By Topic

Proceedings EC-VIP-MC 2003. 4th EURASIP Conference focused on Video/Image Processing and Multimedia Communications (IEEE Cat. No.03EX667)

2-5 July 2003

Go

Filter Results

Displaying Results 1 - 25 of 71
  • Blind source separation of speech signals based on an ICA geometric procedure

    Publication Year: 2003, Page(s):631 - 636 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (332 KB) | HTML iconHTML

    This work explains a new method for blind separation of a linear mixture of sources, based on geometrical considerations concerning the observation space. This new method is applied to a mixture of several sources and it obtains the estimated coefficients of the unknown mixture matrix A and separates the unknown sources. The principles of the new method and a description of the algorithm followed ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Separating images collected in the World Wide Web into two semantic classes: photographs and graphics

    Publication Year: 2003, Page(s):495 - 500 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (419 KB) | HTML iconHTML

    This work presents the classification of images collected on the World Wide Web, using a supervised classification method, called IDS (itemized dichotomizer 3). The classification consists in separating the images into two semantic classes: graphics and photographs. Photographs include natural scenes, like people, faces, animals, flowers, landscapes and cities. Graphics are logos, drawings, icons,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiobjectives genetic snakes: application on audio-visual speech recognition

    Publication Year: 2003, Page(s):625 - 630 vol.2
    Cited by:  Papers (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (396 KB) | HTML iconHTML

    In this article a new optimization of genetic snakes (GS): multiobjectives genetics snakes (MGS) faster and simpler to implement is proposed. They enable us to make converge two snakes in parallel while minimizing energies of different nature. We apply them to the modeling of mouth contours within the framework of the audio-visual speech recognition (AVSR). The proposed AVSR system implements a cl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The statistical characterization of the sea for the segmentation of maritime images

    Publication Year: 2003, Page(s):489 - 494 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (408 KB) | HTML iconHTML

    This paper describes part of an imaging system to indicate possible collision situations between maritime vessels. History shows us that any collision involving a marine craft can have a devastating effect both on human life and the environment. Presented here is a method for the statistical characterization of the sea present in an image and the subsequent segmentation of the image into two regio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiresolution for the detection of xiphoidal sounds in noisy medical audio signals

    Publication Year: 2003, Page(s):619 - 624 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (388 KB) | HTML iconHTML

    In this paper a method we have developed in order to detect particular events (xiphoidal sounds) in swallowing audio signals is presented. The difficulty of the problem comes from the noisy nature of our medical audio signals, due to biological and environmental reasons. Besides, xiphoidal sounds have a highly nonstationary behaviour that makes conventional analysis methods such as Fourier transfo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast recognition of multiple faces using MCM

    Publication Year: 2003, Page(s):435 - 440 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (507 KB) | HTML iconHTML

    In this paper we present the novel minimal classification method (MCM) that provides an elegant and computationally efficient approach to the problem of multiple face recognition. In the classification we use a special set of filters which yield low values of correlation with a given set of images and large values with other natural images. Such filters are called antifaces. The minimal classifica... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech detection in the noisy environment using wavelet transform

    Publication Year: 2003, Page(s):661 - 666 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (365 KB) | HTML iconHTML

    In this article we present speech detection systems based on Daubechie, Coiflet and Symlet wavelet transforms respectively. For each a selection of the most eligible levels of signal decomposition for the corrupted speech detection problem was made. Using those levels the distinction between noise and corrupted signal can be amplified as far as 100 times. Tests were accomplished using a set of Slo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identification of sound source in machine vision sequences using audio information

    Publication Year: 2003, Page(s):601 - 606 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (346 KB) | HTML iconHTML

    Identifying the sound source location in the acquired image for further processing is of concern in image/video processing especially when tracking objects of vibrating or sound making nature in the scene becomes necessary. On the other hand relying on the picture content to identify such objects is not an easy task especially when there are similar objects in the acquired image. In this paper, we... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perceptually transparent audio compression based on a variable bit rate AAC coder

