The emergence of Vision-Language Models (VLMs) like Contrastive Language-Image Pretraining (CLIP) provides appealing solutions to various vision problems including Dynamic Facial Expression Recognition (DFER). However, most of the proposed approaches face major challenges, particularly related to inefficient full fine-tuning of the encoders and the complexity of the models. Moreover, some of the proposed methods seem to struggle with suboptimal performance due to (i) poor alignment between textual and visual representations, and (ii) ineffective temporal modeling. To address these challenges, we propose PE-CLIP, a parameter-efficient fine-tuning (PEFT) framework that elegantly adapts CLIP for dynamic facial expression recognition, requiring significantly reduced number of trainable parameters while maintaining high accuracy. At its core, to enhance efficiency and performance, PE-CLIP introduces two specialized adapters namely a Temporal Dynamic Adapter (TDA) and a Shared Adapter (ShA). The TDA is a GRU-based module with a dynamic scaling mechanism, capturing sequential dependencies while adaptively modulating the contribution of each temporal feature to emphasize the most informative ones while mitigating irrelevant variations. The ShA is a lightweight adapter refine representations within both textual and visual encoders, ensuring consistent feature processing while maintaining parameter efficiency. Additionally, we leverage Multi-modal Prompt Learning (MaPLe), which introduces learnable prompts to both visual and action unit-based textual description inputs, further improving the semantic alignment between modalities and enabling the efficient adaptation of CLIP for dynamic tasks. We evaluate our proposed PE-CLIP on two benchmark datasets, namely DFEW, FERV39K, and AFEW, achieving competitive performance compared to state-of-the-art methods while requiring fewer trainable parameters. By striking an optimal balance between parameter efficiency and performance, PE-CLIP sets a new benchmark in resource-efficient DFER. The source code of the proposed PE-CLIP will be publicly available at https://github.com/Ibtissam-SAADI/PE-CLIP .

International audience

Facial beauty prediction (FBP) is an emerging area of artificial intelligence (AI) that focuses on the development of models that analyze facial features to assess beauty, based on human perception. This task is particularly challenging due to the subjective nature of beauty and limited resources. Deep learning methods have proven their exceptional ability to capture complex features and are therefore well suited for FBP tasks. This paper reviews recent advances in FBP, focusing on deep learning techniques and benchmark datasets. A proposed taxonomy organizes the main methods according to their design and applications, and comparative analyzes highlight trends and the performance of different models. Finally, the study outlines future research directions to drive progress in this evolving field.

Anomaly detection in time series poses a critical challenge in industrial monitoring, environmental sensing, and infrastructure reliability, where accurately distinguishing anomalies from complex temporal patterns remains an open problem. While existing methods, such as the Anomaly Transformer leveraging multi-layer association discrepancy between prior and series distributions and Dual Attention Contrastive Representation Learning architecture (DCdetector) employing dual-attention contrastive learning, have advanced the field, critical limitations persist. These include sensitivity to short-term context windows, computational inefficiency, and degraded performance under noisy and non-stationary real-world conditions. To address these challenges, we present MAAT (Mamba Adaptive Anomaly Transformer), an enhanced architecture that refines association discrepancy modeling and reconstruction quality for more robust anomaly detection. Our work introduces two key contributions to the existing Anomaly transformer architecture: Sparse Attention, which computes association discrepancy more efficiently by selectively focusing on the most relevant time steps. This reduces computational redundancy while effectively capturing long-range dependencies critical for discerning subtle anomalies. A Mamba-Selective State Space Model (Mamba-SSM) is also integrated into the reconstruction module. A skip connection bridges the original reconstruction and the Mamba-SSM output, while a Gated Attention mechanism adaptively fuses features from both pathways. This design balances fidelity and contextual enhancement dynamically, improving anomaly localization and overall detection performance. Extensive experiments on benchmark datasets demonstrate that MAAT significantly outperforms prior methods, achieving superior anomaly distinguishability and generalization across diverse time series applications. By addressing the limitations of existing approaches, MAAT sets a new standard for unsupervised time series anomaly detection in real-world scenarios. Code available at https://github.com/ilyesbenaissa/MAAT . • MAAT uses Sparse Attention and Mamba-SSM for temporal dependencies. • Block-wise sparse attention reduces costs vs models like DCdetector . • Gated attention merges sparse attention with Mamba-SSM for better detection. • Uses SSM via Mamba for effective complex, noisy data management . • Outperforms Anomaly Transformer and DCdetector in F1, accuracy .

