Image Enhancement for the 3-D Reconstruction in the Uncontrolled Environment using Shape from Silhouette

Abstract

Among the multiple models for 3-D shape reconstruction, Shape from silhouette (SFS) is one of the fast and simple 3D shape rendering techniques as compare to other approaches. In SFS model multiple images captured from different viewpoints in a controlled environment are used as input data at the front end to extract silhouette and are free of noises. Silhouette extraction from such well-defined input data is easy and accurate, having no loss of information while extracting the silhouette. On the other hand images from uncontrolled environment involve many degradation factors. Common and frequently degradation factors are motion blur and noise addition which effects acquired image quality, illumination and resolution seriously. The proposed work is an effort to extract useful information from such environmentally variant images. The successful reconstruction of the image is main emphasis.