A curve analysis approach to surface feature extraction from range image

A curve analysis approach to extracting surface curvature features from a range image is presented. The aim is to cope with the problem of the sensitivity of the derivative estimation to the noise and the conflict between the smoothness of the image required by the feature extraction procedures and the preservation of the local structure of the original image. It is based on the analysis of a one-dimensional image profile, because the surface curvature such as mean curvature and Gaussian curvature can be computed from the partial derivatives in the two axis directions. These derivatives should be estimated using only coherent data. This is achieved by curve fitting after curve segmentation. A measure is presented for postprocessing of segmentation that takes into account the pixel value in relation to a threshold and its neighboring context. The use of this measure significantly improves the quality of image segmentation.<
>