Summary Fraud keeps increasing in our society and security applications become crucial and needed in our daily life. Biometric technology attempts to stop fraud and falsification in different opportunities such as bank services, access to controlled areas or crossing frontiers, by recognizing the identity of a person using his physiological (fingerprint, iris, face) or behavioral modalities (gait, signature). In this article, we focus on an emerging biometric modality called the finger knuckle print (FKP). In fact, this modality has several advantages such as the easy distinction between different persons, stability over time and user acceptance. So, an FKP identification approach is proposed using scale invariant feature transform descriptors based sparse representation method. The classification step, between training and testing FKP samples, is made using the support vector machines method. Experiments applied on two public FKP databases: The Hong Kong Polytechnic University (PolyU) Contactless Finger Knuckle Images Database and the Indian Institute of Technology Delhi (IITD) Finger Knuckle Database, containing respectively 2500 and 790 images, demonstrate high correct identification rates by reaching 98.58% and 99.15% for these two databases.

In this paper, we propose a new Conditional Region Growing (CRG) approach with the ability of finding the accurate MC boundaries starting from selected seed points. The starting seed points are determined based on regional maxima detection and superpixel analysis. The region growing step is controlled by a set of criteria derived from prior knowledge to characterize MCs. The key feature is to highlight below each MC to estimate the appropriate criteria and not to use the same parameters for all of them. Defined criteria can be divided into two categories. The first one concerns the neighbourhood searching size. The second one deals with the gradient information and shape evolution within the growing process. Experimental results show the benefits of used criteria in terms of improving the MC delineation qualities.

In this paper, an unsupervised registration approach based on possibility theory, called "Unsupervised Possibilistic registration", is proposed to encounter this problem. It consists on adding an unsupervised projection step that allows matching possibility maps, obtained from the two images instead of the grey-level images (knowing that the thematic classes and their number have no effect on the registration). The experiments and the comparative study using MRI images have shown promising results. It is shown that the proposed unsupervised registration approach overcomes major problems of existing methods and allows temporal complexity optimization.

Image registration requires a step of detection and matching of primitives. This phase is important to obtain reliable registration. In this paper, we mainly focus on geometric registration methods which are based on the extraction and matching of distinctive feature points in images. Several methods such as SIFT, SURF, BRIEF, BRISK, ORB, FREAK and FRIF, are already proposed. In this paper, we present a comparative study of feature detector and descripts methods for registration which can be classified according to the type of descriptor and can be local classical or binary. We have presented, through this study, the difference between geometric methods of descriptor leveling as well as points of interest detector used and which have an influence on the resetting registration result. We can see that each method has weak points as well as strong points. The major difference is the level of invariance to the type of processing and the temporal complexity.

Remotely sensed images represent an important source of information for monitoring land changes that may occur. There is, therefore, a need to analyze and interpret such information in order to extract useful semantic change interpretations. However, extracting such semantics from satellite images is a complex task that requires prior and contextual knowledge. In this paper, we focus on the issue of semantic scene interpretation for change interpretation. Consequently, a strategy for semantic remote-sensing imagery scene interpretation is proposed. This strategy is based on a representative framework that is structured around several levels of interpretation: the pixel level, the visual primitive level, the object level, the scene level, and the change interpretation level. Each level integrates a logical mechanism to extract useful knowledge for interpretation. The proposed model has been evaluated using two Landsat scene images acquired in 2000 [Landsat Enhanced Thematic Mapper plus (ETM+)] and 2017 (Landsat 8) in order to check its relevance for semantic scene and change interpretation. Precision, recall, and F-measure metrics were used in order to show the capacity of the proposed methodology for semantic classification. A visual evaluation was also performed to evaluate the performance of the presented interpretation strategy, and the query results for each level show a promising capability for semantic object classification, spatial and temporal relations' extraction, and change interpretation.

In mammograms, the breast skin line often appears ambiguous and poorly defined. This is mainly due to the breast organ compression during the image acquisition process along with the inherent low density of the tissue in that area. The accurate delimitation of the breast region becomes a challenging task to conventional segmentation techniques. In this study, the authors propose a new segmentation approach allowing to overcome this challenge. This approach is based on the application of two complementary segmentation techniques exploring each, respectively, the grey‐scale intensities and the local‐homogeneity domains. The knowledge resulting from each segmentation technique is considered as a knowledge source and is modelled using the belief functions formalism. The two considered knowledge sources are then fused using an iterative process. The obtained results show the efficiency of the proposed evidential approach especially in terms of ambiguity removal and decision quality improvement for accurate breast border delimitation (which is often under‐segmented and assimilated to the background by most of the existing segmentation techniques).

