Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Multimedia Computing and Systems (ICMCS), 2012 International Conference on

Date 10-12 May 2012

Filter Results

Displaying Results 1 - 25 of 220
  • Efficient text independent speaker identification based on GFCC and CMN methods

    Publication Year: 2012 , Page(s): 90 - 95
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1539 KB) |  | HTML iconHTML  

    The performance of automatic speaker identification systems degrade drastically in the presence of noise and other distortions, especially when there is a noise level mismatch between the training and testing environments. In this experimental research we have studied a recently robust front-end algorithm based on Gammatone Frequency Cepstral Coefficients GFCC combined to Cepstral Mean Normalization CMN technique. Our system using a Gaussian Mixture Models GMM classifier are implemented and tested under MATLAB®7 programming environment with multilevel White Gaussian Noise WGN applied to a test utterances using our proper database containing 51 Arabic speakers. Our aim is to study the performance of this suggested architecture and make a comparison with the conventional Mel Frequency Cepstral Coefficients MFCC method which we have successfully implemented and tested in the previous work. The obtained experimental results confirm the superior performance of the proposed method over MFCC and outperform it in different noisy environments. Our evaluations based on the recognition rate accuracy show that both MFCC and the proposed feature extractor have perfects performances in low-noise environments when Signal per Noise Ratio SNR is greater than 35 dB (practically 100% in all cases), but when the SNR of test signal changed from 0 to 40 dB, the average accuracy of the MFCCs methods is only 50.05%, while the proposed GFCCs extractors combined to CMN normalization still achieves an average accuracy of 55.43%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual-attention-based thumbnail using two-stage GrabCut

    Publication Year: 2012 , Page(s): 96 - 101
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1247 KB) |  | HTML iconHTML  

    This paper proposes a new thumbnail generation method to improve the recognizability of visual attention objects on small displays. Previous methods such as simple scaling reduce the recognizability of original images because the visual attention objects become too small to recognize. When we view thumbnails on small displays such as those of mobile devices, recognizability is indispensable for handling many images simultaneously. To solve the problem of low recognizability of visual attention objects, we adopt GrabCut to extract visual attention objects from an original image and then divide the original image into visual attention objects and a background image. While the background image is reduced to fit the size of a thumbnail, the extracted visual attention objects are merged into the reduced background image to preserve their recognizability. In adopting GrabCut, we propose a two-stage GrabCut method to automate the extraction of attention objects; the extraction was performed by hand in previous methods. Our experimental results show that our proposed method is able to shorten the search time by 44% and improve the precision of the search by 19% in comparison with simple scaling. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identification of Broadband Radio Access Network using the Takagui-Sugeno fuzzy systems and Higher Order Statistics

    Publication Year: 2012 , Page(s): 473 - 477
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1487 KB) |  | HTML iconHTML  

    In this paper, we consider the problem of selective radio channel identification. Two technics are used, the first one is based on Higher Order Statistics (HOS), the second is based on Takagui-Sugeno (TS) fuzzy systems. In order to evaluate the proposed algorithms, we have used two practical selective frequency fading channels called Broadband Radio Access Network (BRAN A and BRAN E) normalized for MC-CDMA systems are considered to perform the proposed technics. The simulation results, for different Signal to Noise Ratio (SNR), demonstrates that: the algorithm based on Higher Order Statistics (HOS) is more efficiency than the TS algorithms in noisy environment - smallest SNR- but the TS algorithm more efficient than the HOS algorithms for highest SNR values. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Revisiting feature level and score level fusion techniques in multimodal biometrics system

    Publication Year: 2012 , Page(s): 881 - 885
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (597 KB) |  | HTML iconHTML  

    The primary application of biometric technology is to analyze human characteristics for security purpose as security issues have been the focused interest in recent years. A survey of different fusion techniques in multimodal biometrics is made. This paper also attempts to identify some of the challenges and issues that confront research in multimodal biometrics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Android mobile augmented reality application based on different learning theories for primary school children

    Publication Year: 2012 , Page(s): 404 - 408
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (782 KB) |  | HTML iconHTML  

    Due to advancements in the mobile technology and the presence of strong mobile platforms, it is now possible to use the revolutionising augmented reality technology in mobiles. This research work is based on the understanding of different types of learning theories, concept of mobile learning and mobile augmented reality and discusses how applications using these advanced technologies can shape today's education systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation effects of lateral coupling between L3 cavity and two quasi waveguides bends in 2D Photonic Crystal Bandpass Filter

    Publication Year: 2012 , Page(s): 1152 - 1156
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1360 KB) |  | HTML iconHTML  

