Abstract: To obtain the pattern of jacquard warp-knitted fabric quickly and accurately, a new approach to texture segmentation of jacquard warp-knitted fabric based on wavelet transform and Gaussian markov random field is proposed in this paper. Firstly the paper analysises texture characters and formation reason of jacquard warp-knitted fabric in theory. Secondly the problems of variable scaling vectors, parameter estimation and image segmentation in GMRF are studied systematically. The perform of the above presented algorithm is verified with with Matlab program. The experimental results show that this approach is a feasible way for texture segmentation of jacquard fabric.