Finding the appropriate number of clusters in the absence of prior information is a hard and sensitive problem in clustering and data analysis. In this paper, we present a new cluster validity index (CVI) called H F able to find the optimal number of clusters present in a given data. The HF index is based on the membership partition. It can be seen as the generalisation of the Wu-and-Li (WL) and Tang (T) indices. Its particularity is the integration of a generalised ad-hoc punishing term, on the one hand, and the involving of median between centroids multiplied by the average of data per cluster for computing the separation, on the other hand. These contributions allow avoiding the monotony from which suffer the majority of CV I s and obtaining a precise evaluation. The optimal number of clusters Copcorresponds to the minimum of the HF index. In order to ensure the effective choice of the optimal number of clusters, we propose an algorithm based on the HF and WL indices. The performance of the proposed index and algorithm are demonstrated through different experimentations on images clustering using the algorithm Fuzzy-C-Means (FCM). The HF index's ability to appropriately determine the number of clusters is compared with those of WL, T and the Xi-Beni (XB) indices with different initialisations.

Segmentation of breast masses in mammograms is a challenging issue due to the nature of mammography and the characteristics of masses. In fact, mammographic images are poor in contrast and breast masses have various shapes and densities with fuzzy and ill-defined borders. In this paper, we propose a method based on a modified Chan-Vese active contour model for mass segmentation in mammograms. We conduct the experiment on mass Regions of Interest (ROI) extracted from the MIAS database. The proposed method consists of mainly three stages: Firstly, the ROI is preprocessed to enhance the contrast. Next, two fuzzy membership maps are generated from the preprocessed ROI based on fuzzy C-Means algorithm. These fuzzy membership maps are finally used to modify the energy of the Chan-Vese model and to perform the final segmentation. Experimental results indicate that the proposed method yields good mass segmentation results.

Shape and margin features are very important for differentiating between benign and malignant masses in mammographic images. In fact, benign masses are usually round and oval and have smooth contours. However, malignant tumors have generally irregular shape and appear lobulated or speculated in margins. This knowledge suffers from imprecision and ambiguity. Therefore, this paper deals with the problem of mass classification by using shape and margin features while taking into account the uncertainty linked to the degree of truth of the available information and the imprecision related to its content. Thus, in this work, we proposed a novel mass classification approach which provides a possibility based representation of the extracted shape features and builds a possibility knowledge basis in order to evaluate the possibility degree of malignancy and benignity for each mass. For experimentation, the MIAS database was used and the classification results show the great performance of our approach in spite of using simple features.

Information fusion consists in combining information in order to maximize the relevant information and reduce the redundancy. It is widely used in many fields, especially in image processing, for analyzing situations. Since the first use of the information fusion concept, many approaches have been introduced to define a processing model to merge information. Three basic approaches are used in information fusion: the JDL Model which is the first one used, the Intelligence Cycle Model and the DFD (Data - Features - Decision) Model. According to the field of application and the type of the information manipulated, the processing model is different. In image processing, various techniques and methods are used to perform image fusion. Many techniques are most used in research studies: PCA (Principal Component Analyses), Wavelet transform,... In this paper we present a general overview of the basic models and techniques used in image fusion.

Medical association rules induction is used to discover useful correlations between pertinent concepts from large medical databases. Nevertheless, ARs algorithms produce huge amount of delivered rules and do not guarantee the usefulness and interestingness of the generated knowledge. To overcome this drawback, we propose an ontology based interestingness measure for ARs ranking. According to domain expert, the goal of the use of ARs is to discover implicit relationships between items of different categories such as ‘clinical features and disorders’,‘clinical features and radiological observations’, etc. That's to say, the itemsets which are composed of “similar” items are uninteresting. Therefore, the dissimilarity between the rule's items can be used to judge the interestingness of association rules; the more different are the items, the more interesting the rule is. In this paper, we design a distinct approach for ranking semantically interesting association rules involving the use of an ontology knowledge mining approach. The basic idea is to organize the ontology's concepts into a hierarchical structure of conceptual clusters of targeted subjects, where each cluster encapsulates “similar” concepts suggesting a specific category of the domain knowledge. The interestingness of association rules is, then, defined as the dissimilarity between corresponding clusters. That's to say, the further are the clusters of the items in the AR, the more interesting the rule is. We apply the method in our domain of interest – mammographic domain-using an existing mammographic ontology called Mammo*, with the goal of deriving interesting rules from past experiences, to discover implicit relationships between concepts modeling the domain.