ABSTRACT Advancements in deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs), have ushered in an era of generating highly realistic images. While this technological progress has captured significant interest, it has also raised concerns about the high challenge in distinguishing real images from their synthetic counterparts. This paper takes inspiration from the potent convergence capabilities between vision and language, coupled with the zero‐shot nature of vision‐language models (VLMs). We introduce an innovative method called Bi‐LORA that leverages VLMs, combined with low‐rank adaptation (LORA) tuning techniques, to enhance the precision of synthetic image detection for unseen model‐generated images. The pivotal conceptual shift in our methodology revolves around reframing binary classification as an image captioning task, leveraging the distinctive capabilities of cutting‐edge VLM, notably bootstrapping language image pre‐training (BLIP)2. Rigorous and comprehensive experiments are conducted to validate the effectiveness of our proposed approach, particularly in detecting unseen diffusion‐generated images from unknown diffusion‐based generative models during training, showcasing robustness to noise, and demonstrating generalisation capabilities to GANs. The experiments show that Bi‐LORA outperforms state of the art models in cross‐generator tasks because it leverages multi‐modal learning, open‐world visual knowledge, and benefits from robust, high‐level semantic understanding. By combining visual and textual knowledge, it can handle variations in the data distribution (such as those caused by different generators) and maintain strong performance across different domains. Its ability to transfer knowledge, robustly extract features and perform zero‐shot learning also contributes to its generalisation capabilities, making it more adaptable to new generators. The experimental results showcase an impressive average accuracy of 93.41% in synthetic image detection on unseen generation models. The code and models associated with this research can be publicly accessed at https://github.com/Mamadou‐Keita/VLM‐DETECT .

Evaluating house prices is crucial for various stakeholders, including homeowners, investors, and policymakers. However, traditional spatial interpolation methods have limitations in capturing the complex spatial relationships that affect property values. To address these challenges, we have developed a new method called Multi-Head Gated Attention for spatial interpolation. Our approach builds upon attention-based interpolation models and incorporates multiple attention heads and gating mechanisms to better capture spatial dependencies and contextual information. Importantly, our model produces embeddings that reduce the dimensionality of the data, enabling simpler models like linear regression to outperform complex ensembling models. We conducted extensive experiments to compare our model with baseline methods and the original attention based interpolation model. The results show a significant improvement in the accuracy of house price predictions, validating the effectiveness of our approach. This research advances the field of spatial interpolation and provides a robust tool for more precise house price evaluation. Our GitHub repository. 1 1 Final_file/tree/main/ASI-main . contains the data and code for all datasets, which are available for researchers and practitioners interested in replicating or building upon our work. • Multi-Head Gated Attention model improves spatial interpolation for house price prediction. • Geographical and structural attention mechanisms enhance spatial feature extraction. • Embedding generation reduces data complexity, boosting model performance and accuracy. • New dataset combines Italian city data with structural and geographical attributes. • Model outperforms traditional methods, validated across multiple diverse datasets.

