Laboratoire Dingenierie Des Systemes Of Versailles Lisv

Vélizy-Villacoublay, France

Laboratoire Dingenierie Des Systemes Of Versailles Lisv

Vélizy-Villacoublay, France

Time filter

Source Type

Nachar R.A.,University of Balamand | Inaty E.,University of Balamand | Bonnin P.J.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Alayli Y.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
Security and Communication Networks | Year: 2015

CAPTCHA is a security technique to allow a computer application to distinguish between computer and human access. Most of now a day CAPTCHA words have their characters connected together which makes them very difficult to be segmented and recognized. In this paper we present an efficient technique that first benefits from the intersections between characters in a word and then segment it based on the recognition of each segmented character. Edge corners (ECs) are used in both segmentation and recognition phases. A novel fuzzy logic-based scheme is proposed to match characters using their ECs. Experimental results show the efficiency of the proposed scheme in terms of success rate using a large set of CAPTCHA's words. © 2015 John Wiley & Sons, Ltd.


Al Nachar R.,University of Balamand | Inaty E.,University of Balamand | Bonnin P.J.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Alayli Y.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
Proceedings of the Mediterranean Electrotechnical Conference - MELECON | Year: 2014

This paper presents a novel method to find corners that are well located and stable interest points in a given image. Our corners are defined as intersection points of non collinear straight image edges, which are very robust against various image transformations like image scaling, rotation, translation and also to viewpoint and illumination changes. Some light updates on the linking edge step that should be applied in order to extract edges and their intersections that construct the searched corners are also discussed. Experiments conducted on real images demonstrate that the proposed method is able to achieve a very good performance in accuracy, stability and especially computational efficiency in comparison with existing methods. © 2014 IEEE.


Al Nachar R.,University of Balamand | Inaty E.,University of Balamand | Bonnin P.J.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Alayli Y.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications | Year: 2014

A new algorithm to detect straight edge parts which form the contour of an object presented in an image is discussed in this paper. This algorithm is very robust and can detect true straight edges even when their pixel's locations are not straight due to natural noise at the object borders. These straight edges are than used to report and classify contour's corners according to their angle and their adjacent segments lengths. A new technique for polygonal approximation is also presented to find the best set among these corners to construct the polygon vertices that best describe the approximating contour. It starts by eliminating the corners, one after the other using Iterative Corner Suppression (ICS) process. This in turn enables us to obtain the smallest possible error in the approximation. Experimental results demonstrate the efficiency of this technique in comparison with recently proposed algorithms. Copyright © 2014 SCITEPRESS - Science and Technology Publications. All rights reserved.


Al Nachar R.,University of Balamand | Inaty E.,University of Balamand | Bonnin P.J.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Alayli Y.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
Integrated Computer-Aided Engineering | Year: 2015

This paper presents a new algorithm for image co-registration using dominant corners located on the image's edges under the assumption that the deformation between the successive images is modeled by an affine transformation. This assumption is guaranteed when the time interval between acquired images is small like in a video sequence. Therefore, it is mainly dedicated for motion analysis. The method detects first straight edges of an object contour then classifies their intersection points as contour's corners characterized by their angles and adjacent segments lengths. The suppressor starts then to eliminate iteratively the weak corners until reaching a set of dominant ones called "Dominant Corners". These dominant corners are shown to be very repeatable under affinity transformation. A Primitive is constructed by four consecutive dominant corners located on the same contour. The invariant measure that characterizes each primitive is the ratio of areas of two triangles constructed by two triplets selected from these four corners and the corners directions difference. The primitives are formed in the two studied images from an image sequence. All primitives are used to vote for the best affine model that relates the two images. The method used in primitive construction will lead to an important enhancement over existing methods in the voting process in time and accuracy. This method is tested on real images and good results are reported. © 2015 - IOS Press and the author(s). All rights reserved.


