Title :
Curve segmentation by continuous smoothing at multiple scales
Author :
Orrite, Carlos ; López, José E. ; Alcolea, Angel
Author_Institution :
Dept. of Electr., Electron. & Commun. Eng., Zaragoza Univ., Spain
Abstract :
In the case of curve description, the accurate and precise estimation of corners plays an important role. Corners exhibit a high change of curvature κ´, so we propose the location of them by means of the estimation of κ´ at different scales of smoothing. The main problem arises when the curvature is computed because of the inherent quantization. We propose to calculate the curvature of contours detected at subpixel level so that, the quantization error is reduced. Once the change of curvature has been estimated, the curve is segmented at high κ´ points. It is important to emphasise the fact that the curves are segmented before a smoothing at coarser scale is applied, otherwise two close corners could be merged as smoothing increases
Keywords :
edge detection; image segmentation; parameter estimation; quantisation (signal); smoothing methods; continuous smoothing; contours curvature; corner estimation; curvature estimation; curve description; curve segmentation; edge detection algorithm; multiple scales; quantization error; subpixel level; Application software; Change detection algorithms; Computer errors; Computer vision; Detectors; Error correction; Kernel; Partitioning algorithms; Quantization; Smoothing methods;
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
DOI :
10.1109/ICIP.1996.560561