Automatic classification of bone metastases is a major challenge and is receiving increasing attention from the research community. One of the major challenges is the accurate classification of medical images, especially the distinction between benign and malignant images, which can greatly help physicians in decision-making. Recently, several deep-learning techniques have been proposed for medical image classification. Their performance, however, is influenced by both the dataset and the imaging modality. In this work, we investigate the performance of several state-of-the-art CNN architectures, namely InceptionV3, EfficientNet, ResNext50, and DenseNet161, as well as Transformer architectures, namely ViT and DeiT. We trained and tested these algorithms on a large dataset consisting of CT-scan images. The Transformer algorithms were found to be superior to CNN algorithms in detecting bone metastases. In particular, ViT Tiny achieved the best performance in terms of accuracy and F1-score as compared to other architectures.

Abstract In recent years, estimating beauty of faces has attracted growing interest in the fields of computer vision and machine learning. This is due to the emergence of face beauty datasets (such as SCUT-FBP, SCUT-FBP5500 and KDEF-PT) and the prevalence of deep learning methods in many tasks. The goal of this work is to leverage the advances in Deep Learning architectures to provide stable and accurate face beauty estimation from static face images. To this end, our proposed approach has three main contributions. To deal with the complicated high-level features associated with the FBP problem by using more than one pre-trained Convolutional Neural Network (CNN) model, we propose an architecture with two backbones (2B-IncRex). In addition to 2B-IncRex, we introduce a parabolic dynamic law to control the behavior of the robust loss parameters during training. These robust losses are ParamSmoothL1, Huber, and Tukey. As a third contribution, we propose an ensemble regression based on five regressors, namely Resnext-50, Inception-v3 and three regressors based on our proposed 2B-IncRex architecture. These models are trained with the following dynamic loss functions: Dynamic ParamSmoothL1, Dynamic Tukey, Dynamic ParamSmoothL1, Dynamic Huber, and Dynamic Tukey, respectively. To evaluate the performance of our approach, we used two datasets: SCUT-FBP5500 and KDEF-PT. The dataset SCUT-FBP5500 contains two evaluation scenarios provided by the database developers: 60-40% split and five-fold cross-validation. Our approach outperforms state-of-the-art methods on several metrics in both evaluation scenarios of SCUT-FBP5500. Moreover, experiments on the KDEF-PT dataset demonstrate the efficiency of our approach for estimating facial beauty using transfer learning, despite the presence of facial expressions and limited data. These comparisons highlight the effectiveness of the proposed solutions for FBP. They also show that the proposed Dynamic robust losses lead to more flexible and accurate estimators.

Since the emergence of the Covid-19 pandemic in late 2019, medical imaging has been widely used to analyze this disease. Indeed, CT-scans of the lungs can help diagnose, detect, and quantify Covid-19 infection. In this paper, we address the segmentation of Covid-19 infection from CT-scans. To improve the performance of the Att-Unet architecture and maximize the use of the Attention Gate, we propose the PAtt-Unet and DAtt-Unet architectures. PAtt-Unet aims to exploit the input pyramids to preserve the spatial awareness in all of the encoder layers. On the other hand, DAtt-Unet is designed to guide the segmentation of Covid-19 infection inside the lung lobes. We also propose to combine these two architectures into a single one, which we refer to as PDAtt-Unet. To overcome the blurry boundary pixels segmentation of Covid-19 infection, we propose a hybrid loss function. The proposed architectures were tested on four datasets with two evaluation scenarios (intra and cross datasets). Experimental results showed that both PAtt-Unet and DAtt-Unet improve the performance of Att-Unet in segmenting Covid-19 infections. Moreover, the combination architecture PDAtt-Unet led to further improvement. To Compare with other methods, three baseline segmentation architectures (Unet, Unet++, and Att-Unet) and three state-of-the-art architectures (InfNet, SCOATNet, and nCoVSegNet) were tested. The comparison showed the superiority of the proposed PDAtt-Unet trained with the proposed hybrid loss (PDEAtt-Unet) over all other methods. Moreover, PDEAtt-Unet is able to overcome various challenges in segmenting Covid-19 infections in four datasets and two evaluation scenarios.

