Regression based bandwidth selection for segmentation using Parzen windows

Singh, Sanjiv; Ahuja, Rakesh

doi:10.1109/iccv.2003.1238307

Cited by 23 publications

(12 citation statements)

References 13 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(The origin of the coordinate system is at the top-left corner.) We then performed segmentation by incorporating the smoothness-penalty cost function given in Equation 18. The combination of this soft surfacedependent constraint and the hard geometrical constraints enabled us to obtain significantly improved results as shown in Figure 3(c), which clearly demonstrate the effectiveness of the cost function.…”

Section: Experiments and Resultsmentioning

confidence: 79%

“…This is done by smoothing both histograms by a Parzen Window with a Gaussian kernel, and then normalizing them such that each of them sum to one. Depending on whether the estimated object intensity distribution is unimodal or not (as determined by the mean-shift process [17,18]), either a single-surface or a multiple-surface graph search will be executed. The graph search is performed in a narrow-band surrounding an ellipsoid fitted to the pre-segmentation result.…”

Section: Tumor Surface Layer Segmentationmentioning

confidence: 99%

“…We employ an adaptive mean-shift process [17,18] to identify the modes of the object histogram, and hence to determine the number of surface layers present in the target object.…”

Section: Tumor Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

Simultaneous detection of multiple elastic surfaces with application to tumor segmentation in CT images

Jolly

2008

SPIE Proceedings

View full text Add to dashboard Cite

We present a new semi-supervised method for segmenting multiple interrelated object boundaries with spherical topology in volumetric images. The core of our method is a novel graph-theoretic algorithm that simultaneously detects multiple surfaces under smoothness, distance, and elasticity constraints. The algorithm computes the global optimum of an objective function that incorporates boundary, regional and surface elasticity information. A single straight line drawn by the user in a cross-sectional slice is the sole user input, which roughly indicates the extent of the object. We employ a multi-seeded Dijkstra-based range competition algorithm to pre-segment the object on two orthogonal multiplanar reformatted (MPR) planes that pass through the input line. Based on the 2D pre-segmentation results, we estimate the object and background intensity histograms, and employ an adaptive mean-shift mode-seeking process on the object histogram to automatically determine the number of surface layers to be segmented. The final multiple-surface segmentation is performed in an ellipsoidal coordinate frame constructed by an automated ellipsoid fitting procedure. We apply our method to the segmentation of liver lesions with necrosis or calcification, and various other tumors in CT images. For liver tumor segmentation, our method can simultaneously delineate both tumor and necrosis boundaries. This capability is unprecedented and is valuable for cancer diagnosis, treatment planning, and evaluation.

show abstract

Section: Experiments and Resultsmentioning

confidence: 79%

Section: Tumor Surface Layer Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous detection of multiple elastic surfaces with application to tumor segmentation in CT images

Jolly

2008

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…The difficulty in selecting the kernel was recognized in [3,4,12] and was addressed by automatically determining a bandwidth for spherical kernels. These approaches are all purely data driven.…”

Section: Introductionmentioning

confidence: 99%

Image and Video Segmentation by Anisotropic Kernel Mean Shift

Wang

Thiesson

et al. 2004

Lecture Notes in Computer Science

159

113

View full text Add to dashboard Cite

Abstract. Mean shift is a nonparametric estimator of density which has been applied to image and video segmentation. Traditional mean shift based segmentation uses a radially symmetric kernel to estimate local density, which is not optimal in view of the often structured nature of image and more particularly video data. In this paper we present an anisotropic kernel mean shift in which the shape, scale, and orientation of the kernels adapt to the local structure of the image or video. We decompose the anisotropic kernel to provide handles for modifying the segmentation based on simple heuristics. Experimental results show that the anisotropic kernel mean shift outperforms the original mean shift on image and video segmentation in the following aspects: 1) it gets better results on general images and video in a smoothness sense; 2) the segmented results are more consistent with human visual saliency; 3) the algorithm is robust to initial parameters.

show abstract

“…. , n} [4,6,25]. One possible choice for the underlying kernel function is a Gaussian kernel: the kernel centered at x i reads…”

Section: σ Estimationmentioning

confidence: 99%

Model Order Selection and Cue Combination for Image Segmentation

Rabinovich

Belongie

Lange

et al.

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06)

View full text Add to dashboard Cite

Model order selection and cue combination are both difficult open problems in the area of clustering. In this work we build upon stability-based approaches to develop a new method for automatic model order selection and cue combination with applications to visual grouping. Novel features of our approach include the ability to detect multiple stable clusterings (instead of only one), a simpler means of calculating stability that does not require training a classifier, and a new characterization of the space of stabilities for a continuum of segmentations that provides for an efficient sampling scheme. Our contribution is a framework for visual grouping that frees the user from the hassles of parameter tuning and model order selection: the input is an image, the output is a shortlist of segmentations.

show abstract

Regression based bandwidth selection for segmentation using Parzen windows

Abstract: We

Cited by 23 publications

References 13 publications

Simultaneous detection of multiple elastic surfaces with application to tumor segmentation in CT images

Simultaneous detection of multiple elastic surfaces with application to tumor segmentation in CT images

Image and Video Segmentation by Anisotropic Kernel Mean Shift

Model Order Selection and Cue Combination for Image Segmentation

Contact Info

Product

Resources

About