Aiming at solving the problem of manually measuring the fabric surface thickness, this paper proposes a three-dimensional (3D) reconstruction method based on the tangential two-dimensional (2D) sequence images. Firstly, the characteristic region of the fabric surface is extracted. Secondly, the image is splitting based on the maximum between-class variance method. Thirdly, the splitting image is processed by the morphological method. Fourthly, the canny operator is used to obtain the edge detection for calculating the edge contour coordinate. Finally, the surf function is used to reconstruct the 3D model of the fabric surface. To evaluate the performance of the proposed 3D model, the thickness and relief degree of the fabric surface are used, and the comparison between the proposed method and the manual measurement is carried out. The results demonstrate that, under a reasonable relief degree condition, the proposed method is more effective to evaluate the thickness of the fabric surface and the estimated thickness is more accurate than the manually measured one.