Clustering is inherently a process of exploratory data analysis. It has attracted more attention recently because much real-world data consists of multiple representations or views. However, it becomes increasingly problematic when dealing with large and heterogeneous data. It is worth noting that several approaches have been developed to increase computational efficiency, although most of them have some drawbacks: (1) Most existing techniques consider equal or static weights to quantify importance across different views and samples, so common and complementary features cannot be used. (2) The clustering task is performed by arbitrary initialization without caring about the rich structure of the joint discrete representation, and thus poorly executed. In this paper, we propose a novel approach called “Auto-Weighted Binary Multi-View Clustering Via Deep Initialization” for large-scale multi-view clustering based on two main scenarios. First, we consider the distinction between different views based on the importance of samples, and therefore apply a dynamic learning strategy for the automatic weighting of views and samples. Second, in the context of initializing binary clustering, we develop a new CNN feature and use a low-dimensional binary embedding by exploiting the efficient capabilities of Fourier mapping. Moreover, our approach simultaneously learns a joint discrete representation and performs direct clustering using a constrained binary matrix factorization; the optimization problem is perfectly solved in a unified learning model. Experimental results conducted on several challenging datasets demonstrate the effectiveness and superiority of the proposed approach over state-of-the-art methods in terms of accuracy, normalized mutual information, and purity.

In this article, we propose a new approach for the cow heat detection from endoscopic images. Our approach permits to identify on the fly the cow heat state through two successive stages, namely cervix detection then heat classification. For this purpose, images are analyzed by a Transformer based detection model to localize the cervix, in which case they are analyzed by a CNN-based heat classification model. The proposed approach permits to assist the farmer during the insemination operation by localizing the cervix in an accurate way. Moreover, the confidence level of the final decision of the classification model is increased by focusing its analysis only on cervix images. The effectiveness of our method is demonstrated on our generated dataset and the obtained performance outperform the state of the art.

Recently, the estimation of facial age has attracted much attention. This letter extends and improves a recently developed method (Guehairia et al., 2020) for fusing multiple deep facial features for age estimation. This method was based on deep random forests. We propose a new pipeline that integrates tensor-based subspace learning before applying DRFs. Deep face features of a training set are represented as a 3D tensor. Multi-linear Whitened Principal Component (MWPCA) and Tensor Exponential Discriminant (TEDA) are used to extract the most discriminative information. The tensor subspace features are then fed into DRFs to predict age. Experiments conducted on five public face databases show that our method can compete with many state-of-the-art methods.

In the last decade, several studies have shown that facial attractiveness can be learned by machines. In this paper, we address Facial Beauty Prediction from static images. The paper contains three main contributions. First, we propose a two-branch architecture (REX-INCEP) based on merging the architecture of two already trained networks to deal with the complicated high-level features associated with the FBP problem. Second, we introduce the use of a dynamic law to control the behaviour of the following robust loss functions during training: ParamSmoothL1, Huber and Tukey. Third, we propose an ensemble regression based on Convolutional Neural Networks (CNNs). In this ensemble, we use both the basic networks and our proposed network (REX-INCEP). The proposed individual CNN regressors are trained with different loss functions, namely MSE, dynamic ParamSmoothL1, dynamic Huber and dynamic Tukey. Our approach is evaluated on the SCUT-FBP5500 database using the two evaluation scenarios provided by the database creators: 60%–40% split and five-fold cross-validation. In both evaluation scenarios, our approach outperforms the state of the art on several metrics. These comparisons highlight the effectiveness of the proposed solutions for FBP. They also show that the proposed dynamic robust losses lead to more flexible and accurate estimators.