    Based on effects of lateral coupling between the resonant L3 cavity and tow quasi waveguides bends in tow dimensional photonic crystal (2D PhC) who depends strongly on the parameters of geometry of the PC lattice, especially on the dielectric rods sizes. We proposed Photonic Crystal BandPass Filter (PCBPF), the out put transmission spectra of our filter covered three band. Band I covers the wavelength range from 1.331 to 1.355 μm has 86% of transmission power, Band II, from 1.390 to 1.427 μm, has 98% of the transmission power and Band III from 1.46 to 1.507 μm, has 27% of the transmission power. The full width at half maximum bandwidth of these bands is 9.7, 13.1 and 16.4 nm, respectively. This Filter (PCBPF) is proposed for photonic integrated circuits (PIC), wavelength division multiplexing (WDM) systems and sensing applications. The normalized transmissions spectra of this filter are obtained them using 2D Finite Difference Time Domain Method (2D-FDTD). The Photonic Band Gap is calculated by Plane Wave Expansion method (PWE). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new multi-objective particle swarm optimization for reactive power dispatch

    Publication Year: 2012 , Page(s): 1119 - 1124
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1353 KB) |  | HTML iconHTML  

    This paper proposes a new approach of computation using particle swarm in order to resolve multiobjective problems quickly and effectively. This approach is called accelerated multiobjective particle swarm which incorporates vector function as objective function and uses matrix computation to develop the Pareto front unlike the existing multi-objective algorithms which use an external archive. We also propose a novel method of initialization that contributes also in the acceleration of the algorithm. We apply this approach to resolve multi-objective reactive power dispatch problem. Simulations of the proposed algorithm are encouraging for very short CPU time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improvement of cartographic information for the WMS and WFS Web services

    Publication Year: 2012 , Page(s): 815 - 820
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2283 KB) |  | HTML iconHTML  

    The standard geographic web services WMS (web map service) and WFS (web feature service) comprise respectively two methods GetFeature and GetFeatureInfo that allow to obtain attributes associated to a geographic object represented on a map. Most certainly, the returned result brings semantics to the object but requires adaptation to the theme chosen by the user. Our paper proposes the conception and implementation of two interfaces the semi-automatic identification of additional attributes through semantic links in the schema of database, and the presentation of thematic enriched data to the final user. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Affective rendering: Visual effect animations for affecting user arousal

    Publication Year: 2012 , Page(s): 737 - 742
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4398 KB) |  | HTML iconHTML  

    We propose affective rendering as a new affective computing technology which deals with user emotion in the field of image synthesis. Affective rendering is realized in 3 steps - affect sensing, affect analysis and affect adapted rendering. This paper reports several basic experiments carried out for studying how the typical visual parameters, such as color and shape, affect view's arousal, and also describes a prototyping of visual effect animations that can affect viewer's arousal by adapting the visual parameters to user's current arousal estimated from respiration and blood volume. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semantic based 3D model retrieval

    Publication Year: 2012 , Page(s): 195 - 199
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1482 KB) |  | HTML iconHTML  

    Semantic based 3D model retrieval (SB3DMR) has attracted more and more research interests, and is a challenge research problem in the field of content based 3D model retrieval (CB3DMR). Current studies concentrate on the relevance feedback or supervised learning to reduce the semantic gap between 3D model low-level features and high-level semantic. In this paper, a new method in extracting semantic feature for 3D model is proposed. It can get high-level semantic information automatically from low-level. First, invariant descriptors are extracted from 3D models to efficient semantic annotation. An unsupervised learning method to describe the semantics of the 3D models is proposed. Second, and based on the resulting semantic annotation, 3D models are semantically classified. Finally, spatial relationships are used to derive other high-level semantic features to augment our knowledge base and to improve the retrieval accuracy. An ontology based 3D model retrieval framework is used to combine the semantic concepts and visual features and introduce the query by semantic example. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised classification of grayscale image using Probabilistic Neural Network (PNN)

    Publication Year: 2012 , Page(s): 101 - 105
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1741 KB) |  | HTML iconHTML  

    Image classification is a very common step in image analysis process. It is a low-level processing that precedes the step of measuring, understanding and decision. Its purpose is image partitioning into related and homogeneous regions in the sense of a homogeneity criterion. In this paper, we proposed a procedure to determine the optimal number of classes in a grayscale image classification based on a Probabilistic Neural Network (PNN). The used procedure is completely automatic with no parameter adjusting. The results on synthetic images show a high robustness and better performance. The results showed that PNN is a good technique for one-dimensional data classifying. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Service specific overlay composition and reconfiguration

    Publication Year: 2012 , Page(s): 479 - 484
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1588 KB) |  | HTML iconHTML  