Palmprint identification is a popular biometric technology used for personal characterization. Traditional palmprint recognition methods are mostly based on acquisition devices with contact, and this, may affect their user friendliness. In this paper, a toucheless palmprint identification method based on Scale Invariant Feature Transform (SIFT) descriptors and sparse representation method is proposed, in order to extract palmprint features of left and right palms. The fusion scheme is performed at rank level using Support Vector Machines (SVM) classifier and probability distribution to generate the final identity of a person. Experiments evaluated on CASIA palmprint database and a proposed toucheless REST (REgim Sfax Tunisia) hand database, report promising performances which are competitive to other existing palmprint identification methods.

This paper proposes an approach referred as: iterative refinement of possibility distributions by learning (IRPDL) for pixel-based image classification. The IRPDL approach is based on the use of possibilistic reasoning concepts exploiting expert knowledge sources as well as ground possibilistic seeds learning. The set of seeds is constructed by incrementally updating and refining the possibility distributions. Synthetic images as well as real images from the RIDER Breast MRI database are being used to evaluate the IRPDL performance. Its performance is compared with three relevant reference methods: region growing, semi-supervised fuzzy pattern matching, and Markov random fields. The IRDPL performance (in terms of recognition rate, 87.3%) is close to the Markovian method (88.8%) that is considered to be the reference in pixel-based image classification. IRPDL outperforms the other two methods, respectively, at the recognition rates of 83.9% and 84.7%. In addition, the proposed IRPDL requires fewer parameters for the mathematical representation and presents a reduced computational complexity.

Human hand is a physiological biometric trait employed in order to characterize and identify an individual. It is considered as one of the most popular biometric technologies especially in forensic applications, due to its high users acceptance compared to other biometric technologies. In this paper, we propose a new hand biometric system for personal identity verification, combining two local features at matching score level. Indeed, these features are represented by SIFT (Scale Invariant Feature Transform) descriptors and geometrical measurements of the hand. Our experiments are evaluated using Bogazici University Hand database containing 1926 left hand images acquired from 642 subjects and showed promising results which are comparable with other approaches.

Human hand is a physiological biometric trait employed in order to characterize and identify a person. It is considered as one of the most popular biometric technologies especially in forensic applications, due to its high users acceptance compared to other biometric technologies. In this paper, we propose a hand biometric system for personal identity verification, fusing multiple features of the hand at matching score level. In fact, shape and texture are extracted from hand, fingers and palmprint in order to represent the hand image of each person. In the feature extraction strategy, the scale Invariant Feature Transform (SIFT) is extracted from the hand image to describe local invariant features of the hands contour and also extracted from fingers images. In the other hand, Gabor filters are extracted from palmprint images to describe the texture of the hand. The main advantage of these two descriptors (SIFT and Gabor) is that features extracted are invariant to rotation, translation, scale and lighting changes. Personal verification was performed by fusing similarity scores achieved from the hand shape, the fingers and the palmprint. Experimental results show good performances (EER=1.95%) in hand verification using a database containing 230 different subjects.

This paper presents a comprehensive experimental study on face recognition to prove that holistic approaches are more robust than geometric and local approaches in order to address the problem of which method holistic or geometric can assist to face recognition. This work is done based on the motivation to integrate soft biometric traits into face recognition systems using same computing. A bag of features extraction and classification combined with each other to find the most appropriate technique that can enhance face recognition task. The experimental study shows that the texture information is discriminant in facial images representation, Gabor filter is more useful than Local Binary Pattern, a space dimensionality reduction using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) is very interesting to increase recognition rates. The fusion between Gabor, PCA or LDA and Multi class Support Vector Machines (SVM) ranks top the list of all other combinations.These techniques will be performed later to integrate soft biometrics.

Ontologies are considered as one of the most powerful tools for knowledge representation and reasoning. Thus, they are considered as a fundamental support for image annotation, indexing and retrieval. In order to build a remote sensing satellite image ontology that models the geographic objects that we find in a scene, their characteristics as well as their relationships, we propose to reuse existing geographic ontologies to enrich an ontological core. Reusing high quality resources (called source ontologies) helps ensuring a good quality for the extracted knowledge, and alleviating the conceptualization stage, i.e. avoiding building a new ontology from scratch. Ontology alignment is an important phase within the enrichment process. It is a process that allows discovering mappings between core and source ontologies, where each mapping is a couple of entities brought from each ontology and linked together either by an equivalence or a subsumption relationship. Such relationships are based on various similarity measures. In this paper, we first present a brief literature review of existing theoretical frameworks for similarity measures, then we describe a new alignment approach based on a semi-automatic mapping selection process that needs little human intervention. First experiments show the benefit from using the proposed approach.

