Academic & Scientific Articles

Permanent URI for this communityhttp://dl.cerist.dz/handle/CERIST/3

Browse

Author: search.filters.author.Hamami, Latifa

Search Results

Now showing 1 - 10 of 23
  • Thumbnail Image
    Item
    Error Drift Compensation for Data Hiding of the H.264/AVC
    (Romanian Society of Control Engineering and Technical Informatics, 2013) Bouchama, Samira; Hamami, Latifa; Aliane, Hassina
    The error propagation problem is one of the most attractive issues in the field of data hiding of compressed video because the achievement of several data hiding characteristics remains dependant on it. In this paper, a solution to compensate the error propagation is proposed for data hiding of the H.264/AVC. The error compensation is performed by a prior measurement of the introduced error in the watermarked block or in the neighbouring blocks. Two schemes are proposed: The first algorithm exploits the method of watermarking paired-coefficients in each block in order to bring the error to the middle of the block matrix. The distortion caused by each paired-coefficient is calculated in order to give a watermarking priority to the pairs which introduce the minimum error. In the second scheme, the error estimated in the neighbouring blocks is reduced from the residuals during the encoding process. In both schemes, results show that an important improvement of the video quality can be achieved and a good compromise is provided between the video distortion, the bitrate and the embedding.
  • Thumbnail Image
    Item
    Les Algorithmes génétiques Application à la segmentation des images
    (CERIST, Alger, 2004) Lassouaoui, Nadia; Hamami, Latifa; Nouali-Taboudjemat, Nadia
    Les algorithmes génétiques ont des propriétés qui en font des candidats de choix pour résoudre des problèmes d’optimisation dans lesquels la taille de l’espace de recherche est importante, où les paramètres interagissent de manière complexe et où très peu d’informations sur la fonction à optimiser sont disponibles. Ces propriétés ont motivé leur application à divers domaines. Dans ce papier, nous présentons les fondements des AGs ; les travaux récents effectués en analyse d’images et plus particulièrement en segmentation ; nous étudions en détails et appliquons un algorithme non supervisé de segmentation, nous l’améliorons en proposant un nouvel opérateur de mutation. Et avec le multiseuillage par Fisher, nous l’avons adapté à la détection des corps cellulaires dans des images de cellules biologiques du col.
  • Thumbnail Image
    Item
    Detection and Description the Lesions in Brain Images
    (University Cadi Ayyad (Marroc), 2005-11) Lassouaoui, Nadia; Hamami, Latifa; Nouali-Taboudjemat, Nadia; Hadjar, Samir; Saadi, Hocine
    In this paper, we present the various stages for lesion recognition in brain images. We firstly apply a filtering based on geodesic reconstruction operator for increasing the quality of image. After, we use an unsupervised segmentation genetic algorithm for detecting the abnormal zones with respect of theirs morphological characteristics because they define the nature of illness (cyst, tumour, malignant, benign, …). The obtained segmented images are analyzed for computing the characteristics of illness which are necessary for the recognition stage for deducing a decision about the type of illness. So, we give also the various algorithms used for computing the morphological characteristics of lesions (size, shape, position, texture, …). Since we obtain a decision about the malignity or benignity of the lesion and a quantitative information for helping the doctors to locate the sick part.
  • Thumbnail Image
    Item
    Morphological geodesic reconstruction in the extraction of the lesions in brain images
    (Université Aboubekr Belkaïd –Tlemcen, 2003-09) Lassouaoui, Nadia; Hamami, Latifa
    In this paper, we present algorithms that permit to extract the lesions in brain images. The goal is to extract the abnormal zones with respect of theirs morphological haracteristics as: size, shape and position. Then, we present to the doctor a simple image of abnormal zone that is easy to analysis and correct to diagnosis. For it, we used an algorithm of edge detection based on morphological gradient for delimit this areas; moreover, we have used algorithm based on complex operator knowing by morphological geodesic reconstruction, it permits to extract the areas where the lesions exist. These algorithms are based on mathematical morphology operators. The results obtained are satisfactory; the edge detection respects the characteristics and the morphology of the sick part of the brain, whereas with the algorithm of segmentation in homogeneous areas, we could make the extraction of the sick part of the brain, with the respect of all characteristics in a reasonable time allowing to think of real-time operation.
  • Thumbnail Image
    Item
    Genetic algorithms and multifractal segmentation of cervical cell images
    (IEEE, 2003-07) Lassouaoui, Nadia; Hamami, Latifa
    This paper deals with the segmentation problem of cervical cell images. Knowing that the malignity criteria appear on the morphology of the core and the cytoplasm of each cell, then, the goal of this segmentation is to separate each cell on its component, that permits to analyze separately their morphology (size and shape) in the recognition step, for deducing decision about the malignity of each cell. For that, we use a multifractal algorithm based on the computation of the singularity exponent on each point of the image. For increasing the quality of the segmentation, we propose to add an optimization step based on genetic algorithms. The proposed processing has been tested on several images. Herein, we present some results obtained by two cervical cell images.
  • Thumbnail Image
    Item
    Extraction des lésions dans des images de scanner cérébral pour système de télédiagnostic
    (Springer-Verlag, 2004) Lassouaoui, Nadia; Hamami, Latifa; Nouali-Taboudjemat, Nadia; Aït Abdelkader, Belaïd