Abstract Over the past two decades, several studies have paid great attention to biometric palmprint recognition. Recently, most methods in literature adopted deep learning due to their high recognition accuracy and the capability to adapt with different acquisition palmprint images. However, high-dimensional data with a large number of uncorrelated and redundant features remain a challenge due to computational complexity issues. Feature selection is a process of selecting a subset of relevant features, which aims to decrease the dimensionality, reduce the running time, and improve the accuracy. In this paper, we propose efficient unimodal and multimodal biometric systems based on deep learning and feature selection. Our approach called simplified PalmNet–Gabor concentrates on the improvement of the PalmNet for fast recognition of multispectral and contactless palmprint images. Therefore, we used Log-Gabor filters in the preprocessing to increase the contrast of palmprint features. Then, we reduced the number of features using feature selection and dimensionality reduction procedures. For the multimodal system, we fused modalities at the matching score level to improve system performance. The proposed method effectively improves the accuracy of the PalmNet and reduces the number of features as well the computational time. We validated the proposed method on four public palmprint databases, two multispectral databases, CASIA and PolyU, and two contactless databases, Tongji and PolyU 2D/3D. Experiments show that our approach achieves a high recognition rate while using a substantially lower number of features.

Autonomous vehicles present a promising opportunity in the future of transportation systems by providing road safety. As significant progress has been made in the automatic environment perception, the detection of road obstacles remains a major challenge. Thus, to achieve reliable obstacle detection, several sensors have been employed. For short ranges, the Ultra-Wide Band (UWB) radar is utilized in order to detect objects in the near field. However, the main challenge appears in distinguishing the real target’s signature from noise in the received UWB signals. In this paper, we propose a novel framework that exploits Recurrent Neural Networks (RNNs) with UWB signals for multiple road obstacle detection. Features are extracted from the time-frequency domain using the discrete wavelet transform and are forwarded to the Long short-term memory (LSTM) network. We evaluate our approach on the OLIMP dataset which includes various driving situations with complex environment and targets from several classes. The obtained results show that the LSTM-based system outperforms the other implemented related techniques in terms of obstacle detection.

The recognition of Covid-19 infection and distinguishing it from other Lung diseases from CT-scan is an emerging field in machine learning and computer vision community. In this paper, we proposed deep learning based approach to recognize the Covid-19 infection from the CT-scans. Our approach consists of two main stages. In the first stage, we trained deep learning architectures with Multi-task strategy for Slice-Level classification. In the second stage, we used the previous trained models with XG-boost classifier to classify the whole CT-scan into Normal, Covid-19 or Cap class. The evaluation of our approach achieved promising results on the validation data of SPGC-COVID dataset. In more details, our approach achieved 87.75% as overall accuracy and 96.36%, 52.63% and 95.83% sensitivities for Covid-19, Cap and Normal, respectively. From other hand, our approach achieved the fifth place on the three test datasets of SPGC on COVID-19 challenge where our approach achieved the best result for Covid-19 sensitivity.

Autonomous Driving (AD) systems are heavily reliant on supervised models. In these approaches, a model is trained to detect only a predefined number of obstacles. However, for applications like railway obstacle detection, the training dataset is limited and not all possible obstacle classes are known beforehand. For such safety-critical applications, this situation is problematic and could limit the performance of obstacle detection in autonomous trains. In this paper, we propose an exploratory study using unsupervised models based on a large set of generated convolutional autoencoder models to detect obstacles on railway's track level. The study was conducted based on three components: loss functions, activations and optimizers. Existing works rely on fixing thresholds to judge the performance of the model. We propose instead a methodology based on Multi-Criteria Decision Making (MCDM) to evaluate the performance of all models. Furthermore, we introduce the notion of gap-score to evaluate each model by calculating the average difference between the reconstruction score on images with and without obstacles. The aim is to find models maximizing the average of gap-scores and rank them according to their performances. Experimental results show that the evaluated models can provide up to 68 % average gap-score.