In this paper, an approach for pixel unmixing based on possibilistic similarity is proposed. This approach uses possibility distributions to express both the expert’s semantic knowledge (a priori knowledge) and the contextual information. Dubois-Prade’s probability-possibility transformation is used to construct these possibility distributions starting from statistical information (learning areas delimitated by an expert for each thematic class in the analyzed scene) which serve, first, for the estimation of the probability density functions using the kernel density estimation. The pixel unmixing is then performed based on the possibilistic similarity between a local possibility distribution estimated around the considered pixel and the obtained possibility distributions representing the predefined thematic classes. The obtained similarity values are used in order to obtain the abundances of different classes in the considered pixel. Accuracy analysis of pixels unmixing demonstrates that the proposed approach represents an efficient estimator of their abundances of the predefined thematic classes and, in turn, higher classification accuracy is achieved. Synthetic images are used in order to evaluate the performances of the proposed approach.

Ontologies nowadays are known to be potential tool for enabling interoperability across heterogeneous systems and semantic web applications. For this, Ontology mapping is required for combining distributed and heterogeneous ontologies modeling the same domain in order to establish correspondences among the related entities of the ontologies sources. Many works dealing with ontology mapping have been proposed. The addressed contribution in this paper is the conflict resolution among the different similarity measures using the Dempster Shafer theory into the mapping. The proposed method consists on combining the similarities which were originally created by syntactic and structural similarity algorithms. The similarity techniques represent the elementary masses to reason on and the management of derived similarity measures will be based on fusion theory to model uncertainty and treat ambiguity to resolve conflicts between the different elementary sources. The generated data will be interpreted in terms of logic correspondence between the entities of interest.

Hyperspectral sensors (HS) are next-generation optical sensors that have excellent spectroscopic performance with hundreds of spectral bands. Multispectral sensors (MS) are conventional optical sensors that have a few tens of spectral bands with high spatial resolution. This work aims to combine, the spectral information of the hyperspectral image with the spatial and spectral information of the multispectral image for automatic classification while considering spatial relationships between sources in low-spatial resolution data. The considered approach is validated first by using synthetic images from the USGS spectral library, but also using Hyperion sensor as hyperspectral image. And SPOT sensor as multispectral image, representing the region of Gabes Matmata in southern Tunisia.

Actually, we still have not a well established satellite image ontology that would be very useful to assist us to study major facts affecting earth, detect and monitor natural phenomena. Nevertheless, there are several domain-specific geographic ontologies that can be used as semantic resources to build such an ontology. Thus, we can start from a core satellite image ontology such as the one of Durand and enrich it using these geographic ontologies. Ontology matching is one of the principal activities in the ontology enrichment process and highly depends on the similarity measures that are considered as well as the way they are combined together in order to decide whether two concepts coming from different ontologies are alienable. In the literature, research on similarity mainly focuses on issues related to how to compute and refine similarity measures. However, few research addresses studying their dependencies and contributions in the evaluation of the overall similarity between objects to be compared. In this paper and in order to align an initial remote sensing satellite image ontology with a set of geographic ontologies, we give insights on the main similarity models as well as their associated measures. We then propose a method in order to select a reduced set of the most important similarity measures to use for the alignment. Afterwards, we present a method that can produce a ranking model that allows sorting mappings between concepts coming from two different ontologies, in a decreasing order of a global similarity score. First experimentations show that the proposed approach is promising.

The interpretation of hyperspectral imagery is an essential task for classification, changes detection and monitoring of natural phenomena. One challenge of the processing hyperspectral images, with better spectral and temporal resolution is the huge amount of data volume and the interpretation in high dimensionality data. Various techniques have been developed in the literature for dimensionality reduction, generally divided into two main categories: projection techniques and bands selection techniques. In this work, we present a new approach for interpretation in hyperspectral imagery based on hybrid dimensionality reduction methods. The presented approach combines a projection method with a bands selection method. Indeed, the objective of the research is to obtain an efficient hyperspectral image interpretation. The performances of the proposed approach were evaluated using AVIRIS hyperspectral image.

Hand shape biometry is among the most popular biometrics employed to characterize a person in forensic applications, due to its simplicity of use and acceptance of individuals. However, this modality presents weaknesses which may make system inaccurate. In fact, people from the same family or twins may have related hand features. Therefore, the performance of the hand verification process depends highly on the hand descriptors. In this paper, we propose a new approach for personal verification combining hand shape and palmprint features extracted using the Scale Invariant Feature Transform (SIFT). This transform was improved its high distinction and efficiency in many applications especially in object recognition and video tracking. Our experiments on IITD hand database demonstrate promising results by fusing at matching level score the hand shape and palmprint modalities. These results are comparable with similar bimodal identification methods.

