Graph Cut Research Papers - Academia.edu (original) (raw)

Image segmentation has traditionally been thought of us a low/mid-level vision process incorporating no high level constraints. However, in complex and uncontrolled environments, such bottom-up strategies have drawbacks that lead to large... more

Image segmentation has traditionally been thought of us a low/mid-level vision process incorporating no high level constraints. However, in complex and uncontrolled environments, such bottom-up strategies have drawbacks that lead to large misclassification rates. Remedies to this situation include taking into account (1) contextual and application constraints, (2) user input and feedback to incrementally improve the performance of the system. We attempt to incorporate these in the context of pipeline segmentation in industrial images. This problem is of practical importance for the 3D reconstruction of factory environments. However it poses several fundamental challenges mainly due to shading. Highlights and textural variations, etc. Our system performs pipe segmentation by fusing methods from physics-based vision, edge and texture analysis, probabilistic learning and the use of the graph-cut formalism

В статье предложены эвристики и комбинации эвристик для решения задачи сбалансированного разбиения гиперграфа, моделирующего электронную схему, на подграфы. Ключевые слова — размещение элементов СБИС, разбиение гиперграфа, декомпозиция... more

В статье предложены эвристики и комбинации
эвристик для решения задачи сбалансированного
разбиения гиперграфа, моделирующего электронную схему, на подграфы.
Ключевые слова — размещение элементов СБИС,
разбиение гиперграфа, декомпозиция электронных схем.

Одним из способов декомпозиции задачи большой размерности на подзадачи является пред-ставление ее в виде графа или гиперграфа и последующее разбиение на приблизительно равные части, причем число связей между подграфами должно быть... more

Одним из способов декомпозиции задачи большой размерности на подзадачи является пред-ставление ее в виде графа или гиперграфа и последующее разбиение на приблизительно равные части, причем число связей между подграфами должно быть минимальным. Если веса ребер графа моделируют объем межпроцессорных связей, а вес узлов гиперграфа вычислительную сложность, то подзадачи можно эффективно решать на параллельных вычислительных систе-мах. Известные многоуровневые эвристические методы на базе алгоритма Фидуччиа–Мэтьюза позволяют решать такие задачи за приемлемое время. В настоящей статье предложены мо-дификации ключевой структуры данных алгоритма, позволяющие улучшить свойства метода сбалансированного разбиения гиперграфа на подграфы с целью достижения меньшего размера сечения и уменьшения издержек параллельных методов решения исходной задачи. Приведены результаты сравнения нового алгоритма для одноуровневого и иерархического методов разби-ения.

With the target of simultaneously segmenting semantically related videos to identify the common objects, video object cosegmentation has attracted the attention of researchers in recent years. Existing methods are primarily based on... more

With the target of simultaneously segmenting semantically related videos to identify the common objects, video object cosegmentation has attracted the attention of researchers in recent years. Existing methods are primarily based on pair-wise relations between adjacent pixels and regions, which are susceptible to performance degradation from object entries/exists or occlusions. Specifically, we refer these video frames without the common objects present as the "empty" frames. In this paper, we propose a multilevel hypergraph-based full Video object CoSegmentation (VCS) method, which incorporates high-level semantics and low-level appearance/motion/saliency to construct the hyperedge among multiple spatially and temporally adjacent regions. Specifically, the high-level semantic model fuses multiple object proposals from each frame instead of relying on a single object proposal per frame. A hypergraph cut is subsequently utilized to calculate the object cosegmentation. Experiments on four video object segmentation/cosegmentation datasets against state-of-the-art methods with both objective and subjective results manifest the effectiveness of the proposed VCS method, including the SegTrack and VCoSeg datasets without "empty" frames, the XJTU-Stevens dataset with 3.7% "empty" frames, and the Noisy-ViCoSeg dataset proposed together with our method with 30.3% "empty" frames.

For quantitative analysis of histopathological images, such as the lymphoma grading systems, quantification of features is usually carried out on single cells before categorizing them by classification algorithms. To this end, we propose... more

