Cooperative Intelligent Transport Systems (C-ITS) enhance traffic efficiency and road safety by enabling effective Cooperative Traffic Management (CTM). Multi-Agent Systems (MAS), as a distributed and adaptive technology, offer promising solutions for optimizing CTM through autonomous and coordinated decision-making. Although MAS have been widely explored in transportation research, there remains a notable lack of systematic studies focusing specifically on their application to CTM. This paper presents a Systematic Literature Review (SLR) to identify and analyze existing research that applies MAS to CTM within the context of C-ITS. A curated set of publications was selected based on defined inclusion and exclusion criteria. The analysis reveals a range of MAS-based approaches addressing CTM challenges. Based on the reviewed multi-agent-based CTM approaches, we propose a new taxonomy, structured according to the application domain, adopted physical components, interaction methods (cooperation, collaboration, negotiation, and coordination), agent types, and experimental settings. This taxonomy provides a structured overview of how MAS contribute to CTM in C-ITS. The review also outlines key challenges and research opportunities, aiming to support future advancements in traffic management strategies. The results highlight the potential of MAS to improve traffic flow, system robustness, and safety in intelligent transport environments.

The Cooperative Intelligent Transport System (C-ITS) aims to address traffic efficiency, road safety, and environmental sustain-ability by facilitating communication among autonomous entities with complex behaviors. Traffic congestion is a significant issue in modern urban areas, influenced by factors like accidents, road works, weather and peak hours, leading to wasted time, fuel, and increased pollution. To address these challenges, multi-agent systems have proven effective in managing dynamic traffic in C-ITS environments. In this paper, we propose a novel Reinforcement Learning Agent (RLA) method for decision-making in C-ITS systems to optimize traffic flow and control. Our method utilizes the Q-learning algorithm, enabling effective problem-solving. We conducted experiments to demonstrate the versatility and effectiveness of our approach in complex C-ITS environments. Our method surpasses traditional metrics like mean travel time and mean speed, validated through comparisons with Actor-Critic methods and against the Original Traffic Trace (OTT). This research contributes to advancing decision-making capabilities within C-ITS systems by leveraging RLA for traffic optimization and efficiency.

Resource allocation, scheduling, and provisioning are indeed critical and complex issues in cloud computing environments, as they directly impact both the user experience and the profitability of cloud service providers. Also, the excessive use of resources and the fact that the required resources may exceed those available have raised additional challenges. The effective and optimal allocation of resources in this dynamic cloud environment poses a significant challenge due to the substantial increase in cloud utilization. Then, an energy-efficient task scheduling algorithm is required to improve the efficiency of the resource allocation process. This paper proposed an efficient and autonomous dynamic resource allocation in cloud computing with optimized task scheduling. We aim to minimize the cost of virtual machines and the makespan. Furthermore, its impact on the best response time and energy consumption has been studied. The simulation shows that our method gave better results than the former ones.

Rich heterogeneous data provided by social networks can be very big, which imposes considerable challenges for object extraction and image classification. Therefore, the objective of this work is to propose an unsupervised object cosegmentation method that could be notably efficient to improve image classification performance. The main goal of cosegmentation is to extract the salient common objects within each image. To this end, we propose to minimize an energy function based on the Markov Random Field using the saliency detection, while considering linear dependence of generated foreground histograms of the input image collection. In fact, the saliency detection is processed in two steps. In each image, we detect salient objects, by considering appearance similarity and spatial distributions of image pixels. Then, fuzzy quantification is used to correct the belonging of pixels to the foreground objects. Finally, an iterative optimization permits to enhance the final segmentation results. The proposed method has been validated as a preprocessing step for image classification. Indeed, to enhance cosegmentation-based classification performance, we have applied a semi-supervised object classification based on ensemble projection. Qualitative and quantitative evaluations of the proposed cosegmentation and classification techniques on the iCoseg, CDS and Oxford Flowers 17 datasets demonstrate the effectiveness of the proposed framework.

