A reconstruction method for ultrasonic deterioration image by the combination of constructive solid geometry and strongly typed genetic programming

摘要

The ultrasonic wave imaging system is effective in extreme environments to record images without being influenced by any optical properties. It is thus necessary to restore the image of the object from a deteriorated image so that the object can be recognized in a search. In a previous study, a neural network was employed as a postprocessor to reconstruct the original object image. However, this method needs to learn the original object image. In this study, constructive solid geometry is combined with genetic programming as a new technique that does not require prior learning. To confirm the effectiveness of this technique, the image of an object from a deteriorated ultrasonic image is reconstructed to the original image.