SMRFI: Shape matching via registration of vector-valued feature images

Tang, Lisa; Hamarneh, Ghassan

doi:10.1109/cvpr.2008.4587789

Cited by 11 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The differences lie in the procedures that extract feature points, compute shape descriptors and quantify the distortion introduced by a correspondence, which are dependent on the data representation. In the case of images, the problems of measuring distances and preserving the neighbourhood structures of elements are simplified by the regular parameterization that is enforced by these data sets [TH08]. Furthermore, we might also have to consider different types of transformations (e.g., the projection of a 3D shape onto a 2D plane), for problems such as matching stereo images or registration of images taken from different viewpoints [Bro92].…”

Section: Representative Methodsmentioning

confidence: 99%

“…First, the shapes are transformed into 2D images (or 3D volumes) by mapping each feature point to its nearest pixel (or voxel). The value that is assigned to the pixel can be a vector of descriptors computed at the point [TH08], or the generated image can represent a level set function of the shape [HNM06]. Finally, the resulting images or volumes are registered by computing a global alignment followed by a non‐rigid deformation.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Shape Correspondence

Kaick¹,

Zhang²,

Hamarneh³

et al. 2011

Computer Graphics Forum

Self Cite

550

375

View full text Add to dashboard Cite

We present a review of the correspondence problem and its solution methods, targeting the computer graphics audience. With this goal in mind, we focus on the correspondence of geometric shapes represented by point sets, contours or triangle meshes. This survey is motivated by recent developments in the field such as those requiring the correspondence of non-rigid or time-varying surfaces and a recent trend towards semantic shape analysis, of which shape correspondence is one of the central tasks. Establishing a meaningful shape correspondence is a difficult problem since it typically relies on an understanding of the structure of the shapes in question at both a local and global level, and sometimes also the shapes' functionality. However, despite its inherent complexity, shape correspondence is a recurrent problem and an essential component in numerous geometry processing applications. In this report, we discuss the different forms of the correspondence problem and review the main solution methods, aided by several classification criteria which can be used by the reader to objectively compare the methods. We finalize the report by discussing open problems and future perspectives.

show abstract

Section: Representative Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

A Survey on Shape Correspondence

Kaick¹,

Zhang²,

Hamarneh³

et al. 2011

Computer Graphics Forum

Self Cite

550

375

View full text Add to dashboard Cite

show abstract

“…It is also possible to do clever preprocessing of the data to obtain an image similarity measure more suited for the registration. In the work of [11] a selection of shape features were calculated from the objects and transformed into vector-valued 2D feature images, that were then registered using a classic image registration formulation. Skeletal features were used to provide the more global similarity between samples, while curvature and convexity features handles local similarity.…”

Section: Introductionmentioning

confidence: 99%

Image Registration of Cochlear $$\mu $$ μ CT Data Using Heat Distribution Similarity

et al. 2015

View full text Add to dashboard Cite

Better understanding of the anatomical variability of the human cochlear is important for the design and function of Cochlear Implants. Good non-rigid alignment of high-resolution cochlear μCT data is a challenging task. In this paper we study the use of heat distribution similarity between samples as an anatomical registration prior. We setup and present our heat distribution model for the cochlea and utilize it in a typical cubic B-spline registration model. Evaluation and comparison is done against a corresponding normal registration of binary segmentations.

show abstract

“…Liao et al [2] also combined an improved version of mutual information, a feature-based metric, and a local descriptor for brain image registration. In [3], Tang and Hamarneh matched shapes by combining geometric, topological, and intensity-based features. For registration of lung images, Cao et al [4] combined a measure called vesselness difference (VD) with a conventional intensity-based measure.…”

Section: Introductionmentioning

confidence: 99%

Locally-adaptive similarity metric for deformable medical image registration

Tang

Hero

Hamarneh

2012

2012 9th IEEE International Symposium on Biomedical Imaging (ISBI)

Self Cite

View full text Add to dashboard Cite

More and more researchers are beginning to use multiple dissimilarity metrics or image features for medical image registration. In most of these approaches, however, weights for ranking the relative importance between the selected metrics are empirically tuned and fixed for the entire image domain. Different parts of a medical image, however, may contain significantly different appearance properties such that a metric may only be applicable in certain image regions but less so in other regions. In this paper, we propose to adapt this weighting to generate a locally-adaptive set of dissimilarity metrics such that the overall metric set encourages proper spatial alignment. Using contextual information or via a learning procedure, our approach generates a vector weight map that determines, at each spatial location, the relative importance of each constituent of the overall metric. Our approach was evaluated on 2 datasets of 15 computed tomography (CT) lung images and 40 brain magnetic resonance images (MRI). Experiments show that our approach of using a locally-adaptive set of dissimilarity metrics gives superior results when compared against its non-region specific variant.

show abstract

SMRFI: Shape matching via registration of vector-valued feature images

Cited by 11 publications

References 27 publications

A Survey on Shape Correspondence

A Survey on Shape Correspondence

Image Registration of Cochlear $$\mu $$ μ CT Data Using Heat Distribution Similarity

Locally-adaptive similarity metric for deformable medical image registration

Contact Info

Product

Resources

About