Abstract: Aiming at the problems of low efficiency and poor accuracy of existing weld quality detection methods, this paper proposes a weld quality detection and evaluation method based on the binocular phase-shifting technique. The point clouds of weldment with weld are first obtained based on the four-step phase-shifting method and the principle of binocular vision. Secondly, the model combining “rough extraction” and “fine extraction” is adopted to extract the weld point clouds from the weldment point clouds. Then, the ridge line of the weld point clouds is extracted and the direction line of the ridge line is fitted by the cubic B-spline curve fitting algorithm, and the cross-section point clouds of the weld are extracted accordingly. Finally, the multi-dimensional quantitative evaluation index system of weld quality is constructed and the objective evaluation of weld forming quality is completed based on the geometric characteristics of cross-section point clouds. The weld point clouds acquisition system was established and experiments were conducted. The maximum deviation of the weld width obtained in the experiment is 0.287 mm, and the minimum deviation is 0.105 mm. Experimental results indicate that the proposed method can be applied to the detection and evaluation of various types of welds, and has the advantages of strong stability and high precision, which can meet the application requirements of high-precision weld quality detection and evaluation in industrial field.