Results 231 to 240 of about 366,438 (285)
Some of the next articles are maybe not open access.
Motion-driven object segmentation in scale-space
1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258), 1999In this paper we present a method for motion segmentation, in which accurate grouping of pixels undergoing the same motion is targeted. In the presented technique true object edges are first obtained by combining anisotropic diffusion of the original image with edge detection and contour reconstruction in the inherent scale-space.
E.M. Izquierdo, M. Ghanbari
openaire +1 more source
Image segmentation by analysis of scale-space
Proceedings. XV Brazilian Symposium on Computer Graphics and Image Processing, 2003We present a technique in image segmentation based on a hierarchical analysis of scale-space. The image hierarchy is a tree of critical lakes and provides a set of nested partitions. We analyze the scale-space from fine to coarse levels according to specific attributes.
Garcia de Carvalho, Marco António +2 more
openaire +2 more sources
Image segmentation using Scale-Space Random Walks
2009 16th International Conference on Digital Signal Processing, 2009Many methods for supervised image segmentation exist. One such algorithm, Random Walks, is very fast and accurate when compared to other methods. A drawback to Random Walks is that it has difficulty producing accurate and clean segmentations in the presence of noise.
Richard Rzeszutek +2 more
openaire +1 more source
Acoustic-phonetic segment classification and scale-space filtering
ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005Scale-space filtering represents one method for automatically extracting both coarse and fine-grained units from the speech signal. We examine the acoustic-phonetic structure of segments obtained by scale-space filtering of cochleagrams, and report on the correspondences between scale-space segments which are automatically derived and hand-marked ...
M. Withgott, S. Bagley, R. Lyon, M. Bush
openaire +1 more source
Retinal vessel segmentation using Morphological Angular Scale-Space
2012 Third International Conference on Emerging Applications of Information Technology, 2012In this paper, segmentation of retinal vessel is done using an innovative procedure named as Morphological Angular Scale-Space (MASS). A linear structuring element rotated at different angles determines the connected components and ensuring that connectivity is not lost across the vessels.
Anirban Kundu, Rohit Kamal Chatterjee
openaire +1 more source
Scale Space Hierarchy of Segments
2009In this paper, we develop a segmentation algorithm using configurations of singular points in the linear scale space. We define segment edges as a zero-crossing set in the linear scale space using the singular points. An image in the linear scale space is the convolution of the image and the Gaussian kernel.
Haruhiko Nishiguchi +2 more
openaire +1 more source
Color image segmentation by scale-space image analysis
2007 International Conference on Wavelet Analysis and Pattern Recognition, 2007An image analysis method has been proposed to segment color images. The method is capable of segmenting color images based on watershed transform and scale-space analysis of the images. We analyze hierarchical, geometric properties and the hue uniformity measure of the tree of scale-space and show the experimental results for several biological and ...
null Zhi-Qiang Wei, null Miao Yang
openaire +1 more source
The Segmentation of Images via Scale-Space Trees
Procedings of the British Machine Vision Conference 1998, 1998A useful representation of an image would be an object tree in which nodes represent objects, or parts of objects, and which includes at least one node that, together with its children, represents each object: a grandmothernode. It is shown that scale-trees, obtained from greyscale images, approximate such a tree.
J. A. Bangham +3 more
openaire +1 more source
Document image segmentation using wavelet scale-space features
IEEE Transactions on Circuits and Systems for Video Technology, 2002An efficient and computationally fast method for segmenting text and graphics part of document images based on textural cues is presented. We assume that the graphics part have different textural properties than the nongraphics (text) part. The segmentation method uses the notion of multiscale wavelet analysis and statistical pattern recognition.
M. Acharyya, M.K. Kundu
openaire +1 more source
Size-adapted microcalcification segmentation in mammography utilizing scale-space signatures
Computerized Medical Imaging and Graphics, 2010The purpose of this study is size-adapted segmentation of individual microcalcifications in mammography, based on microcalcification scale-space signature estimation, enabling robust scale selection for initialization of multiscale active contours. Segmentation accuracy was evaluated by the area overlap measure, by comparing the proposed method and two
Nikolaos S, Arikidis +6 more
openaire +2 more sources