Summary: In the theory of edge detection of binary images, the classical method is to use regular convolution kernel to construct an edge detect operator, such as Sobel operator, Prewitt operator, Kirsch operator and Roberts operator. The authors propose stochastic filtering to edge detection. Using Order Statistic Filter (OSF) to construct stochastic convolution kernel, the authors yield a new kind of stochastic edge detect operator, the OSF edge operator. The authors carry out the edge detection for radar images and document images, and the experimental results show the efficiency of the OSF edge operator.