Automatic kinship verification from facial images is an emerging research topic in machine learning community. In this paper, we proposed an effective facial features extraction model based on multi-view deep features. Thus, we used four pre-trained deep learning models using eight features layers (FC6 and FC7 layers of each VGG-F, VGG-M, VGG-S and VGG-Face models) to train the proposed Multilinear Side-Information based Discriminant Analysis integrating Within Class Covariance Normalization (MSIDA + WCCN) method. Furthermore, we show that how can metric learning methods based on WCCN method integration improves the Simple Scoring Cosine similarity (SSC) method. We refer that we used the SSC method in RFIW'20 competition using the eight deep features concatenation. Thus, the integration of WCCN in the metric learning methods decreases the intra-class variations effect introduced by the deep features weights. We evaluate our proposed method on two kinship benchmarks namely KinFaceW-I and KinFaceW-II databases using four Parent-Child relations (Father-Son, Father-Daughter, Mother-Son and Mother-Daughter). Thus, the proposed MSIDA + WCCN method improves the SSC method with 12.80% and 14.65% on KinFaceW-I and KinFaceW-II databases, respectively. The results obtained are positively compared with some modern methods, including those that rely on deep learning.

In this paper, we present a combined approach for human localization and classification in Autonomous Train application. Our contribution is threefold. (a) The creation of a new dataset for workers wearing orange vests in a railway environment context. (b) A deep learning supervised YOLO object detector for persons detection combined with a linear SVM (Support Vector Machine) classifier for persons classification into workers wearing orange vests or travelers. (c) A realtime vision-based technique for the environment monitoring in a driverless train application. Experimental results evaluate the parameters of our two stages detection approach and show that our algorithm is robust in detecting and classifying railway workers for a real-time implementation on an embedded system. Our implementation on an embedded system allows a detection with a correct classification rate of 98.5 % of accuracy and a classification time of 1 ms per frame.

Facial expressions recognition have become one of the most important fields of research in pattern recognition, in this paper, we propose a method to identify the facial expressions of the people through their emotions, this method combining Viola-Jones face detection algorithm, Facial image enhancement using histogram equalization, discrete wavelet transform (DWT) and deep convolution neural network. Extraction results of facial features using DWT are the input of CNN, which are used directly to train the CNN network. Our experimental were performed on CK+ database and JAFFE face database, the obtained results based on this network is 96.46% and 98.43% respectively.

Checking the kinship of facial images is a difficult research topic in computer vision that has attracted attention in recent years. The methods suggested so far are not strong enough to predict kinship relationships only by facial appearance. To mitigate this problem, we propose a new approach called Deep-Tensor+ELM to kinship verification based on deep (VGG-Face descriptor) and tensor (BSIF-Tensor & LPQ-Tensor using MSIDA method) features through Extreme Learning Machine (ELM). While ELM aims to deal with small size training features dimension, deep and tensor features are proven to provide significant enhancement over shallow features or vector-based counterparts. We evaluate our proposed method on the largest kinship benchmark namely FIW database using four Grandparent-Grandchild relations (GF-GD, GF-GS, GM-GD and GM-GS). The results obtained are positively compared with some modern methods, including those that rely on deep learning.

Facial expression conveys important signs about the human affective state, cognitive activity, intention and personality. In fact, the automatic facial expression recognition systems are getting more interest year after year due to its wide range of applications in several interesting fields such as human computer/robot interaction, medical applications, animation and video gaming. In this study, the authors propose to combine between different descriptors features (histogram of oriented gradients, local phase quantisation and binarised statistical image features) after applying principal component analysis on each of them to recognise the six basic expressions and the neutral face from the static images. Their proposed fusion method has been tested on four popular databases which are: JAFFE, MMI, CASIA and CK+, using two different cross‐validation schemes: subject independent and leave‐one–subject‐out. The obtained results show that their method outperforms both the raw features concatenation and state‐of‐the‐art methods.

