Tracking by means of geodesic region models applied to multidimensional and complex medical images

This paper proposes a new descriptor for radiological image retrieval. The proposed approach is based on fuzzy shape contexts, Fourier transforms and Eigenshapes. First, fuzzy shape context histograms are computed. Then, a 2D FFT is performed on each 2D histogram to achieve rotation invariance. Finally, histograms are projected onto a lower dimensionality feature space whose basis is formed by a set of vectors called Eigenshapes. They highlight the most important variations between shapes. The proposed approach is translation, scale and rotation invariant. Classes of the medical IRMA database are used for experiments. Comparison with the known approach rotation invariant shape contexts based on feature-space Fourier transformation proves that the proposed method is faster, more efficient, and robust to local deformations.

show abstract

“…Medical image tools are used by physicians for diagnosis. So many works proposed new techniques of medical image processing [3] [4] [5] [6].…”

Section: Introductionmentioning

confidence: 99%

Rotation Invariant Fuzzy Shape Contexts Based on Eigenshapes and Fourier Transforms for Efficient Radiological Image Retrieval

Ayed

Kardouchi

Selouani

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

A novel method for robust object tracking with K-means clustering using histogram back-projection technique

Hardalaç

Kutbay

Şahin

et al. 2018

Multimed Tools Appl

View full text Add to dashboard Cite

Rotation invariant fuzzy shape contexts based on Eigenshapes and fourier transforms for efficient radiological image retrieval

Ayed

Kardouchi

Selouani

2012

2012 International Conference on Multimedia Computing and Systems

View full text Add to dashboard Cite

Tracking by means of geodesic region models applied to multidimensional and complex medical images

Cited by 3 publications

References 53 publications

Rotation Invariant Fuzzy Shape Contexts Based on Eigenshapes and Fourier Transforms for Efficient Radiological Image Retrieval

Rotation Invariant Fuzzy Shape Contexts Based on Eigenshapes and Fourier Transforms for Efficient Radiological Image Retrieval

A novel method for robust object tracking with K-means clustering using histogram back-projection technique

Rotation invariant fuzzy shape contexts based on Eigenshapes and fourier transforms for efficient radiological image retrieval

Contact Info

Product

Resources

About