An efficient recursive edge-aware filter

Cigla, Cevahir
Alatan, Abdullah Aydın
In this study, an efficient edge-aware filtering methodology, namely permeability filter, that exploits recursive updates among horizontal and vertical axes, is extended for common image filtering applications, including denoising, segmentation and depth upscaling. Besides, an 8-neighbor update methodology, that is applicable for all type of recursive filters, is proposed extending orthogonally generated supporting regions into multi-directional support. This extension provides fine smoothing, especially at object boundaries, and yields crisp aggregation regions for each pixel. Since it provides geometrically stable connected support regions for each pixel, the recursive filters remove the dependency on pre-defined windows that is common among the state-of-the-art edge-aware filters, and also provide complete content adaptability. Based on extensive experiments against popular edge-aware filters, it can be concluded that the permeability filter outperforms most of the state-of-the-art techniques in terms of both speed and precision, especially for geometry dependent applications, such as depth data up-scaling and stereo matching; while providing a competitive segmentation and de-nosing capability. Besides, the proposed multi-direction extension methodology significantly improves the performances of recursive filters in almost each application with up to three times increase in computation time. This remarkable performance is due to the unification of connected support regions by soft weights, while preventing over smoothing and enabling crisp models that improve performance on the specified applications. In conclusion, permeability filter and its proposed 8-neighbor recursion methodology is an efficient alternative to edge-aware filters in many application areas by the proposed multi-directional support with window size independency and providing high performance with quite low computational complexity.


An adaptive PHD filter for tracking with unknown sensor characteristics
Zhao, Yuxin; Yin, Feng; Gunnarsson, Fredrik; Amirijoo, Mehdi; Özkan, Emre; Gustafsson, Fredrik (2013-07-09)
The particle filter provides a general solution to the nonlinear filtering problem with arbitrarily accuracy. However, the curse of dimensionality prevents its application in cases where the state dimensionality is high. Further, estimation of stationary parameters is a known challenge in a particle filter framework. We suggest a marginalization approach for the case of unknown noise distribution parameters that avoid both aforementioned problem. First, the standard approach of augmenting the state vector w...
An adaptive, energy-aware and distributed fault-tolerant topology-control algorithm for heterogeneous wireless sensor networks
Deniz, Fatih; Bagci, Hakki; KÖRPEOĞLU, İBRAHİM; Yazıcı, Adnan (2016-07-01)
This paper introduces an adaptive, energy-aware and distributed fault-tolerant topology control algorithm, namely the Adaptive Disjoint Path Vector (ADPV) algorithm, for heterogeneous wireless sensor networks. In this heterogeneous model, we have resource-rich supernodes as well as ordinary sensor nodes that are supposed to be connected to the supernodes. Unlike the static alternative Disjoint Path Vector (DPV) algorithm, the focus of ADPV is to secure supernode connectivity in the presence of node failures...
An efficient image retrieval system using Ordered Weighted Aggregation
Arslan, Serdar; Yazıcı, Adnan (2006-12-08)
In this study, an XML based content-based image retrieval system that combines three visual descriptors of MPEG-7(Dominant Color (DC), Color Layout (CL) and Edge Histogram (EH)) is introduced. The system is extended to support high dimensional indexing for efficient search and retrieval from a native XML-based DBMS. To do this, an index structure, called M-Tree, which uses Euclidean distance function for each feature, is used. In addition the Ordered Weighted Aggregation (OWA) operators are adapted for aggr...
Continuous-time nonlinear estimation filters using UKF-aided gaussian sum representations
Gökçe, Murat; Kuzuoğlu, Mustafa; Department of Electrical and Electronics Engineering (2014)
A nonlinear filtering method is developed for continuous-time nonlinear systems with observations/measurements carried out in discrete-time by means of UKFaided Gaussian sum representations. The time evolution of the probability density function (pdf) of the state variables (or the a priori pdf) is approximated by solving the Fokker-Planck equation numerically using Euler’s method. At every Euler step, the values of the a priori pdf are evaluated at deterministic sample points. These values are used with Ga...
An efficient local search method guided by gradient information for discrete coefficient FIR filter design
Çiloğlu, Tolga (2002-10-01)
A new local search method for the design of linear phase FIR filters with discrete valued coefficients is introduced in this paper. Conventional minimax criterion and normalized peak ripple magnitude (NPRM) are taken as objective functions. The principle is to search along low gradient routes with priority and to direct the search toward steeper sides as improved solutions cease to appear. The characteristics of the objective functions have been explained and used to devise the method. The method is novel i...
Citation Formats
C. Cigla and A. A. Alatan, “An efficient recursive edge-aware filter,” SIGNAL PROCESSING-IMAGE COMMUNICATION, pp. 998–1014, 2014, Accessed: 00, 2020. [Online]. Available: