Texture is a very important research field of machine vision. From application perspective, texture is widely used in the field of automatic detection, medical image processing, and document processing and remote sensing. Texture recognition has been widely used, and the research of texture recognition is of great significance. According to the condition of the Technical development and the feasibility of the arithmetic, the subject used Gray co-occurrence matrix method which belongs to the statistical method to achieve. Gray co-occurrence matrix method is based on the second-order conditional probability density function of the estimated image. First, compute the gray co-occurrence matrix of 4 angles from the gray image. Then, compute the probability of every pair pixel in the gray co-occurrence matrix. Finally, compute the 5 Characteristic values according to the formula of energy, entropy, inertia matrix, correlation, and local balance. The recognition system done by this way can calculate the Characteristic value of texture image accurately, and is very effective to recognize texture. This also proves that the co-occurrence matrix method is a very effective method to recognize texture.