    Publication Year: 2003, Page(s):685 - 690 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (447 KB) | HTML iconHTML

    The paper presents an implementation of a perceptually transparent variable bit rate (VBR) audio coder that complies with the MPEG-4 advanced audio coding (AAC) standard. The coder is based on the MPEG-4 reference software source code of CBR coder. With small modifications in the reference source code a coder guaranteeing perceptual transparency is achieved at compression ratios considerably bette... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards robust steganography using T-codes

    Publication Year: 2003, Page(s):707 - 711 vol.2
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (348 KB) | HTML iconHTML

    Steganography is the art of hiding messages within some cover media. The word steganography derives from Greek, and literally means covered writing. Messages can be hidden in any media. Typical media include digital images, sound, and video. Unfortunately, the hidden message is not resistant to media operations. For example, cropping an image that has a hidden message can result in corrupting the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The influence of increasing the tone value on the printing reproduction quality

    Publication Year: 2003, Page(s):545 - 550 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (395 KB) | HTML iconHTML

    In graphic reproduction, because of the specific features of the process influenced by different parameters, deformities of the screen element happen influencing more or less the reproduction quality decrease at consumers during the observation of the graphic product in real conditions. This work investigates the influence of the tone values increase on the quality decrease of the printed graphic ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An image segmentation tool (IST)

    Publication Year: 2003, Page(s):483 - 488 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (373 KB) | HTML iconHTML

    An image segmentation tool designed for creation and manipulation of contours is presented. To deploy software which satisfies its intended purpose, one has to meet and engage users to expose the real requirements of the system. Thus, the main goal of this paper is to define a functional image of tool and to present the user interface of this image segmentation tool. In conclusion directions for t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Measuring the motion similarity in video indexing

    Publication Year: 2003, Page(s):507 - 512 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (413 KB) | HTML iconHTML

    Recent growth in the number of digital videos available motivates the development of video databases for the efficient management of these videos. Common video databases use image information calculated from key frames such as color, texture, shape to index videos, and only few of them are capable to store and retrieve motion information. In this paper we present a method for automatic motion base... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A speech recognition algorithm based on the features of Croatian language

    Publication Year: 2003, Page(s):613 - 618 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (339 KB) | HTML iconHTML

    The paper examines an acoustic-phonetic, approach to speech recognition, with elements of artificial intelligence. The vowels of the Croatian language are assumed as examples of speaking segments. Frequency transformation has been realized passing the speech segments through the corresponding selective filter banks. It has been shown that on the outputs of this filter bank the significantly compar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Picture quality evaluation strategy using a watermarking technique

    Publication Year: 2003, Page(s):721 - 726 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (372 KB) | HTML iconHTML

    Measurement of image quality is crucial for many image processing algorithms. In this paper, a "no-reference" picture quality evaluation is proposed. We use watermarking as a tool for evaluating quality. We embed, in an image, a watermark. Measures are computed between original and extracted watermarks instead of image to evaluate picture quality between the original image and the degraded one. Ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech signal reconstruction for real-time voice transmission over the Internet

    Publication Year: 2003, Page(s):557 - 562 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (337 KB) | HTML iconHTML

    The interpolation approaches to the shape recovery of a speech signal in transmission over packet switched communications networks are proposed. The samples of a signal fragments are mixed and transmitted in correspondence with standard procedure of packet-switched transmission. After reception a reverse permutation is made. In the case of packet losses missing samples are separated by several sam... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of articulatory-based multilevel segmental HMMs for phonetic classification in ASR

    Publication Year: 2003, Page(s):655 - 660 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (380 KB) | HTML iconHTML

    A simple multiple-level HMM is presented in which speech dynamics are modelled as linear trajectories in an intermediate, formant-based representation and the mapping between the intermediate and acoustic data is achieved using one or more linear transformations. An upper-bound on the performance of such a system is established. Experimental results on the TIMIT corpus demonstrate that, if the dim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ridge polynomial networks in pattern recognition

