Synthetic Roof Image Generation using an Extended Gaussian Mixture Model (EGMM)
Abstract
In this paper, we address the problem of generating synthetic images by using a single image, or multiple images,
and present an effective Extended Gaussian Mixture Model (EGMM). We apply this method to roof surface images for
investigating and identifying differences, changes, and/or structural damage. This technique allows a single impression of a
roof to be randomly generated according to input parameters, and can produce new image models using multiple roof
images. We further extend GMMs by mixing color textures of the roof images to generate new models. The best fit statistical
model image is obtained by finding the minimum pixel distances as compared to the original image. This approach generates
very realistic roof models that are useful in performance evaluation and testing, and offers the potential for further research
and application in other surface inspection processes.
Downloads
Author(s) and co-author(s) jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties, and that the Article has not been published elsewhere. Author(s) agree to the terms that the IJRDO Journal will have the full right to remove the published article on any misconduct found in the published article.
