Square groove detection based on Förstner with Canny edge operator using laser vision sensor

Weld seam recognition is critical for providing information for automated welding control, promoting the advancement of welding sensing technology, and improving welding manufacturing automation. The extraction of the square groove’s feature points using a new method is presented in this paper. Noise is produced in significant quantities due to the difficult method used to acquire the weld image. To process images, a specific method must be utilized. In this work, the central line of the laser stripe is extracted based on Canny edge detection with Haralicks facet model. Based on the central line, the Förstner algorithm is used to recognize the corner points of the square weld groove. Following the establishment of a test platform, a series of detection tests for various sizes of the square groove is established. The acquired detection results are sufficiently accurate, with maximum relative errors of less than 3.19%, demonstrating the rationale of the suggested visual sensor’s physical design and the validity of the proposed detection algorithms.