On-axis deflectometric system for freeform surface measurement.

We propose an on-axis deflectometric system for the accurate measurement of freeform surfaces with large slope ranges. A miniature plane mirror is attached on the illumination screen to fold the optical path and achieve the on-axis deflectometric testing. Due to the existence of the miniature folding mirror, the deep-learning method is applied to recover the missing surface data in a single measurement. Low sensitivity to the calibration error of system geometry and high testing accuracy can be achieved with the proposed system. The feasibility and accuracy of the proposed system have been validated. The system is low in cost and simple in configuration, and it provides a feasible way for the flexible and general testing of freeform surfaces, with a significant potential of the application in on-machine testing.

Phase unwrapping in ICF target interferometric measurement via deep learning.

This paper proposes an unwrapping algorithm based on deep learning for inertial confinement fusion (ICF) target interferograms. With a deep convolutional neural network (CNN), the task of phase unwrapping is transferred into a problem of semantic segmentation. A method for producing the data set for the ICF target measurement system is demonstrated. The noisy wrapped phase is preprocessed using a guided filter. Postprocessing is introduced to refine the final result, ensuring the proposed method can still accurately unwrap the phase even when the segmentation result of the CNN is not perfect. Simulations and actual interferograms show that our method has better accuracy and antinoise ability than some classical unwrapping approaches. In addition, the generalization capability of our method is verified by successfully applying it to an aspheric nonnull test system. By adjusting the data set, the proposed method may be transferred to other systems.