The instrumentation and physiological patient factors bound to the patient in-vivo complicate the treatment of the images during a medical examination. Thus, they can contribute to the generation of artifacts in the resulting images. The artifacts degrade the quality of the images and can lead, in certain cases, to a bad diagnosis. For this reason, the appeal to the use of the simulation techniques allows to evaluate and improve the devices of acquisition and image processing. The models (called phantoms) are important tools to simulate human anatomy and physiology and to allow the evaluation of acquisition methods and image analysis. Thereby, the simulation offers a way of great importance to evaluate and improve medical techniques of acquisition devices, treatment and the reconstruction of images in-vitro.

Face recognition is a very popular biometric solution in the literature. Several solutions are presented to meet the needs of individual's verification or identification. There are three types of face recognition approaches: local, global and hybrid. In this paper, we proposed a local approach for face recognition based on combined features selection methods like Genetic algorithm, Gramdt Shmidt algorithm, mRmR features selection algorithm and naïve Bayesian classifier. Our proposed approach will be compared with some face recognition systems based on global features. A comparative study is given in this paper based on Recognition rates and Execution times. Our Face recognition system, which is based on naïve Bayesian classifier and tested on ORL face database, has showed 78.75% recognition rate and interesting execution times compared to global approaches.

Multitemporal hyperspectral images are gaining an ever-increasing importance revealed by the ambition of the remote sensing community to develop new generation of sensors. Therefore, multitemporal images classification and change detection issues are greatly relevant in several research topics. In this paper, we propose a novel approach for modeling the temporal variation of the reflectance response as a function of time period and wavelength; summarizing the spectral signature of hyperspectral pixels as a 3-D mesh. This approach is adopted for hyperspectral time series analysis leading to the main following contribution: an advanced form of the temporal spectral signature defining the reflectance at each pixel as a congregation of the spatial/spectral/temporal dimensions. Afterward, by formulating the temporal data set in an adequate multidimensional feature space of contextual data, an innovative processing scheme exploiting the theoretical backgrounds of 3-D surface reconstruction and matching is adopted for data interpretation. Finally, an improved method for multitemporal endmember extraction and spectral unmixing based on multilinear algebra methods is introduced. A case study, in a region located in southern Tunisia, is conducted on a multitemporal subset of Hyperion images. Up to 89.86% of sampling sites have been correctly predicted by the proposed approach, outperforming conventional classifiers. The good performances obtained, on simulated multitemporal images and over various real experimental scenarios, illustrate the effectiveness and the generalization capacities of the proposed approach.

This paper develops a noise-robust processing method which can be used to enhance the classification of remotely sensed hyperspectral images. The method first illustrates the benefit of boosting the classical classifiers by exploiting the capability of belief functions. The evidential approach is adopted to produce a map which is approximately insensitive to the noise accompanying the original hyperspectral data-set. Then, a new Evidential Kernel Fisher Discriminant is proposed by using a modified version of the Expectation-Maximization (EM) algorithm. An experimental comparison of the proposed approach with other classical methods is conducted using both synthetic and real hyperspectral data collected by the HYPERION sensor. Our experiments reveal that both classification and unmixing process can benefit from the proposed aggregated approach, remarkably, when the noise level present in the original hyperspectral series is propositionally high.

Within the framework of the unmixing of hyperspectral images, the pixel mixture is a difficult problem to solve. This difficulty comes from several outliers which seriously affect the reliability of spectral unmixing results. The illumination change effect, where the image does not reflect the true appearance of the scene, in many cases due to shadow facts, is considered to be one of the most important outliers. The present work proposes a new approach called Spectral Angle Measure-based Spectral Unmixing which uses the spectral angle constraint for abundance quantification. The major benefit of this approach is its ability to take advantage of the geometric properties of the Spectral Angle Measure technique to estimate abundance quantification independently of the amplitude (magnitude) of the Endmembers spectral signatures, using only spectral angle measures. As a consequence, a significant reduction in spectral unmixed error corresponding to the spectral similarity within-class confusion is obtained. A second benefit concerns physical constraints which are respected. The experiment was conducted using simulated and real images to validate our approach and to compare it with a well known statistical one.

An approach that aims to reveal and to explain the pattern of information potentially present in a dataset consisting of n objects by ordering them using the possibility-based Robinsonian similarity matrix is proposed. The similarity is estimated between objects containing imperfect and heterogeneously-assigned data. A graph-based model is proposed to visualize these patterns. This method is applied to a medical database. Without any a priori medical knowledge and without knowing the key attributes of the pathologies, the objects have been ranked according to their corresponding classes.