    This paper presents a Hybrid Service Overlay Network (H-SON) for composing Service Specific Overlay Networks (SSON) in mobile environments. The overlay topology is organized into dynamically-adaptable hierarchical Chord rings reflecting node mobility and service quality transformation. Moreover, our loss-based utility function is used to predict the client's QoE. Node resources can thus be automatically and dynamically redistributed and established SSONs can be reconfigured before quality levels deteriorate below acceptable levels. The proposed H-SON can accelerate the composition process by limiting service searches into bounded areas and can limit query broadcasts. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improve security of web Browser with stand-alone e-Learning awareness application

    Publication Year: 2012 , Page(s): 852 - 857
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (901 KB) |  | HTML iconHTML  

    We are living in the electronic age where electronic transactions such as e-mail, e-banking, e-commerce, and e-learning etc.. are becoming more and more prominent. To access online for this services, web browser is today's almost unique software used. These days' hackers know that browsers are installed into all computers, and can be used to compromise a machine by distributing malware via malicious or hacked websites. Also these sites use JavaScript to manipulate web browsers and can drive user system to failures, each web browsers have features that define theirs behaviors, unfortunately most of users are unwilling to enable or disable this features, because many of them still do not understand even basic security concepts, This paper will briefly describe some specific web browser features misconfiguration and associated risks, also we present an application that will check configuration of selected web browser in order to find all misconfigured features, and propose to student through tailored e-learning awareness program to reconfigure them securely. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The two first levels of Spider's Web planar graph and The Network planar graph

    Publication Year: 2012 , Page(s): 57 - 60
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (786 KB) |  | HTML iconHTML  

    The theory of graphs, with its diverse applications in natural (Chemistry, Biology) and social sciences in general and in theoretical computer science in particular, is becoming an important component of the mathematics curriculum in colleges and universities all over the world. In this paper we present some theoretical results about some topological indices, like the Wiener index W, Degree distance index DD and the Hyper-Wiener index WW of a graph G. In the application section we are going to apply these theoretic results, for the two first levels of the Spider's Web planar graph Rn and the two first levels of the Network planar graph Gn, to give their Wiener index, Degree distance index and Hyper-Wiener index. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MultiLevel-OrBAC: Multi-Level Integrity management in organization based access control framework

    Publication Year: 2012 , Page(s): 933 - 938
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (798 KB) |  | HTML iconHTML  

    This work proposes a new integrity access control model: “MultiLevel-OrBAC”. On the one hand, we extend OrBAC (Organization-Based Access Control Model) to take into account integrity rules and levels based on the Totel integrity model. On the other hand, we present a representative scenario of secure applications in which integrity and security rules are interacting inside MultiLevel-OrBAC security policy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An MPEG-4 Quadric-based LoD simplification for facial animation

    Publication Year: 2012 , Page(s): 743 - 748
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1291 KB) |  | HTML iconHTML  

    Level of detail (LoD) techniques provide efficient and established tools that reduce 3D models complexity while attempting to preserve their features. While these techniques are well documented and have been applied with proven results, only few solutions attempted to create a solution that is compatible with Motion Picture Experts Group (MPEG-4) facial animation standard, which involves human facial mesh simplification. In this paper we present our work on an adaptive LoD algorithm which prioritises the human face features in the facial mesh and simplifies the animation streams, reducing animation complexity and overhead. Our approach applies continuous LOD to a MPEG-4 compliant model using an extension of Garland's Quadric-Based Surface algorithm and introducing a novel error metric. This is achieved with a novel approach that applies a selective model simplification that is both MPEG-4 compatible and also can simplify animation streams. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised video objects detection and tracking using region based level-set

    Publication Year: 2012 , Page(s): 201 - 206
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1054 KB) |  | HTML iconHTML  

    In this paper, we propose an efficient unsupervised method for moving object detection and tracking. To achieve this goal, we use basically a region-based level-set approach and some conventional methods. Modeling of the background is the first step that initializes the following steps such as objects segmentation and tracking. Our proposed method produces good results and decreases processing time. We present here the main steps of our method and preliminary results which are very encouraging for many applications such as video surveillance and traffic monitoring. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward the construction of a virtual ecosystem by evolving virtual creature's behaviours

    Publication Year: 2012 , Page(s): 350 - 355
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1538 KB) |  | HTML iconHTML  

    In this paper a virtual ecosystem environment with basic physical law and energy concept has been proposed, this ecosystem is populated with 3D virtual creatures that are living in this environment in order to forage food. Artificial behaviours are developed to control virtual creatures. A genetic algorithm with an artificial neural network were implemented together to guarantee some of these behaviours like searching food. Foods are presented in different locations in the virtual ecosystem. The evolutionary process uses the physical properties of the virtual creatures and an external fitness function that will conduct to the expected behaviours. The experiment evolving locomoting virtual creatures show that these virtual creatures try to obtain at least one of the food sources presented in its trajectory. Our best-evolved creatures are able to reach multiple food sources during the simulation time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for mapping UML class into XML data based on technical Specifications

