Segmenting Geometric Reliefs from Textured Background Surfaces

Abstract

Fig. 1: A pen container showing a relief on a textured background and a corresponding segmentation.ABSTRACT Segmentation of geometric reliefs from a textured background has various applications in reverse engineering. We consider two approaches to solve this problem. The first classifies parts of a surface mesh as relief or background, and then uses a snake which moves inwards towards the desired relief boundary, which is coarsely located using an energy based on the classification. The second approach initially smoothes the surface to eliminate the background texture, and locates the snake at the relief boundary using an energy based on the step between the background and the relief.Both snakes start at simple user-drawn contours, and are driven towards the relief boundaries by the snake energy functional. In both cases, the snake has different evolution phases with different energy terms, to initially rapidly drive the snake towards the relief boundary, and to later accurately match it.To describe geometric textures, we analyze surface differential properties, and integral and statistical quantities based upon them, computed at multiple scales taken over local neighborhoods, following similar ideas from image texture processing. For classification, we use a support vector machine together with sequential forward floating search for feature selection. A straightforward Laplacian method is used for smoothing.We use example scanned models to demonstrate that both approaches are useful, but are suitable for different types of model.

Computer Assisted Relief Generation—A Survey

“…If the underlying surface is not smooth but textured, the extraction becomes more challenging. Two remedies for this case are presented in [LMLR07b].…”

“…If the underlying surface is not smooth but textured, the extraction becomes more challenging. Two remedies for this case are presented in [LMLR07b]. Snake-like approaches, like the above ones, are able to adapt to concave sculptures but they fail to detect the background within a relief if the foreground surrounds it.…”

Relief extraction and editing

“…While at times the relief may lie on a simple base surface such as a plane, a cylinder, or a surface of revolution, which can readily be estimated, in many other cases the base surface is unknown [1]. Starting from an initial user-drawn contour loosely enclosing the relief (a snake), Liu et al [1,2,3,4] gave a series of algorithms to separate reliefs from their underlying surfaces, both for smooth and textured backgrounds. Zatzarinni showed how to automatically extract reliefs by defining a height function along the base surface normals, the latter being adaptively estimated using local geometric features computed via experimentally determined coefficients [5].…”

Segmenting Periodic Reliefs on Triangle Meshes

“…More complex, in terms of processing, are reliefs lying on a textured background. We have already addressed the segmentation problem-separating the relief from the underlying background-for such cases in [1] and [2].…”

“…The relief's outer boundaries can be detected using our previous segmentation methods: see [1] for the smooth background case, and [2] for textured backgrounds. These methods separate reliefs from their underlying surface using an active contour (or snake) driven by energy terms based on two significant relief characteristics, the raised step at the relief boundary, or the difference in surface properties between the relief and the background surface.…”