Venous thrombosis (VT) volume assessment, by verifying its risk of progression when anticoagulant or thrombolytic therapies are prescribed, is often necessary to screen life-threatening complications. Commonly, VT volume estimation is done by manual delineation of few contours in the ultrasound (US) image sequence, assuming that the VT has a regular shape and constant radius, thus producing significant errors. This paper presents and evaluates a comprehensive functional approach based on the combination of robust anisotropic diffusion and deformable contours to calculate VT volume in a more accurate manner when applied to freehand 2-D US image sequences. Robust anisotropic filtering reduces image speckle noise without generating incoherent edge discontinuities. Prior knowledge of the VT shape allows initializing the deformable contour, which is then guided by the noise-filtering outcome. Segmented contours are subsequently used to calculate VT volume. The proposed approach is integrated into a system prototype compatible with existing clinical US machines that additionally tracks the acquired images 3-D position and provides a dense Delaunay triangulation required for volume calculation. A predefined robust anisotropic diffusion and deformable contour parameter set enhances the system usability. Experimental results pertinence is assessed by comparison with manual and tetrahedron-based volume computations, using images acquired by two medical experts of eight plastic phantoms and eight in vitro VTs, whose independently measured volume is the reference ground truth. Results show a mean difference between 16 and 35 mm(3) for volumes that vary from 655 to 2826 mm(3). Two in vivo VT volumes are also calculated to illustrate how this approach could be applied in clinical conditions when the real value is unknown. Comparative results for the two experts differ from 1.2% to 10.08% of the smallest estimated value when the image acquisition cadences are similar.

Land cover interpretation using multisensor remote sensing images is an important task that allows the extraction of information that is useful for several applications. However, satellite images are usually characterized by several types of imperfection, such as uncertainty, imprecision, and ignorance. Using additional sensors can help improve the image interpretation process and decrease the associated imperfections. Fusion methods such as the probability, possibility, and evidence methods can be used to combine information coming from these sensors. An extensive literature has accumulated during the last decade to resolve the issue of choosing the best fusion method, particularly for satellite images. In this paper, we present a semiautomatic approach based on case-based reasoning (CBR) and rule-based reasoning, allowing intelligent fusion method retrieval. This approach takes into account the advantage of data stored in the case base, allowing a more efficient processing and a decrease in image imperfections. The proposed approach incorporates three modules. The first is a learning module based on evaluating three fusion methods (probability, possibility, and evidence) applied to the given satellite images. The second looks for the best fusion method using CBR. The last is devoted to the fusion of multisensor images using the method retrieved by CBR. We validate our approach on a set of optical images coming from the Satellite Pour l'Observation de la Terre 4 and radar images coming from European Remote Sensing Satellite 2 (ERS-2) representing a central Tunisian region.

In this work, we present a new fusion method that uses fuzzy set theory. This method is applied to the diagnostic system rule bases. It aims at combining all the rule bases into only one rule base and then taking into consideration the characteristics of this base. The fusion method is characterized by a hybrid fusion which combines rule fusion approach with knowledge fusion approach. Knowledge fusion relies on the distortion measure of various bases. This distortion measure is integrated into the rule fusion process in order to generate one rule base for improving the diagnostic system performance. It is defined as the confidence degrees associated to each rule base parameter. The confidence degrees are then integrated into prediction procedure of the new diagnostic system.

Monitoring changes in the vegetation cover during the intercrop season is of a special interest in intensive agricultural regions. The presence of bare soils leads to detrimental environmental effects such as soil erosion or water quality degradation. To identify and monitor winter land cover at a regional scale in the Brittany region in France, data from the Moderate Resolution Imaging Spectroradiometer (MODIS) low resolution time series were used. This study examines the Self-Organizing Map (SOM) for classifying winter land cover with MODIS time series in agricultural and fragmented landscapes. Field data and high resolution images have been used to generate two sets of pixels for training and validation. A comparison between the suggested method and NDVI thresholding is presented.

ONERA radar RAMSES was recently upgraded with low frequency band (P-band, 435 MHz). In P-band, frequencies penetrate through the ground and through forest canopy. Unfortunately, the formation of the subsurface radar images presents a number of new specific challenges that include algorithm validity, calibration methods, radio-frequency interference, and image focusing and analysis. This paper addresses the aspects of focusing images from an airborne low frequency SAR of buried targets in a lossy and dispersive soil. The hydrological model (Richards' equation) was used to model the multilayer case.