    Publication Year: 2003, Page(s):519 - 524 vol.2
    Cited by:  Papers (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (370 KB) | HTML iconHTML

    Ridge polynomial networks (RPNs) are a special class of high order neural networks, which are computationally much more efficient than traditional high order neural networks. Motivated by the ability of high order NNs to perform shift and rotation invariant pattern recognition tasks, we apply RPNs for function approximation and character recognition. We are using features from the image block repr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An evaluation method for network systems based on delay jitter analysis

    Publication Year: 2003, Page(s):569 - 574 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (332 KB) | HTML iconHTML

    This paper proposes a method for evaluating network systems based on delay-jitter analysis using generalized stochastic Petri nets (GSPN). Systems are modeled by GSPN and tagged client approach. The mean delay time and its variance for systems are calculated by using equations derived from a Markov chain of the GSPN model. Systems can be evaluated statistically by the obtained values. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Issues concerning usability of 802.11 networks for real-time service transport

    Publication Year: 2003, Page(s):583 - 588 vol.2
    Cited by:  Papers (1)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (399 KB) | HTML iconHTML

    There has been a considerable expansion of alternative, VOIP based enterprise telephony networks in recent years. These networks have introduced stable and flexible cores that can be used to accommodate traffic from diverse set of edge applications. One of the newer developments in the access part of the network is introduction of wireless Ethernet as a medium that enables mobility and flexibility... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Testing the methods of sound signal compression

    Publication Year: 2003, Page(s):595 - 600 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (316 KB) | HTML iconHTML

    Three sound signal compression methods are being offered allowing (depending on the application aim) finding the best trade-off between the compression efficiency and the realization complexity. The testing of the methods proposed was done on a half-nature simulation system including personal computers 10 Mbit/sec Ethernet LAN and the sound signal input/output means. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced software implementation of MPEG-4 AAC audio encoder

    Publication Year: 2003, Page(s):679 - 684 vol.2
    Cited by:  Papers (1)  |  Patents (17)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (329 KB) | HTML iconHTML

    MPEG-4 AAC audio encoder is developed. AAC main and AAC low complexity object types, defined as part of main profile in general audio part of ISO/IEC 14496-3 (MPEG-4) standard, are implemented. Encoder targets high-quality, wideband, complex audio. Encoder was carefully designed to respect present accomplishments in audio coding (standardized in MPEG-4). At the same time, several implementation no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Blind watermarking via low frequency component modification

    Publication Year: 2003, Page(s):701 - 706 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (427 KB) | HTML iconHTML

    In this paper we present a blind low frequency watermarking scheme. We obtain a robustness improvement to most common image processing operations by embedding the watermark in the approximation image of the original image. In order to embed the watermark with minimal loss in image fidelity, the watermark strength is modulated according to the local image characteristics. We generate a visual mask ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Web- based multimedia courseware: applied photonics

    Publication Year: 2003, Page(s):741 - 746 vol.2
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (444 KB) | HTML iconHTML

    Distance education and nontraditional classrooms have the capability to reach more students using specialised instruction, self-paced learning and virtual laboratories (and/or virtual instruments). While a good learning experience can be obtained from such a purely simulation systems, in many situations, it is commonly recognised that effective and complete learning, especially in engineering and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Similarity hypergraph representation for impulsive noise reduction

    Publication Year: 2003, Page(s):539 - 544 vol.2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (369 KB) | HTML iconHTML

    In this paper, a new approach to the problem of impulsive noise reduction in image is presented. First, an image neighborhood hypergraph representation using a similarity measure is computed. Next, a detection procedure based on hypergraph properties is used to classify hyperedges either as noisy, or clean data. Then we apply a nonlinear filter to noisy detected pixels. The results show that the p... View full abstract»

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