Al Nachar R.,University of Balamand | Inaty E.,University of Balamand | Bonnin P.J.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Alayli Y.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications | Year: 2014

This paper presents a new algorithm for image registration working on an image sequence using dominant corners located on the image's edges under the assumption that the deformation between the successive images can be modeled by an affine transformation. To guarantee this assumption, the time interval between acquired images should be small like the time interval in a video sequence. In the edge image, dominant corners are extracted per linked contour and form a polygon that best approximates the current linked contour. The number of these dominant corners per contour is derived automatically given an approximation error. These dominant corners are shown to be very repeatable under affinity transformation. Then, a Primitive is constructed by four dominant corners. The invariant measure that characterizes each primitive is the ratio of areas of two triangles constructed by two triplets selected from these four corners. Copyright © 2014 SCITEPRESS - Science and Technology Publications. All rights reserved.


Dourlens S.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Ramdane-Cherif A.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
Studies in Computational Intelligence | Year: 2011

Robot software tend to be complex due to management of sensors and actuators in real time facing uncertainty and noise and the more complex tasks to realize in different situations like the human robot multimodal interaction task. This implies a large amount of events to exchange and to process. Robotics intelligent Architecture must be well-conceived to reduce this complexity. Information must be well organized and meaning of situation must be quickly extracted to take decision. Meaning of the situation and situation refinement require the development of a description of the current relationships among entities and events in the environment context. Extraction of meaning and ontological storage of events are very important for interpretation. Human Robot Interaction involves three main parts: awareness and acquisition context, interpretation context and execution context. They define scenarios of multimodal interaction to realize the precondition part called fusion, and the post condition part called fission. In the aim to solve the above problem, we have designed a new architecture using semantic agents and services. We propose in this chapter, simple and efficient components to any multimodal interaction architecture requirements and universal, compliant and generic architecture using a common knowledge representation language. Our framework is designed for high level data fusion, fission and components management. We don't focus on hardware parts, sensors and actuators. Semantic knowledge is expressed in domain ontologies that permit to extract the situational meaning about any entities in the environment, monitor and adapt the architecture if necessary. In this objective, we apply a narrative knowledge representation language to the memory of agents in a distributed network. We also present the structure and extension of the network for agents to act in ubiquitous environments. © 2011 Springer-Verlag Berlin Heidelberg.


Bertrand S.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Bruneau O.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Ouezdou F.B.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Alfayad S.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
Mechanism and Machine Theory | Year: 2012

This paper presents the closed-form solutions of IKMs (Inverse Kinematic Models) of the anthropomorphic biped robot HYDROïD which has 8 active DOFs (Degrees Of Freedom) per leg. From a general point of view, six IKMs are developed in this article. Moreover, a new approach to resolve the redundancy and the particular DOF distribution of the robot is suggested. This approach is validated and proves efficiency according to different aspects. Firstly, the increase of the workspace and the flexibility offered during walking motion is discussed. Furthermore, the coordination between the two internal/external DOFs of the leg allows the reduction of the joint motion range and energy consumption. The last point is presented through various simulations of walking motion in the non-redundant and redundant cases. To do that, an existing control strategy, developed at the Laboratoire d'Ingénierie des Systèmes de Versailles (LISV), is adapted, improved and used to perform walking motion. It uses homogeneous transformation matrices for the high level control, takes into account gait planning, the robot's structural parameters and the robot's sensor measurements. © 2011 Elsevier Ltd All rights reserved.


Madani T.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv | Daachi B.,Grenoble Institute of Technology | Benallegue A.,Laboratoire Dingenierie Des Systemes Of Versailles Lisv
Robotics and Autonomous Systems | Year: 2013

In this paper, a variable structure adaptive controller is proposed for redundant robot manipulators constrained by moving obstacles. The main objective of the controller is to force the model states of the robot to track those of a chosen reference model. In addition, the controller is designed directly in Cartesian space and no knowledge on the dynamic model is needed, except its structure. The parameters of the controller are adapted using adaptive laws obtained via Lyapunov stability analysis of the closed loop. The performances of the proposed controller are evaluated using a 3 DOF robot manipulator evolving in a vertical plane constrained by a mobile obstacle. The obtained results show its effectiveness compared to other tested variable structure controllers. © 2013 Elsevier B.V. All rights reserved.

Loading Laboratoire Dingenierie Des Systemes Of Versailles Lisv collaborators
Loading Laboratoire Dingenierie Des Systemes Of Versailles Lisv collaborators