Edge detection directly affects the accuracy of image measurement. In this paper, focusing on the edge detection of the image of mechanical part polluted by hybrid noise consisting of Gaussian noise and impulse noise, an adaptive edge detection method is proposed. The proposed method combines a new hybrid filter smoothing noise adaptively with Canny operator to avoid the conflict of Canny operator between noise removing and edge locating, and uses Otsu threshold selection method to determine Dual-threshold of Canny operator adaptively. Using the gauge image polluted by hybrid noise as experiment object, the performance of the proposed method is evaluated qualitatively and quantitatively. Experimental results show that the proposed edge detection method has good performance.