Distance Map Based Enhancement for Interpolated Images

Zeng, Peifeng; Hirata, T.

doi:10.1007/3-540-36586-9_6

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the maximum of the DT of an object is its width; the distribution of the distances in the DT is also a useful shape descriptor. -Other interesting areas in which the DT has been applied are: image registration [Kozinska et al 1997;Cuisenaire and Macq 1999b]; subpixel contour tracing [Siddiqi et al 1997]; multidimensional data analysis (classification, clustering) [Starovoitov 1996]; image enhancement [Zeng and Hirata 2003]; ray-tracing optimization [Paglieroni 1997;Sramek and Kaufman 2000]; embedding surface for level set-based methods [Sethian 1999;Osher and Sethian 1988;Tek and Kimia 2003;Siddiqi et al 1997;Sebastian et al 2003;Xia et al 2004]; efficient belief-propagation [Felzenszwalb and Huttenlocher 2006]; multiphase flow simulations [Ceniceros and Roma 2005]; medical image analysis [Cuisenaire and Macq 1999b;hao Tseng et al 1998;Wintermark et al 2002;Jolesz et al 1997;Thiran and Macq 1996;Saito and Toriwaki 1994;Sebastian et al 2003]; analysis of interaction between biological structures [Travençolo et al 2007]; botanics [Travis et al 1996]; and geology [Paglieroni 1997;Parker 1997]. …”

Section: R Fabbri Et Almentioning

confidence: 99%

2D Euclidean distance transform algorithms

Costa²,

et al. 2008

View full text Add to dashboard Cite

The distance transform (DT) is a general operator forming the basis of many methods in computer vision and geometry, with great potential for practical applications. However, all the optimal algorithms for the computation of the exact Euclidean DT (EDT) were proposed only since the 1990s. In this work, state-of-theart sequential 2D EDT algorithms are reviewed and compared, in an effort to reach more solid conclusions regarding their differences in speed and their exactness. Six of the best algorithms were fully implemented and compared in practice.The work of R. Fabbri was supported by CNPq (200875/2004-3) and FAPESP (03/09834-0); O. M. Bruno acknowledges support from FAPESP (03/09834-0) and CNPq (303746/04-1); L. Da F. Costa thanks FAPESP (99/12765-2 and 05/00587-5) and CNPq (308231/03-1).

show abstract

Section: R Fabbri Et Almentioning

confidence: 99%

2D Euclidean distance transform algorithms

Costa²,

et al. 2008

View full text Add to dashboard Cite

show abstract

“…where Ez is the number of edge points in slice z of the aligned floating volume, (x" y,) are the coordinates of an edge 20 point from slice z of the aligned floating volume and DMz is the Distance Map of slice z from the aligned floating volume [15]. In our case (5) was employed to obtain MED measurements between the preoperative and postoperative volumes before and after the registration process.…”

Section: In(lf )mentioning

confidence: 99%

Volumetric difference evaluation of registered three-dimensional preoperative and postoperative CT volumes

Economopoulos

Asvestas

Matsopoulos

et al. 2010

Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine

View full text Add to dashboard Cite

A methodology is presented for registering three dimensional preoperative and postoperative CT scan volumes and for evaluating their differences in selected areas of interest.The proposed method was applied to CT cone beam data from ten patients in order to assess the volume of augmented bone in the alveolar region. A 3D affine model was used to align the preoperative and postoperative data. The differences between the aligned sets were assessed through subtraction radiography.The volume of the differences was finally evaluated by defining regions of interest in each slice of the subtracted 3D data. Both quantitative and qualitative results were obtained after applying the method to all sets. The effectiveness of the volumetric assessment algorithm was verified by applying the algorithm to an object of known volume.

show abstract

“…This approach does not provide stable results for blurred and noisy edges. In [11], the edge is modeled by a special function, but it does not fit our needs.…”

Section: Edge Width Analysismentioning

confidence: 99%