• Home
  • Search
  • Skeleton Extraction via Structure-Adaptive Anisotropic Filtering
  • Cite Icon3
  • https://doi.org/10.1145/2632856.2632897Copy DOI Icon

Skeleton Extraction via Structure-Adaptive Anisotropic Filtering

  • Jul 10, 2014
  • Xiaofeng Du +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Skeletonization of gray-scale images is a challenging problem in computer vision due to the non-uniform width of shape and the clutter background. This paper presents a novel approach of skeletonization for gray-scale images directly from original image based on anisotropic Gaussian filter. To deal with the non-uniform width of natural object parts, we adapt the shape of filter kernel to local gradient feature. The orientation of filter is firstly estimated based on local structure tensor, and then the scale is calculated based on gradient vector flux. After that, the anisotropic Gaussian filter is performed on the image. The skeleton strength map is defined by the gradient vector flux measure. Finally, thin and binary skeleton is obtained by non-maximum suppression the skeleton strength map. Our method performs well on both binary and gray image in skeleton extraction even for clutter image.

Similar Papers
  • PDF
  • Research Article
  • Citations36

An Image Denoising Technique Using Wavelet-Anisotropic Gaussian Filter-Based Denoising Convolutional Neural Network for CT Images

  • Nov 06, 2023
  • Applied Sciences
  • Teresa Kwamboka Abuya +2
  • Research Article
  • Citations1

Road traffic sign recognition algorithm based on computer vision

  • Jan 01, 2018
  • International Journal of Computational Vision and Robotics
  • Huiming Dai +2
  • Conference Article
  • Citations6

Gray image colorization in YCbCr color space

  • Dec 01, 2012
  • Smriti Kumar +1
  • Research Article
  • Citations21

Two-dimensional multi-pixel anisotropic Gaussian filter for edge-line segment (ELS) detection

  • Dec 15, 2013
  • Image and Vision Computing
  • Jian-Lei Liu +1
  • Conference Article
  • Citations2

Anisotropic filtering with nonlinear structure tensors

  • Feb 02, 2006
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Carlos-Alberto Castaño-Moraga +1
  • Conference Article
  • Citations6

An Anisotropic Gaussian Filter for Noise Filtering of InSAR Interferogram

  • Oct 01, 2006
  • Pei Wang +2
  • Conference Article

Automatic Image Colorization via Weighted Sparse Representation Learning

  • Sep 01, 2020
  • Bo Li +1
  • Research Article

DEEP LEARNING – POWERED GRAYSCALE TO COLOR CONVERSION USING OPEN CV

  • Mar 22, 2025
  • International Journal on Science and Technology
  • Y.Bhanu Prakash Reddy - +3
  • Conference Article
  • Citations1

Maneuvering Target Tracking in Cluttered Background Based on Color Invariance and Support Vector Machine

  • Sep 01, 2009
  • Gang Meng +3
  • PDF
  • Research Article
  • Citations5

RECOGNITION OF HUMAN POSE FROM IMAGES BASED ON GRAPH SPECTRA

  • May 18, 2015
  • The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • A A Zakharov +2
  • Conference Article
  • Citations8

Structure-Adaptive Anisotropic Filter with Local Structure Tensors

  • Dec 01, 2008
  • Wei Wang +2
  • Conference Article
  • Citations8

Improved Detection of 1-2-4 LSB Steganography and RSA Cryptography in Color and Grayscale Images

  • Dec 01, 2015
  • Suchi Goyal +2
  • Conference Article
  • Citations3

Interest point detection for hyperspectral imagery

  • May 01, 2009
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Leidy P Dorado-Muñoz +3
  • Conference Article
  • Citations2

A Human Activity Recognition Approach Based on Skeleton Extraction and Image Reconstruction

  • Jun 25, 2021
  • Yanbing Chen +3
  • Conference Article

Numerical analysis on RHEED patterns based on gray level: A case study of IBAD-MgO film

  • Nov 01, 2015
  • Xiao Liang Shi +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.