Digital watermarking challenges are multiple. The most important are copyright protection, integrity control, and indexing. The latter has gained significant attention from the research community due to the increasing production of multimedia data. Existing anaglyph 3D video watermarking methods are developed mainly for copyright protection applications but they have not targeted indexing applications that facilitate the retrieving of anaglyph 3D videos in databases. Hence, it is necessary to develop a robust watermarking technique dedicated to indexing in order to both protect and facilitate retrieving anaglyph 3D videos. This paper presents a novel watermarking-based retrieval system for anaglyph 3D videos. The system utilizes a mosaic image generated from the original video as the signature, providing a comprehensive representation of the video’s content. To handle the large size of the mosaic image, it is divided into a set of vectors. The obtained vectors are embedded into different selected frames using a dynamic insertion key to ensure visual quality and robustness against collusion attacks. During retrieval, the extracted signatures from the database are compared with the query video’s mosaic image using a similarity measure. Experimental results demonstrate high visual quality, robustness, and effectiveness of the proposed system.

In recent years, the advent of the Internet and the rapid growth of digital media applications have made video a primary medium for information transmission. However, this progress has also brought about new challenges, including concerns related to unauthorized copying, digital plagiarism, and the distribution and utilization of copyrighted digital content. In order to address these issues, watermarking has emerged as a solution. It involves embedding a watermark into a digital cover and subsequently extracting it to resolve ownership disputes and copyright infringements related to media content. Numerous conventional video watermarking techniques have been introduced, demonstrating their effectiveness in achieving both invisibility and robustness against various types of attacks. Recently, the application of deep learning principles in embedding signatures into video content has gained significant attention. This approach offers considerable advantages in the field of watermarking due to its accuracy, superior outcomes, and exceptional learning capabilities. This paper provides an overview of recent advancements in deep learning-based video watermarking. It categorizes the proposed approaches according to the employed network architecture, offering a comprehensive summary of the field’s latest developments. The study concludes by examining potential research avenues in the domain of deep learning-based video watermarking.

International audience

Convolutional Neural Networks (CNNs) have been highly successful in computer vision tasks, including leaf disease detection. However, their lack of interpretability limits our understanding of their decision-making process and undermines trust in their predictions. In this study, we aim to unravel the black box of CNNs for leaf disease detection through a comprehensive model analysis and feature importance study. We review various techniques in explainable artificial intelligence and propose a methodology that combines model analysis and feature importance methods. We analyze the model’s internal representations and activations in order to understand how different layers process information. Additionally, we employ feature importance methods, like SHapley Additive exPlanations (SHAP), to quantify the influence of individual features on predictions. By assigning importance scores to each pixel or feature, we identify the most discriminative regions or characteristics used by the CNN for disease detection. These insights provide a deeper understanding of learned representations, the decision-making process, and the key visual cues used by CNNs. Our findings enhance interpretability, foster trust in automated leaf disease detection systems, and facilitate the development of more explainable and reliable models in precision agriculture.

Unimodal or multimodal medical image fusion is a powerful technique to aid in medical diagnosis. However, this fusion remains dependent on the methods chosen, and on the type of color or gray level images. In this paper, we propose a generalization of the multimodal medical image fusion technique to take as input color-converted images without distorting the merged image neither spatially nor spectrally. To carry out this work, two phases are necessary: (i) preprocessing and (ii) modal fusion. For the first phase, it is a question of converting all the gray level images into a color image in the RGB base. The outputs of the preprocessing phase will be consumed in the fusion phase regardless of their modality as YIQ color images. We then identify the low frequency (LF) sub-bands and the high frequency (HF) from the Y components based on the non-subsampled shear transform (NSST). Subsequently, the LF sub-images are combined using the weight local feature (WLF) merging rule while the HF sub-images are merged using the sum-modified-laplacian (NSML) technique. Finally, to obtain the merged image we apply the inverse NSST and inverse YIQ. To assess the performance, various experiments conducted on different datasets.

Recently, despite the impressive success of deep learning, eXplainable Artificial Intelligence (XAI) is becoming increasingly important research area for ensuring transparency and trust in deep models, especially in the field of artwork analysis. In this paper, we conduct an analysis of major research contribution milestones in perturbation-based XAI methods and propose a novel iterative method based guided perturbations to explain face detection in Tenebrism painting images. Our method is independent of the model's architecture, outperforms the state-of-the-art method and requires very little computational resources (no need for GPUs). Quantitative and qualitative evaluation shows effectiveness of the proposed method.