For quantitative analysis of histopathological images, such as the lymphoma grading systems, quantification of features is usually carried out on single cells before categorizing them by classification algorithms. To this end, we propose an integrated framework consisting of a novel supervised cell-image segmentation algorithm and a new touching-cell splitting method. For the segmentation part, we segment the cell regions from the other areas by classifying the image pixels into either cell or extra-cellular category. Instead of using pixel color intensities, the color-texture extracted at the local neighborhood of each pixel is utilized as the input to our classification algorithm. The color-texture at each pixel is extracted by local Fourier transform (LFT) from a new color space, the most discriminant color space (MDC). The MDC color space is optimized to be a linear combination of the original RGB color space so that the extracted LFT texture features in the MDC color space can achieve most discrimination in terms of classification (segmentation) performance. To speed up the texture feature extraction process, we develop an efficient LFT extraction algorithm based on image shifting and image integral. For the splitting part, given a connected component of the segmentation map, we initially differentiate whether it is a touching-cell clump or a single nontouching cell. The differentiation is mainly based on the distance between the most likely radial-symmetry center and the geometrical center of the connected component. The boundaries of touching-cell clumps are smoothed out by Fourier shape descriptor before carrying out an iterative, concave-point and radial-symmetry based splitting algorithm. To test the validity, effectiveness and efficiency of the framework, it is applied to follicular lymphoma pathological images, which exhibit complex background and extracellular texture with nonuniform illumination condition. For comparison purposes, the results of the p- oposed segmentation algorithm are evaluated against the outputs of superpixel, graph-cut, mean-shift, and two state-of-the-art pathological image segmentation methods using ground-truth that was established by manual segmentation of cells in the original images. Our segmentation algorithm achieves better results than the other compared methods. The results of splitting are evaluated in terms of under-splitting, over-splitting, and encroachment errors. By summing up the three types of errors, we achieve a total error rate of 5.25% per image.

Classification tasks are often based on training with labeled exemplars. This paradigm, as others, presents classi- fiers with two types of information: that pairs of objects belong to the same class (Positive Equivalence Constraints or... more

Classification tasks are often based on training with labeled exemplars. This paradigm, as others, presents classi- fiers with two types of information: that pairs of objects belong to the same class (Positive Equivalence Constraints or PECs) or to different classes (Negative Equivalence Constraints or NECs). We now test classification separately with one or the other of these sources of information.

Stereo camera systems are necessary to obtain 3D information from stereo images. These can be divided into non-convergence and convergence camera models [1], [2] and [5]. Non-convergence cameras obtain stereo images without vertical range... more

Stereo camera systems are necessary to obtain 3D information from stereo images. These can be divided into non-convergence and convergence camera models [1], [2] and [5]. Non-convergence cameras obtain stereo images without vertical range by arranging the optical axes of two ...

... Samy Ait-Aoudia, Ramdane Mahiou, Elhachemi Guerrout ESI - Ecole nationale Supérieure en Informatique, BP 68M, O-Smar 16270 Algiers, Algeria s_ait_aoudia@esi.dz, r_mahiou@esi.dz, e_guerrout@esi.dz ... Potts model The Potts model is a... more

... Samy Ait-Aoudia, Ramdane Mahiou, Elhachemi Guerrout ESI - Ecole nationale Supérieure en Informatique, BP 68M, O-Smar 16270 Algiers, Algeria s_ait_aoudia@esi.dz, r_mahiou@esi.dz, e_guerrout@esi.dz ... Potts model The Potts model is a generalization of the Ising model. ...

High resolution 3D coronary artery MR angiography is time-consuming and can benefit from accelerated data acquisition provided by parallel imaging techniques without sacrificing spatial resolution. Currently, popular maximum likelihood... more

High resolution 3D coronary artery MR angiography is time-consuming and can benefit from accelerated data acquisition provided by parallel imaging techniques without sacrificing spatial resolution. Currently, popular maximum likelihood based parallel imaging reconstruction techniques such as the SENSE algorithm offer this advantage at the cost of reduced signal-to-noise ratio (SNR). Maximum a posteriori (MAP) reconstruction techniques that incorporate globally smooth priors have been developed to recover this SNR loss, but ...

A method to detect boundaries in in natural color images is here proposed, combining edge information and region information. This unsupervised fully automatic process uses edge map information to eliminate false boundaries in the image... more

A method to detect boundaries in in natural color images is here proposed, combining edge information and region information. This unsupervised fully automatic process uses edge map information to eliminate false boundaries in the image region map, and region map information to remove noise in the image edge map. Thus, it integrates these two maps into a single one to get the final result. This proposal is extensively compared to the multi-label graph cut approach, since both approaches are unsupervised and fully automatic, as well as receive the same two inputs, although performing different processing. Experiments performed on a large set of natural color images were the base for such comparison. The results show that the approach here proposed is promising, besides allowing interesting interpretations about boundary detection.

The National Cancer Institute has collected a large database of uterine cervix images, termed “cervigrams ” for cervical can-cer screening research. Tissues of interest within the cervi-gram, in particular the lesions, are of varying... more

The National Cancer Institute has collected a large database of uterine cervix images, termed “cervigrams ” for cervical can-cer screening research. Tissues of interest within the cervi-gram, in particular the lesions, are of varying sizes and com-plex, non-convex shapes. The current work proposes a new methodology that enables the segmentation of non-convex re-gions, thus providing a major step forward towards cervigram tissue detection and lesion delineation. The framework transi-tions from pixels to a set of small coherent regions (superpix-els), which are grouped bottom-up into larger, non-convex, perceptually similar regions, utilizing a new graph-cut cri-terion and agglomerative clustering. Superpixels similarity is computed via a combined region and boundary informa-tion measure. Results for a set of 120 cervigrams, manually marked by a medical expert, are shown. Index Terms — cervicography images; segmentation; graph algorithms 1.