Owing to printed circuit board (PCB) photoelectricity images contain n oisy and darker edge during the capture,an edge detection method for noisy and d arker PCB photoelectricity image based on image fusion is proposed in this paper.Firstly,the edge detection method based on wavelet t ransform and Canny edge detection operator is discussed in detail,and its basic principle is analyz ed.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 enhance ment removing faintness, wavelet decomposing,image fusion,image donising,is also demonstrated.Finally,the subjective experiment comparisons among the three edge detection methods for noisy and darker PCB photoelectricity images acquired by CCD imaging system and microscope are realized,and the res ult 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 sig nal 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 adopting the method in this p aper.