Face recognition is one of the most widely used biometrics for identifying people. However, face images suffer from several issues that could affect the achieved results, especially in a crowded environment. Such as facial expression, occlusion, low resolution, noise, illumination and pose variation. In this paper, we propose a robust image representation system for face recognition. First, 3D face data reconstructed from 2D images are used instead of 3D capture. This is accomplished by modeling the difference in the texture map of the 3D aligned input and reference images. Then, fusing shape and texture local binary patterns (LBP) on a mesh for face recognition using the Mesh-LBP. Finally, we used a deep Auto-Encoder to create a compact data representation based on the obtained face images descriptors from the Mesh-LBP. Through experiments conducted on the Multi-PIE and Bosphorus databases, we show that our method is very competitive against state-of-the-art methods.

Abstract Video is considered as one of the most useful and important forms of multimedia data, that is usually used in several applications. Despite its importance, video indexing and retrieval becomes a challenging task. In order to reduce the amount of data and keep only relevant frames, keyframe extraction becomes necessary in a content‐based video retrieval (CBVR) system. In this paper, a keyframe extraction method is proposed based on the face image quality for video surveillance systems. Data is reduced by rejecting frames without faces. Then, face images are clustered by identity. After that, a set of candidate frames is selected to be proceeded. The face quality assessment is based on four metrics including pose estimation, sharpness, brightness and resolution, and the frame with the best face quality is considered as a keyframe. Experimental tests were carried on several datasets in order to prove the efficiency of authors' method compared with state‐of‐the‐art approaches.

This work proposes a framework for simultaneously segmenting foreground objects in a collection of images having heterogeneous contents. Rather than resorting to image co‐segmentation to segment similar objects in multiple images, which requires the use of categorised images, the authors’ idea disseminates segmentation information within images. In this way, it becomes easier to detect foreground objects in all of them simultaneously, mainly under the hypothesis of using similar or different images. General information is aggregated, on foregrounds as well as on backgrounds, from a set of images for joint segmentation of category‐independent objects. The key idea is to estimate the linear dependence of the foreground histograms of the input images to optimise a Markov random field‐based energy function. Iterative optimisation of each image permits after that the enhancement of the final segmentation results. Extensive experiments demonstrate that the proposed method (PM) enables full‐object segmentation of foreground objects within a collection of images composed of different classes. Indeed, the validation of the accuracy on five challenging datasets (iCoseg, Oxford Flowers, MicroSoft Research Cambridge (MSRC), Caltech101 and Berkeley) shows that the PM achieves satisfactory results as compared with state‐of‐the‐art methods. Besides, it has the challenging ability to efficiently deal with uncategorised objects.

Local Fisher discriminant analysis (LFDA) is a feature extraction technique that proved efficient to reduce several types of data and succeeded to outperform many state-of-the-art methods. However, due to its supervised nature, LFDA’s efficiency depends on the available labeled samples and declines dramatically when the latter are very few. Hence, we assume that we cannot resort to LFDA to reduce unlabeled data. In this article, we studied to what extent this assumption is true and questioned the possibility of using LFDA to reduce hyperspectral images (HSIs) with no available ground truth. To study the real impact of the labeled information on LFDA’s performance, we replaced the costly expert-made ground truth by different sets of labeled samples that are generated based on the image’s offered spectral and/or spatial information, with no prior knowledge of the captured scene nor of its classes. Our proposed sets proved able to guide LFDA in extracting relevant discriminating features. This proved that LFDA does not depend only on expert-made labeled information and led us to define the unsupervised image-adapted LFDA (uiaLFDA) that can properly reduce an HSI without requiring its ground truth. To do so and to replace the ground truth that LFDA usually requires to reduce an HSI, uiaLFDA defines its own set of labeled samples by simply gridding the image into cells where each cell is considered a class. Our experiments ran on three HSIs proved that uiaLFDA is as efficient as LFDA and, even better, in reducing unlabeled HSIs.

