中文摘要：

针对印刷电路板（PCB）光电图像在获取过程中含有噪声和较模糊的边缘等各种原因，提出了一种基于图像融合的含噪声且较模糊PCB光电图像边缘检测方法。首先，讨论了基于小波变换及Canny边缘检测算子的图像边缘检测法，分析了其基本原理。然后，结合两种方法的优点，提出了基于图像融合检测方法的PCB光电图像边缘检测基本原理及中值滤波、增强去模糊、小波分解、图像融合、图像去噪等步骤。最后，将由CCD成像系统及显微镜获取的主要含有高斯噪声且较模糊的PCB光电图像用三种检测方法进行了主观实验对比，采用本文融合方法得到的边缘图像效果最好，在抑制噪声的同时得到了连续的边缘；为了客观地评价PCB光电图像边缘检测的效果，用峰值信噪比及图像边缘信息熵作为评价指标，采用本文方法的峰值信噪比及信息熵的实验结果值都是最大的。

英文摘要：

Owing to printed circuit board （PCB） photoelectricity images contain noisy and darker edge during the capture, an edge detection method for noisy and darker PCB photoelectricity image based on image fusion is proposed in this paper. Firstly, the edge detection method based on wavelet transform and Canny edge detection operator is discussed in detail,and its basic principle is analyzed. Secondly, combining with both advantages, the edge detection for PCB photoelectricity image based on image fusion is proposed,and the process of edge detections such as median fitter, image enhancement removing faint- ness, wavelet decomposing, image fusion,image donising, is also demonstrated. Finally, the subjective ex- periment comparisons among the three edge detection methods for noisy and darker PCB photoelectrieity images acquired by CCD imaging system and microscope are realized, and the result by adopting the method of image fusion is the best. To evaluate the results of edge detection for PCB photoelectricity image objectively, we use peak signal to noise ratio and information entropy as evaluation means, and the experiment results show that the peak signal to noise ratio and information entropy are the highest by a- dopting the method in this paper.