Weld shape and track precise identification is one of the key problems for automatic welding technology. In this paper, a weld track identification method based on illumination correction and center point extraction is proposed to extract welds with different shapes and non-uniform illumination. Firstly, an image pre-processing algorithm based on illumination correction is designed to eliminate the lighting influence. Secondly, an image extraction algorithm based on iterative threshold segmentation and morphological processing is proposed to obtain a continuous weld binary image. Thirdly, sub-pixel center point extraction algorithm and least-square based polynomial fitting is used to obtain the center fitting curve of welding seam. Experimental results show that the proposed method can realize accurate recognition of welding seam track under different illumination conditions effectively. The recognition error for welding seams with different typical shapes is within 4 pixels, and the average fitting error is less than 1.8 pixels. The welding seam identification and fitting method shows great application potential in the field of automatic assembling and robotic welding.