    Le cancer est l’une des maladies les plus répandues dans le monde. Des chercheurs ont pensé à réaliser des systèmes qui seront des outils d’aide au diagnostic et à la décision pour les médecins. La mise sur réseau de tels systèmes permet d’avoir une application de télédiagnostic, le but est d’apporter «une seconde opinion» par un spécialiste distant pour confirmer ou infirmer le diagnostic établi par le praticien local, ou bien aider ce dernier à arriver à un diagnostic correct. Afin de concevoir un tel système, plusieurs aspects sont à prendre en charge. L’un des aspects les plus importants sont les problèmes liés à la taille des images médicales par rapport au débit de transmission. Pour cela, dans le cas du cancer du cerveau, nous proposons de concevoir un module pour l’extraction des lésions, son rôle est d’extraire la lésion tout en respectant sa taille, sa forme et sa position. Ainsi, les images à transmettre sont à deux niveaux de gris, noir et blanc, donc la taille diminue. Un second objectif de ce module est de simplifier l’image pour le médecin tout en conservant toutes les caractéristiques morphologiques de la lésion. Pour cela, nous pouvons procéder de deux manières, soit extraire les limites des lésions, soit extraire toute la zone correspondant à la surface des lésions. Nous utilisons des opérateurs basés sur la théorie de le morphologie mathématique, des résultats prometteurs ont été obtenus, ce qui permettra au médecin d’entamer sûrement l’étape de diagnostic en local ou à distance. Dans ce papier nous présentons principalement notre système de télédiagnostic ainsi les différents algorithmes pour la conception de ce module de segmentation.
  • Thumbnail Image
    Item
    Increase of embedding capacity of the H.264/AVC data hiding based on the intra-prediction modes
    (CERIST, 2011-09) Bouchama, Samira; Hamami, Latifa; Aliane, Hassina
    Data hiding methods applied to the newest video codec H.264/AVC are exploiting several modules of this codec such as the discrete cosine transform (DCT) coefficients and the intra prediction modes. The objective is to realize a good compromise between the embedding capacity, the increase in bitrate and the video quality, to satisfy several applications such as authentication or covert communication. In this paper we present a new approach to exploit the intra prediction modes for data hiding of the 4x4 luminance blocks. The objective is to ensure a good data embedding capacity and to preserve the encoding and the decoding times to satisfy reel time applications. The proposed method is based on dividing the intra prediction modes into four groups. Each group in composed of modes that have close prediction directions. Embedding the secret data is based on applying modification between modes of the same group in order to maintain visual quality and limit the number of additional calculation procedures. The increase of embedding capacity relies on the group composed on four modes since it allows the embedding of two bits per mode instead of one.
  • Thumbnail Image
    Item
    A comparative study between compressed video watermarking methods based on DCT coefficients and intra prediction
    (CERIST, 2011-09) Bouchama, Samira; Hamami, Latifa; Aliane, Hassina
    Several watermarking methods have been applied to the newest video codec H.264/AVC to satisfy different applications such as authentication, tamper proof and copyright protection. Our objective through this paper is to present a comparative study between watermarking methods based on the quantized (Q) DCT coefficients and those based on the intra prediction of the 4x4 luma blocks, in terms of embedding capacity, video quality and bitrate. The use of intra prediction modes is motivating because it is possible to embed a relatively high embedding capacity while preserving the video quality; however it seems difficult to maintain the bitrate. In this paper we show that the Intra prediction based method outperforms the QDCT based method using the same codec configuration.
  • Thumbnail Image
    Item
    Watermarking of compressed video based on DCT coefficients and watermark preprocessing
    (CERIST, 2010-12) Bouchama, Samira; Hamami, Latifa; Aliane, Hassina
    Considering the importance of watermarking of compressed video, several watermarking methods have been proposed for authentication, copyrights protection or simply for a secure data carrying through the Internet. Applied to the H.264/AVC video standard, in most of cases, these methods are based on the use of the quantized DCT coefficients often experimentally or randomly selected. In this paper, we introduce a watermarking method based on the DCT coefficients using two steps: the first one consists in a watermark pre-processing based on similarity measurement which can allow to adapt the best the watermark to the carrying coefficients of low frequencies. A second step takes advantage from the coefficients of high frequencies in order to maintain the video quality and reduce the bitrate. Results show that it is possible to achieve a very good compromise between video quality, embedding capacity and bitrate.
  • Thumbnail Image
    Item
    Watermarking techniques applied to H264/AVC video standard
    (CERIST, 2010-02) Bouchama, Samira; Hamami, Latifa; Aliane, Hassina
    Video watermarking describes the process of embedding information in video to satisfy applications such as the protection of intellectual property and the control of video authentication. In this field, researchers orient their investigations towards the new video standard H264/AVC which is increasingly used because of the coding efficiency it provides comparing to the previous standards. The different modules of this standard are exploited to embed watermark while responding to the application demands in terms of fragility or robustness to certain attacks and in terms of maintaining video quality and video bit rate. The aim of this paper is to give a global vision on the H264/AVC and to present some robust and fragile watermarking techniques applied to this video standard.