Facial automatic kinship verification is a novel challenging research problem in computer vision. It performs the automatic examining of the facial attributes and expecting whether two persons have a biological kin relation or not. In this study, the authors introduce a novel learning method for kinship verification which consists of four main stages. (i) A discrete cosine transform network (DCTNet) applied to each face image in order to extract the most significant inherited facial features through convolutional layers based on 2D DCT filter bank. (ii) The response of the last layer is binarised and partitioned into non‐overlapping block‐wise histograms. (iii) A tied rank normalisation is used to eliminate the disparity of histogram vectors of DCTNet. (iv) The last stage is to distinguish between the different pairs. The distances between data points in the same classes (positive pairs) are as small as possible, while the distances are as large as possible between data points in different classes (negative pairs). Experiments are conducted on three public databases (UBKinFace, KinFaceW‐I, and KinFaceW‐II). They show significant performance improvements compared to state‐of‐the‐art methods.

In recent years, software-based face presentation attack detection (PAD) methods have seen a great progress. However, most existing schemes are not able to generalize well in more realistic conditions. The objective of this competition is to evaluate and compare the generalization performances of mobile face PAD techniques under some real-world variations, including unseen input sensors, presentation attack instruments (PAI) and illumination conditions, on a larger scale OULU-NPU dataset using its standard evaluation protocols and metrics. Thirteen teams from academic and industrial institutions across the world participated in this competition. This time typical liveness detection based on physiological signs of life was totally discarded. Instead, every submitted system relies practically on some sort of feature representation extracted from the face and/or background regions using hand-crafted, learned or hybrid descriptors. Interesting results and findings are presented and discussed in this paper.

The objective of this article is to present a new video compression scheme with several potentialities in medical and industrial field. The proposed method will involve the process of transform, scaling and quantization, and it is based on bandelet transform coupled with the set partitioning in hierarchical trees (SPIHT) coding. The effectiveness of this technique results in combining two advantages. First it takes advantage of the anisotropic regularities of frames; second, it exploits the dependencies between the geometric transformed coefficients using SPIHT encoder to encode significant coefficients, while reducing redundancy, which, in turn, results in decreasing the volume of data without altering the pertinent information. The authors examined three scenarios, according to the above critical points of the visual quality of decompressed video. The first scenario concerns the choice of compression filter. The second identifies appropriate transform type, and the third validates the proposed algorithm with respect to classical algorithms. The performances of the proposed algorithm are evaluated using a set of objective video quality assessment metrics, including PSNR (peak signal- to-noise ratio), MSSIM (mean structural similarity) and VIF (visual information fidelity). The experimental results illustrate clearly the superiority of our algorithm with respect to Wavelet-SPIHT, MPEG-4, and H.264, H.265/MPEG-HEVC (video coding standards) when applied to a set of medical image tests.

The osteoporosis is a common public health problem that weakens bones, which increases risk of fracture, due to the porous trabecular bone microarchitecture. In a clinical routine, the basis osteoporosis screening is done by measuring the bone mineral density (BMD) determined by dual-energy X-ray absorptiometry (DXA), which is an inefficient and manually non-invasive procedure. Therefore, automatic methods that potentially characterize the trabecular bone texture using texture like analysis are deemed very relevant. Fractal is widely used for trabecular bone texture analysis, where the fractal dimension (FD) is the main component of fractal features for quantifying the complexity of the images. The aim of this article is to enhance the quality of the preprocessing prior to the application of the fractal analysis in order to yield a robust FD estimate in frequency domain. A preprocessing stage involves a combination of contrast enhancement followed by Discrete Cosine Transform (DCT), where the DCT coefficients is inputted to differential box-counting method (DBCM) to estimate the FD. This approach is shown to provide better results, in term of discriminating pathological and healthy trabecular bones, using statistical Wilcoxon rank sum test, than estimating FD without preprocessing stage. The testing and evaluation phases are carried out using the Lille INSERM U 703 database that contains a set of ROIs (Region Of Interest) CT-SCAN texture images of both healthy and pathological trabecular bones.

