Integrated active contours for texture segmentation

Abstract

Abstract-We address the issue of textured image segmentation in the context of the Gabor feature space of images. Gabor filters tuned to a set of orientations, scales and frequencies are applied to the images to create the Gabor feature space. A two-dimensional Riemannian manifold of local features is extracted via the Beltrami framework. The metric of this surface provides a good indicator of texture changes and is used, therefore, in a Beltrami-based diffusion mechanism and in a geodesic active contours algorithm for texture segmentation. The performance of the proposed algorithm is compared with that of the edgeless active contours algorithm applied for texture segmentation. Moreover, an integrated approach, extending the geodesic and edgeless active contours approaches to texture segmentation, is presented. We show that combining boundary and region information yields more robust and accurate texture segmentation results.

Active contour for noisy image segmentation based on contourlet transform

“…μ > 0, ν ≥ 0, λ 1 > 0, λ 2 > 0 are fixed parameters. Chen Sagiv et al 18 integrates the GAC with C-V model, which can be formulated conveniently by minimizing the following energy functional:…”

“…In this paper we propose a new method that integrates the GCV 18,19 with the contourlet transform. 23 Let Ω be an image domain of R 2 , I∶ΩR be a given image, and c p;j ¼ hI j ; ψ p;j i be the contourlet coefficients of image I.…”

“…The C-V model is based on the variational level set framework 17 and does not depend on the image gradient, which makes the C-V model outperform the classical active contours, such as the GAC model 9 and the GVF 4 model in some cases. Sagiv et al 18 and Kimmel 19 proposed a new active contour model, which practically can be considered as the integration of geodesic active contours and C-V model (GCV). This model utilizes a more general weighted arc-length in Riemannian space, weighted by a function of the image's gradients to replace the curve regulation term, which controls the smoothness of the curve in the C-V method.…”

Image segmentation by optimizing a homogeneity measure in a variational framework

“…The general approaches to tackle such cases are to design special methods for texture segmentation, 11,12 or to add specific discriminants 6,13 to describe the texture characteristic. For images with both gray level (including color) regions and texture regions, multichannel information, 8,11 or features derived from Gabor filters, 12 etc., are generally required to realize segmentation.…”

Tissue level segmentation and tracking of biological structures in microscopic images based on density maps

“…In level-set literature, numerous texture segmentation algorithms have been proposed that model the image intensities in terms of Gabor functions [3], wavelets [4] and frequency, oscillating functions [5] or in terms of parametric histogram distributions [6]. Our approach fundamentally measures density differences of components, in this case cells, and can be generalized to spatial distributions and packing of microstructural phases in other fields such as microcrystals in metal alloys.…”