Defect detection of optical elements surfaces using curvelet transform

The complex components often require a variety of processes in the manufacturing process, such as turning, milling, grinding, polishing etc. Therefore, it is inevitable to produce defect features on the surface of the component. The defective surfaces will directly affect the performance of the entire component, so it must be identified during production and inspection. In this paper, based on the excellent curve feature recognition and sparse representation of curvelet transform, a defect extraction method based on the curvelet transform for feature separation in transform domain is proposed. The effectiveness of the method is proved by simulation results and experimental examples.