3-D SHAPE FROM A SHADED AND TEXTURAL SURFACE IMAGE

To recover 3-D structure from a natural scene image involving textures, neither the shape-from-shading nor the shape-from-texture analysis is enough because both radiance and texture information coexist within the surface of a natural scene. A new 3-D texture model is developed by considering the scene image as the superposition of a random texture image and a smooth shaded image. The whole image is analyzed using a patch-by-patch process. Each patch is assumed to be a tilted and slanted texture plane. A modified reflectance map function is applied to describe the deterministic part, and the fractional differencing periodic model is chosen to describe the random texture because of its good performance in texture synthesis and its ability to represent the coarseness and the pattern of the surface at the same time. An orthographical projection technique is developed to deal with this particular random model, which has a nonisotropically distributed texture pattern. For estimating the parameter, a hybrid method that uses both the least square and the maximum likelihood estimates is applied directly to the given intensity function. By using these paramters, the synthesized image is obtained and used to reconstruct the original image. The contribution of this research will be in combining shape-from-shading and shape-from-texture techniques to extract 3-D structure and texture pattern features from a single natural scene image that contains both shade and texture in it.