Color is one of the most important and widely used low-level features in content analysis and retrieval. However, most proposed color descriptors lack the spatial information about color distribution. The majorities of spatial color descriptor characterize the spatial color distribution either by the intra or the inter spatial color information. Thus, we provide a complete description by proposing an Intra and Inter Spatial Color Descriptor (IISCD). In fact, we describe the dispersion of each color in the image. In addition, we propose an improvement of the spatial reasoning to describe the inter-color relationships. In addition, a new similarity approach is proposed to image retrieval. The experimental results prove the high effectiveness and feasibility of the proposed descriptor, through Corel database.

In this paper, we investigate the classification of two soft tissue sarcoma subtypes within a multi-modal medical dataset based on three pre-trained deep convolutional networks of the ImageNet challenge. We use multiparametric MRI’s with histologically confirmed liposarcoma and leiomyosarcoma. Furthermore, the impact of depth on fine-tuning for medical imaging is highlighted. Therefore, we fine-tune the AlexNet along with deeper architectures of the VGG. Two configurations with 16 and 19 learned layers are fine-tuned. Experimental results reveal a 97.2% of classification accuracy with the AlexNet CNN, while better performance has been achieved using the VGG model with 97.86% and 98.27% on VGG-16-Net and VGG-19-Net, respectively. We demonstrated that depth is favorable for STS subtypes differentiation. Addionally, deeper CNN’s converge faster than shallow, despite, fine-tuned CNN‘s can be used as CAD to help radiologists in decision making.

Magnetic resonance imaging (MRI) and positron emission tomography (PET) image fusion is a recent hybrid modality used in several oncology applications. The MRI image shows the brain tissue anatomy and does not contain any functional information, while the PET image indicates the brain function and has a low spatial resolution. A perfect MRI–PET fusion method preserves the functional information of the PET image and adds spatial characteristics of the MRI image with the less possible spatial distortion. In this context, the authors propose an efficient MRI–PET image fusion approach based on non‐subsampled shearlet transform (NSST) and simplified pulse‐coupled neural network model (S‐PCNN). First, the PET image is transformed to YIQ independent components. Then, the source registered MRI image and the Y ‐component of PET image are decomposed into low‐frequency (LF) and high‐frequency (HF) subbands using NSST. LF coefficients are fused using weight region standard deviation (SD) and local energy, while HF coefficients are combined based on S‐PCCN which is motivated by an adaptive‐linking strength coefficient. Finally, inverse NSST and inverse YIQ are applied to get the fused image. Experimental results demonstrate that the proposed method has a better performance than other current approaches in terms of fusion mutual information, entropy, SD, fusion quality, and spatial frequency.

Color is one of the most important and widely used low-level features in content analysis and retrieval. However, most proposed color descriptors lack the spatial information about color distribution. The majorities of proposed solutions, which incorporate spatial information to color descriptors, are pixel based approach and adopt the static quantization. To alleviate these aforementioned drawbacks, we propose a top-down descriptor called the Spatial Dominant Color Descriptor (SDCD). In the extraction of dominant colors, we adopt a dynamic quantization by Gaussian Mixture Models (GMMs). The number of dominant colors is determined automatically using the Bayesian Information Criterion (BIC). The spatial proprieties of each color are described by the dispersion factor. we adopt the penalty trio-model in order to compare images during retrieval. The experimental results prove the high effectiveness and feasibility of the proposed descriptor, through Corel database.

In this paper, a new region based active contour model is proposed for image segmentation. The proposed model is based on the combination of an adaptive local term based on the computation of local statistics deduced at each point of the evolved curve and a global term built using the means of intensities inside and outside the evolved curve. The novelty of the approach is the introduction of an adaptive energy term by the definition of local regions along the curve that will be updated at each iteration of the minimization process according to the gradient information. Experiments on medical, synthetic, real-word and noisy images prove the effectiveness of the proposed method regarding methods of state of the art.