The purpose of this paper is to present an intelligent atlas of indexed endoscopic lesions that could be used in computer-assisted diagnosis as reference data. The development of such a system requires a mix of medical and engineering skills for analyzing and reproducing the cognitive processes that underlie the medical decision-making process. The analysis of both endoscopists experience and endoscopic terminologies developed by professional associations shows that diagnostic reasoning in digestive endoscopy uses a scene-object approach. The objects correspond to the endoscopic findings and the medical context of examination and the scene to the endoscopic diagnosis. According to expert assessment, the classes of endoscopic findings and diagnoses, their primitive characteristics (or indices), and their relationships have been listed. Each class describes an endoscopic finding or diagnosis in an intensive way. The retrieval method is based on a similarity metric that estimates the membership value of the case under investigation and the prototype of the class. A simulation test with randomized objects demonstrates a good classification of endoscopic findings. The correct class is the unique response in 68% of the tested objects, the first of multiple responses in 28%. Four descriptors are shown to be of major importance in the classification algorithm: anatomic location, shape, color, and relief. At the present time, the application database contains approximately 150 endoscopic images and is accessible via Internet. Experiments are in progress with endoscopists for the validation of the system and for the understanding of the similarity between images. The next step will integrate the system in a learning tool for junior endoscopists.

An overview is presented of different constraints in conventional medical decision-making for improving collaborative reasoning. When designing and implementing an effective assisted diagnoses system it is imperative to make a complete study of reasoning processes used by physicians every day. We are particularly interested in studying the process of conventional decision-making when, at the first stage, a physician faces a diagnosis decision and, later, when this decision is made by several physicians, that is, when collaborative medical reasoning is involved. The design of an architecture that supports the requirements of medical practices in this framework is presented.

A fuzzy-based multisensor data fusion classifier is developed and applied to land cover classification using ERS 1/JERS-1 SAR composites. This classifier aims at the integration of multisensor and contextual information in a single and a homogeneous framework. Initial fuzzy membership maps (FMMs) to different thematic classes are first calculated using classes and sensors a priori knowledge. These FMMs are then iteratively updated using spatial contextual information. A classification rule is associated to different iterations. This classifier has the following advantages: first, due to the use of fuzzy concepts, it has the flexibility of integrating multisensor/contextual and a priori information. Second, the classification results consist of thematic as well as confidence maps. The confidence map (a classification certainty map representing the degree of certainty in the thematic map) constitutes an important issue in order to evaluate the classification process complexity and the validity of the assumptions. The application of this classifier using ERS-1/JERS-1 SAR composites is shown to be promising.

In this paper, we propose a complete transmission system for still images which minimizes the distortion introduced by residual transmission errors. This system comprises a source encoder combining DCT (discrete cosine transform) and VQ (vector quantization). The compression rate is equal to 16.7 for an average PSNR (peak signal to noise ratio) of 29.2 dB. The data are then encoded by a BCH (63,57,3) block code and mapped on a 64-QAM constellation. The parameters of the code book and channel encoder have been optimized for 64-QAM. For channel decoding, we use maximum likelihood sequence decoding. The PSNR of the reconstructed image in the receiver is equal to 28.6 dB for a channel SNR of 11 dB. This represents a very small degradation of the PSNR (0.6 dB) in presence of a SER (symbol error rate) of 10% at the input of the receiver.

Remote-sensing image classification is one of the most important techniques in understanding the dynamics of the Earth's ecosystems. Various approaches have been proposed for performing this classification task. Obtained classification results are generally shown as a thematic (or class) map in which each pixel is assigned a class label. Due to sensor noise and algorithm limitations, obtained thematic maps are very noisy. The noise has a "salt-and-pepper" appearance in homogeneous regions and produces weakly defined interregion borders. In this paper, a new postprocessing approach aiming to produce thematic maps with sharp interregion boundaries and homogeneous regions is presented. This approach is conducted in two steps: (1) relevant features derived from the original multispectral image (edge maps) as well as from the thematic map, the Smoothed Thematic Map (STM), are determined and (2) a region-growing algorithm is applied over the thematic map. This algorithm grows until reaching an edge (from the edge maps) or a class change in the STM. The proposed approach fills the requirements of being independent of the used classification algorithm and not knowledge-based (in the sense that no a priori information concerning the contents of the considered image is needed). Tests have been conducted on a Landsat image covering mainly agricultural areas.

A new tendency in the design of modern signal processing methods is the creation of hybrid algorithms. This paper gives an overview of different signal processing algorithms situated halfway between Markovian and neural paradigms. A new systematic way to classify these algorithms is proposed. Four specific classes of models are described. The first one is made up of algorithms based upon either one of the two paradigms, but including some parts of the other one. The second class includes algorithms proposing a parallel or sequential cooperation of two independent Markovian and neural parts. The third class tends to show Markov models (MMs) as a special case of neural networks (NNs), or conversely NNs as a special case of MMs. These algorithms concentrate mainly on bringing together respective learning methods. The fourth class of algorithms are hybrids, neither purely Markovian nor neural. They can be seen as belonging to a more general class of models, presenting features from both paradigms. The first two classes essentially include models with structural modifications, while two later classes propose algorithmic modifications. For the sake of clarity, only main mathematical formulas are given. Specific applications are intentionally avoided to give a wider view of the subject. The references provide more details for interested readers.

