Relative Fuzzy Connectedness on Directed Graphs and its Application in a Hybrid Method for Interactive Image Segmentation

Abstract : Image segmentation consists of dividing an image into its compo- sing regions or objects, for example, to isolate the pixels of a target object of a given application. In segmentation of medical images, the object of interest commonly presents transitions at its border predominantly from bright to dark or dark to bright. Traditio- nal region-based methods of image segmentation, such as Relative Fuzzy Connectedness (RFC), do not distinguish well between si- milar boundaries with opposite orientations. The specification of the boundary polarity can help to alleviate this problem but this requires a mathematical formulation on directed graphs. A discussion on how to incorporate this property in the RFC framework is presented in this work. A theoretical proof of the optimality of the new algorithm, called Oriented Relative Fuzzy Connectedness (ORFC), in terms of an energy function on directed graphs subject to seed constraints is presented, and its application in powerful hybrid segmentation methods. The hybrid method proposed ORFC & Graph Cut preserves the robustness of ORFC respect to the seed choice, avoiding the shrinking problem of Graph Cut (GC), and keeps the strong con- trol of the GC in the contour delination of irregular image boundaries. The proposed methods are evaluated using medical images of MRI and CT images of the human brain and thoracic studies.
Complete list of metadatas

Cited literature [2 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02244966
Contributor : Bejar Ccacyahuillca <>
Submitted on : Thursday, August 1, 2019 - 7:52:16 PM
Last modification on : Friday, August 2, 2019 - 9:27:01 AM

File

poster_ORFC_OGC.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02244966, version 1

Citation

Hans Harley Ccacyahuillca Bejar. Relative Fuzzy Connectedness on Directed Graphs and its Application in a Hybrid Method for Interactive Image Segmentation. LatinX in AI Research at ICML 2019, Jun 2019, Long Beach, California, United States. ⟨hal-02244966⟩

Share

Metrics

Record views

12

Files downloads

10