Keyframe extraction is one of the basic procedures relating to video retrieval and summary. It consists on presenting an abstract of the video with the most representative frames. This paper presents an efficient keyframe extraction approach based on local description and graph modularity clustering. The first step is to generate a set of candidate keyframes using a windowing rule in order to reduce the data to be examined. After that, detect interest points in these set of images. Then compute repeatability between each two images belonging to the candidate set and stocks these values in a matrix that we called repeatability matrix. Finally, the repeatability matrix is modelled by an oriented graph and we will select keyframes using graph modularity clustering principle. The experiments showed that this method succeeds in extracting keyframes while preserving the salient content of the video. Further, we found good values in term of precision, PSNR and compression rate.

Action recognition is actually considered as one of the most challenging areas in computer vision domain. In this paper, we propose a new approach based on utilization of motion boundaries to generate Motion Stable Shape (MSS) features to describe human actions in videos. In fact, we have considered actions as a set of human poses. Temporal evolution of each human pose is modeled by a set of new MSS feature's. Motion stable shapes of considered poses are defined by specific regions located at the borders of movements. Our modelisation is composed of different steps. First, a volume of optical flow frames highlighting the principal motions in poses is substracted. Then, motion boundaries are computed from the previous optical flow frames. Finally, maximally Stable Extremal Regions (MSER) are applied to motion boundaries frames in order to obtain MSS features. To predict classes of different human actions, the MSS features are combined with a standard bag-of-words representation. To prove the efficiency of our developed model, we have performed a set of experiments on four datasets: Weizmann, KTH, UFC and Hollywood. Obtained experimental results show that the proposed approach significantly outperforms state-of-the-art methods.

Relation discovery is a crucial task in ontology learning process. The classical approaches for relation extraction, based on statistical, syntactical or pattern matching techniques, focus typically on the taxonomic aspect. The discovery of non-taxonomic relationships is often neglected. We extend these approaches by taking into account the document structure which bears additional knowledge. This paper presents an automatic methodology that addresses the non-taxonomic learning process by considering section heading hierarchy. Our approach gives not only taxonomic relations, but also non-taxonomic ones with their corresponding labels. Experiments have been performed on French Wikipedia articles related to the medical field.

Assessment of image similarity is ubiquitous and essential task to a wide range multimedia applications. In this paper we propose a similarity method which aims at providing an image classification scheme using multi-instances based representation of an image. In other words, the similarity measure is defined to be used within two sample sets where each set, which can be defined in an arbitrary metric space, consists in a set of local features used in describing the content of an image. This measure is a kernel based similarity method inspired from an interesting biological behavior of trees, derived from an energy scheme and induced mathematically by formulating it as a quadratic optimization problem in a reproducing kernel Hilbert space (RKHS).

Content-based image retrieval (CBIR) is a primordial task to provide the most similar images especially in the context of medical imaging for diagnosis aid. In this paper, we propose a CBIR method for a large-scale mammogram datasets. In fact, to extract region of interest (ROI) signatures, four moment descriptors were defined after computing the curvelet coefficients for each level of the ROI. Then, an unsupervised technique based on locality sensitive hashing was adopted for indexing the extracted signatures. The main contribution of the suggested method resides in the variance-based filtering within the retrieval phase in order to extract the suitable buckets in the shortest time, while optimizing the memory requirement. After that, an accurate searching in Hamming space is performed in order to identify the similar ROIs to the query case. Realized experiments on the challenging Digital Database for Screening Mammography (DDSM) dataset proved the performance of the proposed method for the retrieval of the most relevant mammograms in a large-scale dataset. It achieves a mean retrieval precision rate of 97.1% over a total of 11218 mammogram ROIs.

Screening mammography provides two views for each breast: Medio-Lateral Oblique (MLO) and Cranial-Caudal (CC) views. However, current content based image retrieval (CBIR) systems analyze each view independently, in spite of their complementarities. To further improve the retrieval performance, this paper introduces a two-view CBIR system that combines retrieval results of MLO and CC views. First, we computed the similarity scores between MLO (resp. CC) ROIs in the database and the MLO (resp. CC) query ROI. These ROIs are characterized using curvelet moments. Then, a new linear weighted sum scheme combines MLO and CC scores; it assigns weights for each view according to the distribution of the classes of its neighbors. The ROIs having the highest fused scores are displayed to the radiologist and used to compute the malignancy likelihood of the lesion. Experiments performed on mammograms from the Digital Database for Screening Mammography (DDSM) show the effectiveness of the proposed method.

