Souham Meshoul

Ant colony system with extremal dynamics for point matching and pose estimation

For a point-based image registration method, point matching is a hard and a computationally intensive task, especially when issues of noisy and outlying data have to be considered. In this paper we cast the problem as a combinatorial optimization task and describe a global optimization method to achieve robust point matching and pose estimation for image registration purposes. The basic idea is to use an ant colony system (ACS) as a population based search strategy to evolve promising starting solutions, i.e affine transformations. An appropriate local search inspired by extremal optimization is developed and embedded within the search strategy to refine the solutions found. Experimental results are very promising and show the ability of the method to cope with outliers and achieve robust pose estimation.

On solving edge detection by emergence

Emergence is the process of deriving some new and coherent structures, patterns and properties in a complex system. Emergent phenomena occur due to interactions (non-linear and distributed) between the elements of a system over time. An important aspect concerning the emergent phenomena is that they are observable on a macroscopic level, whereas they are produced by the interaction of the elements of the system on a microscopic level. In this paper, we attempt to grab some emergence and complexity principles in order to apply them for problem solving. As an application, we consider the edge detection problem a key task in image analysis. Problem solving by emergence consists in discovering the local interaction rules, which will be able to produce a global solution to the problem that the system faces. More clearly, it consists in finding the local rules which will have some awaited and adequate global behavior, to solve a given problem. This approach relies on evolving cellular automata using a genetic algorithm. The aim is to find automatically the rules that allow solving the edge detection problem by emergence. For the sake of simplicity and convenience, the proposed method was tested on a set of binary images,. Very promising results have been obtained.

A quantum inspired evolutionary framework for multi-objective optimization

This paper provides a new proposal that aims to solve multi-objective optimization problems (MOPs) using quantum evolutionary paradigm. Three main features characterize the proposed framework. In one hand, it exploits the states superposition quantum concept to derive a probabilistic representation encoding the vector of the decision variables for a given MOP. The advantage of this representation is its ability to encode the entire population of potential solutions within a single chromosome instead of considering only a gene pool of individuals as proposed in classical evolutionary algorithms. In the other hand, specific quantum operators are defined in order to reward good solutions while maintaining diversity. Finally, an evolutionary dynamics is applied on these quantum based elements to allow stochastic guided exploration of the search space. Experimental results show not only the viability of the method but also its ability to achieve good approximation of the Pareto Front when applied on the multi-objective knapsack problem.

A novel approach for Online signature verification using fisher based probabilistic neural network

The rapid advancements in communication, networking and mobility have entailed an urgency to further develop basic biometric capabilities to face security challenges. Online signature authentication is increasingly gaining interest thanks to the advent of high quality signature devices. In this paper, we propose a new approach for automatic authentication using dynamic signature. The key features consist in using a powerful combination of linear discriminant analysis (LDA) and probabibilistic neural network (PNN) model together with an appropriate decision making process. LDA is used to reduce the dimensionality of the feature space while maintining discrimination between users. Based on its results, a PNN model is constructed and used for matching purposes. Then a decision making process relying on an appropriate decision rule is performed to accept or reject a claimed identity. Data sets from SVC 2004 have been used to assess the performance of the proposed system. The results show that the proposed method competes with and even outperforms existing methods.

Robust Point Correspondence for Image Registration Using Optimization with Extremal Dynamics

Robust Point Correspondence for image registration is still a challenging problem in computer vision and many of its related applications. It is a computationally intensive task which requires an expensive search process especially when issues of noisy and outlying data have to be considered. In this paper, we cast the problem as a combinatorial optimization task and we solve it using extremal optimization, a new general purpose heuristic recently proposed by Boettcher and colleagues. We show how this heuristic has been tailored to the point correspondence problem and resulted in an efficient outlier removal scheme. Experimental results are very encouraging and demonstrate the ability of the proposed method in identifying outliers and achieving robust matching.

Quantum Genetic Algorithm for Multiple RNA Structural Alignment

RNA structural alignment is one of key issues in bioinformatics. It aims to elucidate conserved structural regions among a set of sequences. Finding an accurate conserved structure is still difficult and a time consuming task that involves structural alignment as a prerequisite. In this work, structural alignment is viewed as an optimization process. A quantum based genetic algorithm is proposed to carry out this process. The main features of this algorithm consist in the quantum structure used to represent alignments and the quantum operators defining the overall evolutionary dynamic of the genetic algorithm. The quantum structure relies on the concept of qubit and allows efficient encoding of individuals. Experiments on a wide range of data sets have shown the effectiveness of the proposed framework and its ability to achieve good quality solutions.

A quantum evolutionary algorithm for data clustering

The emerging field of quantum computing has recently created much interest in the computer science community due to the new concepts it suggests to store and process data. In this paper, we explore some of these concepts to cope with the data clustering problem. Data clustering is a key task for most fields like data mining and pattern recognition. It aims to discover cohesive groups in large datasets. In our work, we cast this problem as an optimisation process and we describe a novel framework, which relies on a quantum representation to encode the search space and a quantum evolutionary search strategy to optimise a quality measure in quest of a good partitioning of the dataset. Results on both synthetic and real data are very promising and show the ability of the method to identify valid clusters and also its effectiveness comparing to other evolutionary algorithms.

A quantum evolutionary algorithm for effective multiple sequence alignment

This paper describes a novel approach to deal with multiple sequence alignment (MSA). MSA is an essential task in bioinformatics which is at the heart of denser and more complex tasks in biological sequence analysis. MSA problem still attracts researcher’s attention despite the significant research effort spent to solve it. We propose in this paper a quantum evolutionary algorithm to improve solutions given by CLUSTALX package. The contribution consists in defining an appropriate representation scheme that allows applying successfully on MSA problem some quantum computing principles like qubit representation and superposition of states. This representation scheme is embedded within an evolutionary algorithm leading to an efficient hybrid framework which achieves better balance between exploration and exploitation capabilities of the search process. Experiments on a wide range of data sets have shown the effectiveness of the proposed framework and its ability to improve by many orders of magnitude the CLUSTALX’s solutions.

Combining Fisher Discriminant Analysis and probabilistic neural network for effective on-line signature recognition

The advent of new technologies enables capturing the dynamic of a signature. This has opened a new perspective for the possible use of signatures as a basis for an authentication system that is accurate and trustworthy enough to be integrated in practical applications. Automatic online signature recognition and verification is one of the biometric techniques being the subject of a growing and intensive research activity. In this paper, we address this problem and we propose a two-stage approach for personal identification. The first stage consists in the use of linear discriminant analysis to reduce the dimensionality of the feature space while maintaining discrimination between user classes. The second stage consists in tailoring a probabilistic neural network for effective classification purposes. Several experiments have been conducted using SVC2004 database. Very high classification rates have been achieved showing the effectiveness of the proposed approach.

An Artificial Immune System for Multimodality Image Alignment

Alignment of multimodality images is the process that attempts to find the geometric transformation overlapping at best the common part of two images. The process requires the definition of a similarity measure and a search strategy. In the literature, several studies have shown the ability and effectiveness of entropy-based similarity measures to compare multimodality images. However, the employed search strategies are based on some optimization schemes which require a good initial guess. A combinatorial optimization method is critically needed to develop an effective search strategy. Artificial Immune Systems (AIS S ) have been proposed as a powerful addition to the canon of meta-heuristics. In this paper, we describe a framework which combines the use of an entropy-based measure with an AIS-based search strategy. We show how AIS S have been tailored to explore efficiently the space of transformations. Experimental results are very encouraging and show the feasibility and effectiveness of the proposed approach.