A parallel architecture for implementation of filters based on order statistics

Γαστεράτος, Αντώνιος; Andreadis, Ioannis; Tsalides, Ph.

doi:10.1016/s0167-8655(98)00066-x

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Έτσι για οποιοδήποτε δομικό στοιχείο κατασκευάζεται ένα κατάλληλο OSM, σύμφωνα με τη διαδικασία που περιγράφηκε. (Gasteratos et al, (1998c)). H αρχιτεκτονική είναι γενική και με βάση αυτήν μπορεί να κατασκευαστούν φίλτρα βασισμένα στα διατεταγμένα στατιστικά, αλλάζοντας απλώς τη μονάδα ελέγχου.…”

unclassified

Ανάπτυξη Και Υλοποίηση Με Εξειδικευμένα Ηλεκτρονικά Κυκλώματα Νέων Τεχνικών Μη Γραμμικής Επεξεργασίας Εικόνων

Γαστεράτος¹

View full text Add to dashboard Cite

Non-linear image processing is an active and growing area of research. Non-linear filters include well-known filter classes, such as rank order filters (median, min, max, etc.) and morphological filters (e.g. opening, closing). Rank order filters exhibit excellent robustness properties and provide solutions in many cases, where linear filters are inappropriate. Linear filters have poor performance in the presence of noise that is not additive, as well as in cases where system non-linearities or non-Gaussian statistics are encountered. Non-linear filters based on order statistics can suppress high frequency and impulse noise in an image, avoiding at the same time extensive blurring of the image, since they exhibit good edge preservation properties. They have found numerous applications, such as in digital image analysis, speech processing and coding, digital TV applications, etc. Median and other rank order filters are related to morphological filters. Erosions and dilations are special cases of rank order filters and any rank order filter can be expressed either as a maximum of erosions or as a minimum of dilations. Mathematical morphology offers a unified and powerful approach to numerous image processing problems, such as shape extraction, noise cleaning, thickening, thinning, skeletonising, object selection according to their size distribution, etc. In soft mathematical morphology the standard definitions were slightly relaxed in such a way that a degree of robustness is achieved, while most of the desirable properties of standard morphological operations are maintained. Another, relatively new, approach to mathematical morphology is the fuzzy mathematical morphology. Several attempts, which have been made to apply fuzzy set theory to mathematical morphology, have resulted in different approaches and definitions.In this thesis, a new framework, which extends the concepts of soft mathematical morphology into fuzzy sets, is presented. Images can be considered as arrays of fuzzy singletons on the Cartesian grid. Based on this concept, definitions for the basic fuzzy soft morphological operations are derived. Compatibility with binary soft mathematical morphology, as well as the algebraic properties of fuzzy soft operations are studied. Illustration of the introduced operations is also provided through several examples and experimental results. The proposed framework aims at applications where the benefits of fuzzy image processing and soft mathematical morphology can be combined (noise removal, digital TV, radar scene processing etc.).A decomposition technique suitable for any grey-scale soft morphological structuring element and its hardware implementation is also studied. The size of the structuring element in morphological image processors is usually restricted to 3x3 pixels. The handling of larger size structuring elements on existing machines is not a straightforward process. Moreover, applications such as textural analysis and granulometry require the application of successively larger size structuring ele...

show abstract

unclassified

Ανάπτυξη Και Υλοποίηση Με Εξειδικευμένα Ηλεκτρονικά Κυκλώματα Νέων Τεχνικών Μη Γραμμικής Επεξεργασίας Εικόνων

Γαστεράτος¹

View full text Add to dashboard Cite

show abstract

Image Analysis and Computer Vision: 1998

Rosenfeld

1999

Computer Vision and Image Understanding

View full text Add to dashboard Cite

This paper presents a bibliography of over 2250 references related to computer vision and image analysis, arranged by subject matter. The topics covered include computational techniques; feature detection and segmentation; image and scene analysis; two-dimensional shape; pattern; color and texture; matching and stereo; three-dimensional recovery and analysis; three-dimensional shape; and motion. A few references are also given on related topics, including geometry and graphics, compression and processing, sensors and optics, visual perception, neural networks, artificial intelligence and pattern recognition, as well as on applications.

show abstract

A New Approach to Improve the Cluster-based Parallel Processing Efficiency of High-Resolution Remotely Sensed Image

Shen

Luo

et al. 2011

J Indian Soc Remote Sens

View full text Add to dashboard Cite

A parallel architecture for implementation of filters based on order statistics

Abstract: A new approach for implementing filters based on order statistics is proposed in this letter. As an illustration realisations of range, a-trimmed mean and WMMR filters are presented. q 1998 Elsevier Science B.V. All rights reserved.

Cited by 3 publications

References 8 publications

Ανάπτυξη Και Υλοποίηση Με Εξειδικευμένα Ηλεκτρονικά Κυκλώματα Νέων Τεχνικών Μη Γραμμικής Επεξεργασίας Εικόνων

Ανάπτυξη Και Υλοποίηση Με Εξειδικευμένα Ηλεκτρονικά Κυκλώματα Νέων Τεχνικών Μη Γραμμικής Επεξεργασίας Εικόνων

Image Analysis and Computer Vision: 1998

A New Approach to Improve the Cluster-based Parallel Processing Efficiency of High-Resolution Remotely Sensed Image

Contact Info

Product

Resources

About