Search

Metal additive manufacturing (AM) provides a platform for microstructure optimization via process control, the ability to model the evolution of microstructures from changes in processing condition or even predict the microstructures from given processing condition would greatly reduce the time frame and the cost of the optimization process. In 1, we present a deep learning framework to quantitatively analyze the microstructural variations of metals fabricated by AM under different processing conditions. We also demonstrate the capability of predicting new microstructures from the representation with deep learning and we can explore the physical insights of the implicitly expressed microstructure representations. We validate our framework using samples fabricated by a solid-state AM technology, additive friction stir deposition, which typically results in equiaxed microstructures. In 2, we further improve and generalize the generating framework, a set of metrics is used to quantitatively analyze the effectiveness of the generation by comparing the microstructure characteristics between the generated samples and the originals. We also take advantage of image processing techniques to aid the calculation of metrics that require grain segmentation.

Textures are used widely in computer graphics to represent fine visual details and produce realistic looking images. Often it is necessary to remove some foreground object from the scene. Removal of the portion creates one or more holes in the texture image. These holes need to be filled to complete the image. Various methods like clone brush strokes and compositing processes are used to carry out this completion. User skill is required in such methods. Texture synthesis can also be used to complete regions where the texture is stationary or structured. Reconstructing methods can be used to fill in large-scale missing regions by interpolation. Inpainting is suitable for relatively small, smooth and non-textured regions. A number of other approaches focus on the edge and contour completion aspect of the problem. In this thesis we present a novel approach for addressing this image completion problem. Our approach focuses on image based completion, with no knowledge of the underlying scene. In natural images there is a strong horizontal orientation of texture/color distribution. We exploit this fact in our proposed algorithm to fill in missing regions from natural images. We follow the principle of figural familiarity and use the image as our training set to complete the image.