Fast fuzzy connected filter implementation using max-tree updates

doi:10.1016/j.fss.2009.08.006

Fuzzy Sets and Systems

Volume 161, Issue 1, 1 January 2010, Pages 118-146

https://doi.org/10.1016/j.fss.2009.08.006 Get rights and content

Abstract

Connected filters are widely used filters in image processing, and their implementation highly benefits from tree representations of images, called max-trees. Extending these filters to fuzzy sets, which may be used to represent imprecision on gray levels in fuzzy gray-level images, requires frequent manipulations of these trees. In this paper we propose efficient algorithms to update tree representations of fuzzy sets according to modifications of the membership values. We show that any modification can be reduced to a series of simple changes, where only one pixel is modified at each step.

References (29)

J. Crespo et al.
The flat zone approach: a general low-level region merging segmentation method
Signal Processing
(1997)
A. Rosenfeld
Fuzzy digital topology
Information and Control
(1979)
E.J. Breen et al.
Attribute openings, thinnings, and granulometries
Computer Vision and Image Understanding
(1996)
L. Vincent, Grayscale area openings and closings, their efficient implementation and applications, in: First Workshop...
J. Serra, P. Salembier, Connected operators and pyramids, in: Image Algebra and Morphological Image Processing IV, SPIE...
P. Salembier et al.
Flat zones filtering, connected operators, and filters by reconstruction
IEEE Transactions on Image Processing
(1995)
H. Heijmans, Connected Morphological Operators and Filters for Binary Images, in: IEEE Internat. Conf. on Image...
C. Vachier, Morphological scale-space analysis and feature extraction, in: IEEE Internat. Conf. on Image Processing,...
F. Meyer, From connected operators to levelings, in: Proc. Fourth Internat. Symp. on Mathematical Morphology and its...
F. Meyer, The levelings, in: Proc. Fourth Internat. Symp. on Mathematical Morphology and its Applications to Image and...

P. Salembier et al.

Antiextensive connected operators for image and sequence processing

IEEE Transactions on Image Processing

(1998)

A. Meijster et al.

A comparison of algorithms for connected set openings and closings

IEEE Transactions on Pattern Analysis and Machine Intelligence

(2002)

C. Berger, T. Géraud, R. Levillain, N. Widynski, A. Baillard, E. Bertin, Effective component tree computation with...

M. Nachtegael, T. Mélange, E.E. Kerre, The possibilities of fuzzy logic in image processing, in: Second Internat. Conf....

Cited by (7)

Fuzzy sets for image processing and understanding
2015, Fuzzy Sets and Systems
Citation Excerpt :
It was initially defined in [136], and then exploited in fuzzy connectedness notions [151], now widely used for instance in medical image segmentation and incorporated in freely available softwares such as ITK.4 More general classes of fuzzy connectivity have later been developed, with again applications in medical imaging [44,115,124]. Using both topology and metrics, the notion of skeleton and medial axis was also extended to fuzzy sets [84,102,118,123].
Detection of masses and architectural distortions in digital breast tomosynthesis images using fuzzy and a contrario approaches
2014, Pattern Recognition
Citation Excerpt :
Connected filters may help to relax this assumption because the shape of potential lesions is given by the signal itself (connected component resulting from image thresholding). Furthermore, this kind of filters has recently been extended to the fuzzy set framework [18,14] making them suitable to handle uncertainty of lesions on both the shape of connected components and the output magnitude with regard to selected criteria. The assumption that motivates the use of such filters as a detection step is that dense kernels can roughly be retrieved by multi-thresholding tomosynthesis images.
Digital breast tomosynthesis (DBT) is a new 3D imaging technique, which overcomes some limitations of traditional digital mammography. Its development induces an increased amount of data to be processed, thus calling for a computer aided detection system to help the radiologist. Towards this aim, this paper focuses on the detection of masses and architectural distortions in DBT images. A complete detection scheme is proposed, consisting of two parts, called channels, each dedicated to one type of lesions, which are then merged in a final decision step, thus handling correctly the potential overlap between the two types of lesions. The first detection channel exploits the dense kernel nature of masses and the intrinsic imprecision of their attributes in a fuzzy approach. The second detection channel models the convergence characteristics of architectural distortions in an a contrario approach. The experimental results on 101 breasts, including 53 lesions, demonstrate the usefulness of the proposed approach, which leads to a high sensitivity with a reduced number of false positives, and compares favorably to existing approaches.
Interactive segmentation based on component-trees
2011, Pattern Recognition
Citation Excerpt :
By definition, component-trees are particularly well suited for the design of methods devoted to process and/or analyse grey-level images based on a priori hypotheses related to the topology (connectedness) and the specific intensity (locally/globally minimal or maximal) of structures of interest. ( The case of colour images is currently under investigation [9,10]; the involvement of component-trees in fuzzy grey-level images is described in [11].) Based on these properties, but also thanks to methodological developments related to complex knowledge handling [12–14], component-trees have been involved in the design of several image processing/analysis applications, especially for filtering/segmentation applications.
Component-trees associate to a discrete grey-level image a descriptive data structure induced by the inclusion relation between the binary components obtained at successive level-sets. This article presents an original interactive segmentation methodology based on component-trees. It consists of the extraction of a subset of the image component-tree, enabling the generation of a binary object which fits at best (with respect to the grey-level structure of the image) a given binary target selected beforehand in the image. A proof of the algorithmic efficiency of this methodological scheme is proposed. Concrete application examples on magnetic resonance imaging (MRI) data emphasise its actual computational efficiency and its usefulness for interactive segmentation of real images.
Fuzzy Sets Methods in Image Processing and Understanding: Medical Imaging Applications
2023, Fuzzy Sets Methods in Image Processing and Understanding: Medical Imaging Applications
Multicriteria 3D PET image segmentation
2015, 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015
Hyperconnections and hierarchical representations for grayscale and multiband image processing
2012, IEEE Transactions on Image Processing

View all citing articles on Scopus

View full text

Fast fuzzy connected filter implementation using max-tree updates

Abstract

Signal Processing

Information and Control

Computer Vision and Image Understanding

Flat zones filtering, connected operators, and filters by reconstruction

IEEE Transactions on Image Processing

Antiextensive connected operators for image and sequence processing

IEEE Transactions on Image Processing

A comparison of algorithms for connected set openings and closings

IEEE Transactions on Pattern Analysis and Machine Intelligence