针对差影法弹孔目标检测存在过检、漏检、易受噪声干扰和对成像条件要求高等问题，提出了一种基于融合技术的小波变换的弹孔目标检测算法。在小波域中，对低频和高频子图像分别采用不同的融合规则修正弹孔目标的小波变换系数，加大目标的小波变换系数，减小或者置0非目标的小波变换系数，再分别进行模极大法和小波降噪处理，最终经小波逆变换后得到只包含弹孔目标的图像。实验结果表明，该算法用于弹孔目标检测，不仅克服了差影法存在的易受干扰的问题，而且弹孔边缘清晰、连续，提高了弹孔检测的准确性和精确性。

The bullet holes detection using image difference technology has the problems of over-detection, leak-detection, being sensitive to noise interference and harsh request for imaging condition. A bullet hole object detection method based on wavelet transform using fusion rules was proposed to overcome the limitations. In the wavelet domain, different fusion rules were applied to the low-frequency and the high-frequency sub-images to revise the wavelet transform coefficients, for increasing the object coefficients while decreasing or resetting the non-object coefficients. Then, it used the maximum points to the low-frequency coefficient and reduced the noise of high-frequency coefficients. The final bullet holes images were obtained through invert wavelet transform. Experimental results show that : the method can overcome the shortcomings of the image difference method, obtain images of bullet holes with clear edge, and improve the veracity and precision of the bullet holes detection.