Time filter

Source Type

Papakostas G.A.,Human Machines Interaction HMI Laboratory | Koulouriotis D.E.,Democritus University of Thrace | Karakasis E.G.,Democritus University of Thrace | Tourassis V.D.,Democritus University of Thrace
Neurocomputing | Year: 2013

A novel descriptor able to improve the classification capabilities of a typical pattern recognition system is proposed in this paper. The introduced descriptor is derived by incorporating two efficient region descriptors, namely image moments and local binary patterns (LBP), commonly used in pattern recognition applications, in the last decades. The main idea behind this novel feature extraction methodology is the need of improved recognition capabilities, a goal achieved by the combinative use of these descriptors. This collaboration aims to make use of the major advantages each one presents, by simultaneously complementing each other, in order to elevate their weak points. In this way, the useful properties of the moments and moment invariants regarding their robustness to the noise presence, their global information coding mechanism and their invariant behaviour under scaling, translation and rotation conditions, along with the local nature of the LBP, are combined in a single concrete methodology. As a result a novel descriptor invariant to common geometric transformations of the described object, capable to encode its local characteristics, is formed and its classification capabilities are investigated through massive experimental scenarios. The experiments have shown the superiority of the introduced descriptor over the moment invariants, the LBP operator and other well-known from the literature descriptors such as HOG, HOG-LBP and LBP-HF. © 2012 Elsevier B.V. Source

Kaburlasos V.G.,Human Machines Interaction HMI Laboratory | Kehagias A.,Aristotle University of Thessaloniki
IEEE Transactions on Fuzzy Systems | Year: 2014

A fuzzy inference system (FIS) typically implements a function f: ℝN: → T, where the domain set ℝ denotes the totally ordered set of real numbers, whereas the range set T may be either T = ℝM (i.e., FIS regressor) or T may be a set of labels (i.e., FIS classifier), etc. This study considers the complete lattice (F,≺) of Type-1 Intervals' Numbers (INs), where an IN F can be interpreted as either a possibility distribution or a probability distribution. In particular, this study concerns the matching degree (or satisfaction degree, or firing degree) part of an FIS. Based on an inclusion measure function σ : F × F → [0,1] we extend the traditional FIS design toward implementing a function f: FN → T with the following advantages: 1) accommodation of granular inputs; 2) employment of sparse rules; and 3) introduction of tunable (global, rather than solely local) nonlinearities as explained in the manuscript. New theorems establish that an inclusion measure σ is widely (though implicitly) used by traditional FISs typically with trivial (i.e., point) input vectors. A preliminary industrial application demonstrates the advantages of our proposed schemes. Far-reaching extensions of FISs are also discussed. © 2014 IEEE. Source

Tsougenis E.D.,Democritus University of Thrace | Papakostas G.A.,Human Machines Interaction HMI Laboratory | Koulouriotis D.E.,Democritus University of Thrace
Multimedia Tools and Applications | Year: 2015

The use of image moments as host coefficients constitutes one of the hot topics in image watermarking field due to their robust behavior. Recenlty, a new approach called separable moments (SMs) has been introduced representing an image as combinations of different orthogonal polynomials that generate a series of new moment families. The scope of the present work is to introduce the specific transformations to the image watermarking field by evaluating their security capability under a wide range of common signal processing and geometric attacks. Furthermore, their ability of carrying large binary watermark messages is also examined. The performance of the proposed moment families is evaluated by a comparison to the original moments and a state-of-the-art method. The experimental results justified that a number of the studied transformations outperforms the benchmark method and occasionally the original moment families. Moreover, specific separable moment families are free of instabilities to the higher order coefficients where the extra watermark information is carried. A significant conclusion lies on the adoption of properties (locality, stability) between the generated separable moment families that lead to the enhancement of the basic watermarking requirements (robustness, imperceptibility and capacity) of the proposed watermarking method. The present work justifies that discrete orthogonal SMs constitute a new attractive transformation for the image moment-based watermarking field. © 2013, Springer Science+Business Media New York. Source

Karakasis E.G.,Democritus University of Thrace | Papakostas G.A.,Human Machines Interaction HMI Laboratory | Koulouriotis D.E.,Democritus University of Thrace | Tourassis V.D.,Democritus University of Thrace
Pattern Recognition | Year: 2013

In this work we introduce a generalized expression of the weighted dual Hahn moment invariants up to any order and for any value of their parameters. In order for the proposed invariants to be formed, the weighted dual Hahn moments (up to any order and for any value of their parameters) are expressed as a linear combination of geometric ones. For this reason a formula expressing the nth degree dual Hahn polynomial, for any value of its parameters, as a linear combination of monomials (cr·xr), is proved. In addition, a recurrent relation for the fast computation of the aforementioned monomials coefficients (cr) is also given. Moreover, normalization aspects of the generalized weighted dual Hahn moment invariants are discussed, while a modification of them is proposed in order to avoid their numerical instabilities. Finally, experimental results and classification scenarios, including datasets of natural scenes, evaluate the proposed methodology. © 2013 Elsevier Ltd. All rights reserved. Source

Tsougenis E.D.,Democritus University of Thrace | Papakostas G.A.,Human Machines Interaction HMI Laboratory | Koulouriotis D.E.,Democritus University of Thrace | Tourassis V.D.,Democritus University of Thrace
Optics and Laser Technology | Year: 2013

A successful image watermarking method is identified by the high performance in a number of basic requirements such as robustness, imperceptibility, capacity and complexity. Enhancement could be achieved through an adaptive process that handles individually the embedded information to each coefficient. The specific need for adaptivity is justified through this work by a set of experiments applied to the traditional moment families (Zernike, Pseudo-Zernike, Tchebichef), where more optimum results are produced. The extensive study of Polar Harmonic Transforms' (PHTs) significance parameters (order, magnitude) along with the use of a generalized embedding strength calculation process, easily applied to circularly orthogonal transformations, leads to a promising solution of the adaptivity issue. Experimental results justify that the proposed image watermarking scheme clearly outperforms the compared methods in terms of robustness, capacity and complexity and promotes the traditional schemes to a next generation of moment-based image watermarking. © 2013 Elsevier Ltd. All rights reserved. Source

Discover hidden collaborations