We present a new interactive segmentation framework to delineate the prostate from MR images. We first explicitly address the segmentation problem based on fast globally Finsler Active Contours (FAC) by incorporating both statistical and geometric shape prior knowledge. In doing so, we are able to exploit the more global aspects of segmentation by incorporating user feedback in segmentation process. In addition, once the prostate shape has been segmented, a cost functional is designed to incorporate both the local image statistics as user feedback and the learned shape prior. We provide experimental results, which include several challenging clinical data sets, to highlight the algorithm's capability of robustly handling supine/prone prostate segmentation.

We present a new globally supervised segmentation method in the characteristic function framework based on an active contours (AC) model incorporating both shape prior and texture descriptors. The shape prior descriptor is formulated as the traditional Legendre moment and the texture descriptor as a linear combination of local inside/outside texture descriptor. Using these two descriptors, the AC energy incorporates both learned textures and training shapes. This formulation has two main advantages: 1) by discriminating independently the foreground/background textures. 2) by incorporating both the learned inside/outside texture and the training shape. The trade-off between inside and outside texture descriptor is ensured by balancing descriptor. We illustrate the performance of our segmentation algorithm using some challenging textured images.

This paper describes a proposition for constructing an automatic personalization system based on SVM (support vector machine) method. Our approach helps the learning units designers to select automatically the learning scenarios adapted to learners. In our experimentation, we have used a database that contains information about computer science engineering students of the Tlemcen university and descriptions of learning scenarios. We have implemented our SVM classifier using the open environment rdquoWekardquo. The test results showed an attractive performance. The values of the classification rate, the precision and the recall are very acceptable.

In this paper, we present a global optimisation method based on a multi-objective Genetic Algorithm (GA) for the design of filter banks in a lossy image coding scheme. To be effective, the filter banks should satisfy a number of desirable criteria related to such scheme. We formulate the optimization problem as multi-objective and we use the Non-dominated Sorting Genetic Algorithm approach (NSGAII) to solve this problem by searching solutions that achieve the best compromise between the different objectives criteria, these solutions are known as Pareto Optimal Solutions. Flexibility in the design is introduced by relaxing Perfect Reconstruction (PR) condition and defining a PR violation measure as an objective criterion to maintain near perfect reconstruction (N-PR) solutions. Furthermore, the optimized filter banks are near-orthogonal. This can only be made possible by minimizing the deviation from the orthogonality in the optimization process. Our designed filter banks lead to a significant improvement in performance of coding with respect to the 9/7 filter bank of JPEG2000 at high compression ratios and offer a slight improvement at low compression ratios.

We present a new unsupervised segmentation of textural images based on integration of a texture descriptor in the formulation of active contour. The proposed texture descriptor intrinsically describes the geometry of textural regions using the shape operator defined in Beltrami framework. We use the Chernoff distance to define an active contours model which discriminates textures by maximizing the distance between the probability density functions which leads to distinguish textural objects of interest and background described by texture descriptor. We prove the existence of a solution to the new formulated active contours based segmentation model and we propose a fast and easy algorithm based on the dual formulation of the Total Variation norm. Finally, we show results on challenging images to illustrate accurate segmentations that are possible.

A new geometric active contour model based on iterative refinement of edge map stopping function obtained by iterative grey level homogenization is presented. To homogenize grey level of initial image, we proposed to couple adaptively the partial differential equation (PDE) of the anisotropic diffusion filter to that of geometric active contour model. The proposed model avoids the leakage problems and ensures that the evolving level set curves of geometric active contour model to reach more rapidly the true edges boundaries of the objects to be segmented. The robustness and precision performance of proposed model are evaluated on MR images and compared to the classical geometric active contour model (CGAC).

We propose a semi-automated method to isolate vessels or other structures from magnetic resonance imaging acquisitions. This method is divided into two parts. The first part is a nonlinear filter, using morphological operators, based on the invariance properties of the image. The second consists of finding the extrema contours. The contour which is proposed here is called the virtual contour, because it is located between the extrema contours. We have tested our method on 20 patients. The results showed that the method is robust and efficient when it comes to segmenting vessels from MRI.