Texture-gradient-based contour detection

Authors:
Nasser Chaji;Hassan Ghassemian
Affiliations:
Department of Electrical Engineering, Tarbiat Modares University, Tehran, Iran and Department of Electrical and Communication Engineering, Birjand University, Birjand, Iran;Department of Electrical Engineering, Tarbiat Modares University, Tehran, Iran
Venue:
EURASIP Journal on Applied Signal Processing
Year:
2006

Citing 6
Cited 1

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
An optimal linear operator for step edge detection

CVGIP: Graphical Models and Image Processing
Comparison of texture features based on Gabor filters

IEEE Transactions on Image Processing
Contour detection based on nonclassical receptive field inhibition

IEEE Transactions on Image Processing
Image segmentation using a texture gradient based watershed transform

IEEE Transactions on Image Processing
Thresholding in edge detection: a statistical approach

IEEE Transactions on Image Processing

Review article: Edge and line oriented contour detection: State of the art

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new biologically motivated method is proposed to effectively detect perceptually homogenous region boundaries. This method integrates the measure of spatial variations in texture with the intensity gradients. In the first stage, texture representation is calculated using the nondecimated complex wavelet transform. In the second stage, gradient images are computed for each of the texture features, as well as for grey scale intensity. These gradients are eciently estimated using a new proposed algorithm based on a hypothesis model of the human visual system. After that, combining these gradient images, a region gradient which highlights the region boundaries is obtained. Nonmaximum suppression and then thresholding with hysteresis is used to detect contour map from the region gradients. Natural and textured images with associated ground truth contour maps are used to evaluate the operation of the proposed method. Experimental results demonstrate that the proposed contour detection method presents more effective performance than conventional approaches.