    Publication Year: 2012 , Page(s): 749 - 754
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (771 KB) |  | HTML iconHTML  

    This paper describes a methodology for mapping UML Class into an XML schema. The structure of a class diagram is then translated element by element to XML schema using stepwise procedures. We use XSD schema for define and validate the structure of XML documents. In this paper we use a mathematical formulation model for the mapping UML Class into XML document, and a framework has been developed to validate this technique. The results demonstrating that the proposed approach is feasible correctly and efficiently. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Influence of Dolph-Chebyshev window on speech enhancement

    Publication Year: 2012 , Page(s): 140 - 143
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1279 KB) |  | HTML iconHTML  

    Any audio speech processing done via manipulation of the short-time spectral amplitude requires transformation of the time-domain speech to the frequency domain. The spectrum can then be modified, and finally transformed back to the time domain. This process is done by windowing the speech signal. In this paper, the influence of Dolph-Chebyshev window is studied for the speech enhancement application. In order to investigate the effect and performance of the Dolph-Chebyshev window, a minimum mean-squared error (MMSE) amplitude estimator in the log-spectral domain was used as an algorithm for the speech enhancement. Evaluations were performed by a comparative study in terms of noise reduction and signal distortion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dual-tree complex wavelet in medical ultrasounds images restoration

    Publication Year: 2012 , Page(s): 297 - 303
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1364 KB) |  | HTML iconHTML  

    This paper presents a new denoising method for ultrasound medical image in restoration domain. The approach is based on analysis in Dual-tree wavelet Transform (DT-CWT). Speckle noise degrades the detectability of low-contrast lesions. So, it affects the tasks of human interpretation and diagnosis. Various methods have been developed in the literature; most of them used only the standard wavelet transform (DWT). However, the Discrete Wavelet Transform (DWT) has some disadvantages that undermines its application in image processing. In this study we investigated a performances complex wavelet transform (DT-CWT) combined with Bivariate Shrinkage and Visu-shrinkage. The proposed method was tested on a noisy ultrasound medical image, and the restored images show a great effectiveness of DT-CWT method compared to the classical DWT. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sensorless speed Backstepping Control of induction machine, based on speed MRAS observer

    Publication Year: 2012 , Page(s): 1019 - 1024
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (727 KB) |  | HTML iconHTML  

    In this paper a Sensorless Backstepping Control scheme for rotor speed and rotor flux control of induction motor drive, is proposed. The most interesting point of this technique is to deal with non-linearity of high-order system by using the virtual control variable to make this system simple, and thus the control outputs can be derived step by step through appropriate Lyapunov functions. Rotor speed and rotor flux estimation is made by an observer using the MRAS (Model reference adaptive system) technique. Simulation results are presented to validate the effectiveness of the proposed sensorless control. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Change detection by new DSmT decision rule and ICM with constraints: Application to Argan land cover

    Publication Year: 2012 , Page(s): 107 - 112
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2572 KB) |  | HTML iconHTML  

    The objective of this work is, in the first place, the integration in a fusion process using hybrid DSmT model, both, the contextual information obtained from a supervised ICM classification with constraints and the temporal information with the use of two images taken at two different dates. Secondly, we have proposed a new decision rule based on the DSmP transformation to overcome the inherent limitations of the decision rules thus use the maximum of generalized belief functions. The approach is evaluated on two LANDSAT ETM+ images, the results are promising. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • FPGA-based real-time implementation of distributed system CA-CFAR and Clutter MAP-CFAR with noncoherent integration for radar detection

    Publication Year: 2012 , Page(s): 1093 - 1098
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1795 KB) |  | HTML iconHTML  

    In this work, we propose real time implementation approaches of distributed Constant False Alarm Rate (CFAR) detection with noncoherent integration. The Cell Averaging (CA-CFAR) and Clutter MAP (CMAP-CFAR) detectors are employed as local detectors. The proposed architecture shows that it can be implemented with the advantages of a parallel structure and allows an important optimization of the required FPGA hardware resources utilization. The structure has been implemented using a Virtex-II XC2V1000-4FG456C FPGA board. The FPGA implementation results are presented and discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new approach of e-learning-adaptive based on ant colonies optimisation algorithm

    Publication Year: 2012 , Page(s): 827 - 832
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1156 KB) |  | HTML iconHTML  

    Adaptive E-learning, refers to a training concept in which technology is introduced step by step in all aspects of the business of training. A technique, inspired by the Ant Colony Optimization (ACO), is proposed to optimize the learning path. The proposed platform is modeled by a graph where nodes represent the educational elements (lessons or exercises), and arcs link navigation between them. Each of the arcs is also a value that describes its importance in relation to teaching neighboring arcs. Students are represented by virtual agents (ants) who use these links. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.