In order to locate and segment the image of grain bags in the granary reserves, and making full use of the spatial location information of grain bags, a threshold method is proposed base on two-dimensional Fisher criterion. Firstly, a two-dimensional histogram is obtained by the gray value and the local average gray value of the pixels. Then, the two-dimensional Fisher criterion function value is determined from the two-dimensional histogram. When the maximum function value is obtained, the pair of gray values is the threshold which can be the optimal threshold value. Since the traditional two-dimensional Fisher algorithm is always time-consuming in processing image, a novel and efficient algorithm is proposed to reduce the computational complexity by introducing a fast classification program. Experimental results indicate that the two-dimensional Fisher method which can distinguish the various grain bag regions efficiently and reduce the computation time greatly gives a steady performance.