The finite state vector quantization (FSVQ) image compression approach is studied. A new compression scheme is proposed which optimizes the performance of the so-called conditional histogram next-state function design. The optimization is performed by determining for every input block the state codebook size, that minimizes the expected value of the number of bits in the compressed data flow. This is done under the constraint to ensure the same reconstruction quality as that of the full-search vector quantizer. The derailment is avoided by transmitting side information to the decoder. The proposed scheme is tested on still medical endoscopic images. Since the system is always adapted to the probability distribution of block occurrences, it provides a lower bit rate than FSVQ that applies state codebooks of fixed size.

In addition to the source coding artifacts, the encoded bit streams representing codeword indexes of a vector quantized image are vulnerable to transmission or media impairments. Impulse block noise in the received images is the main artifact due to transmission errors. We use the fuzzy set theory to represent the vague concept of a block similarity with its spatial context. This approach is conducted in order to detect and to conceal the transmission errors. Error concealment by searching the best matching codeword is an attractive alternative to the commonly used interpolation approach. It reduces considerably the computational complexity at the receiver end. Simulation results show that the proposed method considerably improves the subjective quality of VQ images transmitted over noisy channels.

A new textured image model is proposed. This model is described by means of a neuro-Markovian hybrid approach using a Kohonen map and a hidden Markov model (HMM). Each state of the HMM describes one resolution level in the image. The change of the state corresponds to the change of image analysis resolution level. The HMM observation space is composed of clusters which are estimated using a Kohonen map. The second role of the Kohonen algorithm is to achieve a segmentation which is done in parallel with the one proceeded by a Viterbi algorithm. The results given by the both algorithms present some complementarity.

We apply a new neural network: HLVQ combining supervised and unsupervised learning to vector quantization. A supervised learning based on learning vector quantization 2 performs attention focusing over a background of a self-organizing feature map algorithm. It exhibits the salient features of both algorithms: the topology-preserving mapping characteristic is acquired through unsupervised learning while supervised learning keeps the overlap between classes to a minimum. Pattern labeling is carried out by a separate unsupervised network taking as input the discrete cosine transform of a pattern. First the labelling network is trained on the transform of sub-images. Each neuron of this network is considered as the prototype of one class. Once convergence is achieved, HLVQ is trained. Each sub-image is input to the network. The class of the input pattern is determined by the most activated neuron of the labelling network on presentation of the sub-image transform.

A solution for integrating two pattern recognition methods is proposed. The first method is a neural network method and the second method is a structural method. The authors propose sending structural information to the neural network to take advantage of both methods. The aim is to let the neural network analyze the global pattern and take local ambiguities into account.>

The performance of noncoherent reception in fast frequency hopped spread-spectrum (FFH-SS) communication systems operating through noisy, fading multipath channels is investigated. Systems operating with binary frequency-shift keying (BFSK) modulation and noncoherent demodulation are examined under the assumption of very slow fading. These analyses demonstrate the frequency hopping benefits in selective channels. Expressions are derived for the bit error rate in the context of selective Rayleigh and selective Rician fading channels, as a function of channel and system parameters.>

The authors present the performance analysis of an FFH-SSMA system with a binary frequency-shift keying modulation scheme and noncoherent demodulation, operating in a combined environment of Rayleigh selective fading, other users interference, and additive white Gaussian noise. Improvement due to the use of equal gain diversity (EGD) is studied in terms of bit-error rate (BER). Expressions of the BER are evaluated when a maximum-likelihood decision criterion is used to show the advantages of the use of frequency hopping selective Rayleigh fading channels. Results show the equivalence between frequency hopping and direct-sequence (DS) modulation in combating multipath fading. The performance, in terms of irreducible error probability, of the system under study and that of the DS-CPSK when using EGD are not significantly different.>

The noncoherent reception performance of a slow frequency-hopped binary frequency-shift-keying (SFH-BFSK) modulation scheme in an underwater acoustic channel is investigated. Expressions of the bit error rate (BER) are obtained in the context of Rayleigh selective and Rician selective fading channels as a function of channel and system parameters. Improvements due to the use of error correcting codes (convolutional coding with Viterbi decoding algorithm) are investigated. Because of the difficulty in exact evaluation of the BER, upper bounds are generally used. In this case, the Monte Carlo simulation approach was used to obtain numerical results for high BERs. The Union-Bhattacharyya upper bound is used for low BERs.>