CT图像的实验,证明利用本文得到的权值矩阵用于边缘检测,泛化性较好,抗噪能力强,能得到较为连续精细的边缘。In this paper,the improved BP algorithm is proposed for edge detection of industrial CT images. And the samples exemplifying how to acquire the BP algorithm in a short time span are provided. With help of the obtained weighted matrix the significance of the algorithm is that the edge of binary images can be detected through the process. Furthermore, first divide each gray-scale image into 8 binary planes with different gray level, and then naturally the images surface up through synthesizing the edge of each binary plane. Applying the method to indus- trial CT images＇ edge detection, fine continuous edge can be acquired, the virtues of which lies in its strong resistance against noise pollution and can be widely adopted in practice.

关 键 词：BP算法 边缘检测 CT 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]