Abstract:In this paper, we propose an active contour algorithm for object detection in vectorvalued images (such as RGB or multispectral). The model is an extension of the scalar Chan-Vese algorithm to the vector-valued case [1]. The model minimizes a Mumford-Shah functional over the length of the contour, plus the sum of the fitting error over each component of the vector-valued image. Like the Chan-Vese model, our vector-valued model can detect edges both with or without gradient. We show examples where our model det… Show more
“…This model approximates an image by a two-phase piecewise constant function. The active contours without edge model was also extended to vector valued images [10] and to texture segmentation [11].…”
Abstract. This article introduces a new image segmentation method that makes use of non-local comparisons between pairs of patches of features. A non-local energy is defined by summing the interactions between pairs of patches inside and outside the segmented domain. A maximum radius of interaction can be adapted to fit the amount of variation of the features inside and outside the region to segment. This non-local energy is minimized using a level set approach. The corresponding curve evolution defines a non-local active contour that converges to a local minimum of our energy. In contrast to previous segmentation methods, this approach only requires a local homogeneity of the features inside and outside the region to segment. This does not impose a global homogeneity as required by region-based segmentation methods. This comparison principle is also less sensitive to initialization than edge-based approaches. We instantiate this novel framework using patches of intensity or color values as well as Gabor features. This allows us to segment regions with smoothly varying intensity or colors as well as well as complicated textures with a spatially varying local orientation.
“…This model approximates an image by a two-phase piecewise constant function. The active contours without edge model was also extended to vector valued images [10] and to texture segmentation [11].…”
Abstract. This article introduces a new image segmentation method that makes use of non-local comparisons between pairs of patches of features. A non-local energy is defined by summing the interactions between pairs of patches inside and outside the segmented domain. A maximum radius of interaction can be adapted to fit the amount of variation of the features inside and outside the region to segment. This non-local energy is minimized using a level set approach. The corresponding curve evolution defines a non-local active contour that converges to a local minimum of our energy. In contrast to previous segmentation methods, this approach only requires a local homogeneity of the features inside and outside the region to segment. This does not impose a global homogeneity as required by region-based segmentation methods. This comparison principle is also less sensitive to initialization than edge-based approaches. We instantiate this novel framework using patches of intensity or color values as well as Gabor features. This allows us to segment regions with smoothly varying intensity or colors as well as well as complicated textures with a spatially varying local orientation.
“…Our algorithm is strongly motivated by a region based segmentation method, called active contours without edges, which was originally proposed by Chan and Vese [6] (see also [34] for a related approach) and has led to a number of extensions [7,33] and various numerical implementations [31,14,16]. Our segmentation uses the same fundamental principle but we utilize a dictionarybased texture representation.…”
Abstract. We propose a method for weakly supervised segmentation of natural images, which may contain both textured or non-textured regions. Our texture representation is based on a dictionary of image patches. To divide an image into separated regions with similar texture we use an implicit level sets representation of the curve, which makes our method topologically adaptive. In addition, we suggest a multi-label version of the method. Finally, we improve upon a similar texture representation, by formulating the computation of a texture probability in terms of a matrix multiplication. This results in an efficient implementation of our segmentation method. We experimentally validated our approach on a number of natural as well as composed images.
Segmentation tasks in medical imaging represent an exhaustive challenge for scientists since the image acquisition nature yields issues that hamper the correct reconstruction and visualization processes. Depending on the specific image modality, we have to consider limitations such as the presence of noise, vanished edges, or high intensity differences, known, in most cases, as inhomogeneities. New algorithms in segmentation are required to provide a better performance. This paper presents a new unified approach to improve traditional segmentation methods as Active Shape Models and Chan-Vese model based on level set. The approach introduces a combination of local analysis implementations with classic segmentation algorithms that incorporates local texture information given by the Hermite transform and Local Binary Patterns. The mixture of both region-based methods and local descriptors highlights relevant regions by considering extra information which is helpful to delimit structures. We performed segmentation experiments on 2D images including midbrain in Magnetic Resonance Imaging and heart's left ventricle endocardium in Computed Tomography. Quantitative evaluation was obtained with Dice coefficient and Hausdorff distance measures. Results display a substantial advantage over the original methods when we include our characterization schemes. We propose further research validation on different organ structures with promising results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.