In this study, the authors present an efficient method for approximate large‐scale image indexing and retrieval. The proposed method is mainly based on the visual content of the image regions. Indeed, regions are obtained by a fuzzy segmentation and they are described using high‐frequency sub‐band wavelets. Moreover, because of the difficulty in managing a huge amount of data, which is caused by the exponential growth of the processing time, approximate nearest neighbour algorithms are used to improve the retrieval speed. Therefore they adopted locality‐sensitive hashing (LSH) for region‐based indexing of images. In particular, since LSH performance depends fundamentally on the hash function partitioning the space, they exposed a new function, inspired from the E 8 lattice, that can efficiently be combined with the multi‐probe LSH and the query‐adaptive LSH. To justify the adopted theoretical choices and to highlight the efficiency of the proposed method, a set of experiments related to the region‐based image retrieval are carried out on the challenging ‘Wang’ data set.

The motivation of this work is to register a tumor brain magnetic resonance (MR) image with a normal brain atlas. A normal brain atlas is deformed in order to take account of the presence of a large space occupying tumor. The method use a priori model of tumor growth assuming that the tumor grows in a radial way from a starting point. First, an affine transformation is used in order to bring the patient image and the brain atlas in a global correspondence. Second, the seeding of a synthetic tumor into the brain atlas provides a template for the lesion. Finally, the seeded atlas is deformed combining a method derived from optical flow principles and a model for tumor growth (MTG). Results show that an automatic segmentation method of brain structures in the presence of large deformation can be provided.

In these recent years, kernel methods have gained a considerable interest in many areas of machine learning. This work investigates the ability of kernel clustering methods to deal with one of the meaningful problem of computer vision namely image segmentation task. In this context, we propose a novel kernel method based on an Ellipsoidal Support Vector Data Description ESVDD. Experiments conducted on a selected synthetic data sets and on Berkeley image segmentation benchmark show that our approach significantly outperforms state-of-the-art kernel methods.

Research concerning the detection of interest points features for local query is particularly rich and many methods have been proposed in the literature. Matching of interest points is an essential step in the interest point detectors evaluation process. There are many existing methods for interest points matching and most of them are related to the detectors parameters. In this paper, we present a new matching method based on the prediction validation principle by matching interest points with a local description and with adding spatial constraints. Harris [4], SIFT [6] and SURF [1] were used to detect interest-point features from satellite images. This paper presents a short evaluation of these detectors on satellite images with different spatial resolutions, describes the experimental setup and the results of the detected interest points used for the comparison of the detection rate and the repeatability. Finally, we determine which detector leads to the best results for local query on satellite images.

Retrieval engines provide results according to user request. Nevertheless, reaching satisfaction can not be guaranteed with simple retrieval step. Therefore, it is necessary to communicate this dissatisfaction to the system through relevance feedback techniques. Indeed, with the growing number of image collections and by applying approximate nearest neighbor (ANN) algorithms to resolve the curse of dimensionality, the semantic gap may increase. For this reason, an additional step of relevance feedback is needful to add semantics to the next retrieval iterations. In this paper, a classification of the different relevance feedback techniques related to region-based image retrieval applications is elaborated. Moreover, a new technique of relevance feedback based on re-weighting regions of the query-image by selecting a set of negative examples is detailed. Furthermore, the general context to carry out this technique which is the large-scale heterogeneous image collections indexing and retrieval is presented. In fact, the main contribution of the proposed work is affording efficient results with the minimum number of relevance feedback iterations for high dimensional image databases. Experiments and assessments are carried out within an RBIR system for "Wang" data set in order to prove the effectiveness of the proposed approaches.

