Title :
Invariant feature extraction and neural trees for range surface classification
Author :
Foresti, Gian Luca
Author_Institution :
Dept. of Math. & Comput. Sci. (DIMI), Udine Univ., Italy
fDate :
6/1/2002 12:00:00 AM
Abstract :
In this paper, a neural tree-based approach for classifying range images into a set of nonoverlapping regions is presented. An innovative procedure is applied to extract invariant surface features from each pixel of the range image. These features are: 1) robust to noise, and 2) invariant to scale, shift, rotations, curvature variations, and direction of the normal. Then, a generalized neural tree is used to classify each image point as belonging to one of the six surface models of differential geometry, i.e., peak, ridge, valley, saddle, pit, and flat. Comparisons with other methods and experiments on both synthetic and real three-dimensional range images are proposed
Keywords :
computer vision; differential geometry; feature extraction; image classification; image segmentation; neural nets; trees (mathematics); differential geometry; experiments; image segmentation; invariant feature extraction; neural networks; neural trees; nonoverlapping regions; pixel; range image classification; range surface classification; three-dimensional range images; Classification tree analysis; Feature extraction; Image edge detection; Image segmentation; Neural networks; Noise robustness; Object recognition; Oscillators; Pixel; Solid modeling;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2002.999811