There has recently been increasing interest in using advanced computer vision techniques for automatic plant identification. Most of the approaches proposed are based on an analysis of leaf characteristics. Nevertheless, two aspects have still not been well exploited: (1) domain-specific or botanical knowledge (2) the extraction of meaningful and relevant leaf parts. In this paper, we describe a new automated technique for leaf image retrieval that attempts to take these particularities into account. The proposed method is based on local representation of leaf parts. The part-based decomposition is defined and usually used by botanists. The global image query is a combination of part sub-images queries. Experiments carried out on real world leaf images, the Pl@ntLeaves scan images (3070 images totalling 70 species), show an increase in performance compared to global leaf representation.

Unravelling mysteries of the diversity of the plant community is a crucial issue both for the development of many botanical industries as well as for the conservation of ecosystem biodiversity. Traditionally, botanists have proposed detailed dichotomous key descriptions (called also characters or concepts) about the morphology of plants and particularly of leaves that allow them to construct relationships between different plants and between plants and their environment. However, extracting these concepts is complicated, painstaking and can only be carried out by experts. One way to accelerate and broaden the use of these concepts is to automatically extract them directly from images. In this paper, we focus on one of the most basic and important concepts: the leaf arrangement. According to this concept, leaves are divided into four categories: simple, pinnnately compound, palmately compound and compound trifoliate. To accomplish this task, we follow a hierarchical scheme, reducing ambiguity between categories from the most different shapes to the most similar ones. The choice of appropriate features is performed based on botanical observations and validated by a statistical study. The method was tested on real world leaf images (the Pl@ntLeaves scans). Experimental results show its robustness for a high number of leaf species (70 species) and even in the presence of some distortions (such as rotation and partial leaf overlapping).

Voxel colouring is a popular method for reconstructing a three‐dimensional surface model from a set of a few calibrated images. However, the reconstruction quality is largely dependent on a thresholding procedure allowing the authors to decide, for each voxel, whether it is photo‐consistent or not. Nevertheless, in addition to the absence of any information on the neighbouring voxels during the photo‐consistency test, it is extremely difficult to define the appropriate thresholds, which should be precise and stable on all surface voxels. In this study, the authors propose an automated photo‐consistency test based on fuzzy hysteresis thresholding. The proposed method allows the incorporation of the spatial coherence during volume reconstruction, while avoiding ‘floating voxels’ and holes. Moreover, the ambiguity of choosing the thresholds is extremely minimised by defining a fuzzy degree of membership of each voxel into the class of consistent voxels. Also, there is no need for preset thresholds since the hysteresis ones are defined automatically and adaptively depending on the number of images that the voxel is projected onto. Preliminary results are very promising and demonstrate that the proposed method performs automatically precise and smooth volumetric scene reconstruction.

Due to the rise of the Web and the need to have structured knowledge, an interesting line for research is the formalization of ontologies and the creation of conceptual taxonomies from Web documents. The traditional methods for ontology learning and especially those extracting domain concepts from a textual corpus often privilege the analysis of the text itself, whether they are based on a statistical or linguistic approach. In this paper, we propose an approach which differs from the traditional ones since it uses information on the document structure to extract relevant information. Our approach studies each material form in the text in order to extract the most relevant concepts constituting the ontology related to a given field. The concepts are obtained by analyzing the occurrences of the candidate terms in the titles and in the links belonging to the documents and by considering the used styles.

In this paper, a robust 3D triangular mesh watermarking algorithm based on 3D segmentation is proposed. In this algorithm three classes of watermarking are combined. First, we segment the original image to many different regions. Then we mark every type of region with the corresponding algorithm based on their curvature value. The experiments show that our watermarking is robust against numerous attacks including RST transformations, smoothing, additive random noise, cropping, simplification and remeshing.

Summary form only given. In this paper we introduce a standard approach for medical images segmentation. In fact, for these images the segmentation consists in the extraction of an area of interest representing the organ subject of diagnosis. We distinguish two approaches depending on whether this area is composed of one region or of many regions. If it is composed of a single region, we introduce a growing region algorithm after a prestep based on fuzzy sets. Otherwise, we introduce an approach integrating a hierarchical system of segmentation in regions and a system of fuzzy classification. We illustrate our approach by applying it on real images in the frameworks of dermatology, neurology and mammography.