0000000000020250
AUTHOR
Mohammed El Hassouni
A New Image Distortion Measure Based on Natural Scene Statistics Modeling
In the field of Image Quality Assessment (IQA), this paper examines a Reduced Reference (RRIQA) measure based on the bi-dimensional empirical mode decomposition. The proposed measure belongs to Natural Scene Statistics (NSS) modeling approaches. First, the reference image is decomposed into Intrinsic Mode Functions (IMF); the authors then use the Generalized Gaussian Density (GGD) to model IMF coefficients distribution. At the receiver side, the same number of IMF is computed on the distorted image, and then the quality assessment is done by fitting error between the IMF coefficients histogram of the distorted image and the GGD estimate of IMF coefficients of the reference image, using the …
A General Framework for Complex Network-Based Image Segmentation
International audience; With the recent advances in complex networks theory, graph-based techniques for image segmentation has attracted great attention recently. In order to segment the image into meaningful connected components, this paper proposes an image segmentation general framework using complex networks based community detection algorithms. If we consider regions as communities, using community detection algorithms directly can lead to an over-segmented image. To address this problem, we start by splitting the image into small regions using an initial segmentation. The obtained regions are used for building the complex network. To produce meaningful connected components and detect …
Movie Script Similarity Using Multilayer Network Portrait Divergence
International audience; This paper addresses the question of movie similarity through multilayer graph similarity measures. Recent work has shown how to construct multilayer networks using movie scripts, and how they capture different aspects of the stories. Based on this modeling, we propose to rely on the multilayer structure and compute different similarities, so we may compare movies, not from their visual content, summary, or actors, but actually from their own storyboard. We propose to do so using “portrait divergence”, which has been recently introduced to compute graph distances from summarizing graph characteristics. We illustrate our approach on the series of six Star Wars movies.
A Community-Aware Backbone Extractor for Weighted Networks
International audience
Finding Influential Nodes in Networks with Community Structure
International audience; Identifying influential nodes is a fundamental issue in complex networks. Several centrality measures take advantage of various network topological properties to target the top spreaders. However, the vast majority of works ignore its community structure while it is one of the main properties of many real-world networks. In our previous work 4 , we show that the centrality of a node in a network with non-overlapping communities depends on two features: Its local influence on the nodes belonging to its community, and its global influence on nodes belonging to the other communities. For this end, we introduced a framework to adapt all the classical centrality measures …
Blind Robust 3-D Mesh Watermarking Based on Mesh Saliency and QIM Quantization for Copyright Protection
International audience; Due to the recent demand of 3-D models in several applications like medical imaging, video games, among others, the necessity of implementing 3-D mesh watermarking schemes aiming to protect copyright has increased considerably. The majority of robust 3-D watermark-ing techniques have essentially focused on the robustness against attacks while the imperceptibility of these techniques is still a real issue. In this context, a blind robust 3-D mesh watermarking method based on mesh saliency and Quantization Index Modulation (QIM) for Copyright protection is proposed. The watermark is embedded by quantifying the vertex norms of the 3-D mesh using QIM scheme since it offe…
Influential Spreaders in Networks with Community Structure
International audience; Hassouni (2019). Centrality in Complex Networks with overlapping Community structure. Scientific Reports, 9(1).
Reduced Reference Mesh Visual Quality Assessment Based on Convolutional Neural Network
3D meshes are usually affected by various visual distortions during their transmission and geometric processing. In this paper we propose a reduced reference method for mesh visual quality assessment. The method compares features extracted from the distorted mesh and the original one using a convolutional neural network in order to estimate the visual quality score. The perceptual distance between two meshes is computed as the Kullback-Leibler divergence between the two sets of feature vectors. Experimental results from two subjective databases (LIRIS masking database and LIRIS/EPFL general purpose database) and comparisons with seven objective metrics cited in the state-of-the-art demonstr…
Image Quality Assessment Based on Intrinsic Mode Function Coefficients Modeling
Reduced reference image quality assessment (RRIQA) methods aim to assess the quality of a perceived image with only a reduced cue from its original version, called ”reference image”. The powerful advantage of RR methods is their ”General-purpose”. However, most introduced RR methods are built upon a non-adaptive transform models. This can limit the scope of RR methods to a small number of distortion types. In this work, we propose a bi-dimensional empirical mode decomposition-based RRIQA method. First, we decompose both, reference and distorted images, into Intrinsic Mode Functions (IMF), then we use the Generalized Gaussian Density (GGD) to model IMF coefficients. Finally, the distortion m…
Measuring Movie Script Similarity using Characters, Keywords, Locations, and Interactions
Measuring similarity between multilayer networks is difficult, as it involves various layers and relationships that are challenging to capture using distance measures. Existing techniques have focused on comparing layers with the same number of nodes and ignoring interrelationships. In this research, we propose a new approach for measuring the similarity between multilayer networks while considering interrelationships and networks of various sizes. We apply this approach to multilayer movie networks composed of layers of different entities (character, keyword, and location) and interrelationships between them. The proposed method captures intra-layer and inter-layer relationships, providing…
Backbone Extraction of Weighted Modular Complex Networks based on their Component Structure
This work introduces a generic backbone extraction framework exploiting the mesoscopic network structure. Indeed, numerous real-world networks are made of dense groups of nodes called communities, multi-core or local components. To deal with these groups' heterogeneity, we propose to extract the backbones independently from their various components and fuse them. Experimental investigations on real-world networks demonstrate the effectiveness of the proposed approach compared to the classical techniques' agnostic of the mesoscopic structure of real-world networks.
Convolutional Neural Network for Blind Mesh Visual Quality Assessment Using 3D Visual Saliency
In this work, we propose a convolutional neural network (CNN) framework to estimate the perceived visual quality of 3D meshes without having access to the reference. The proposed CNN architecture is fed by small patches selected carefully according to their level of saliency. To do so, the visual saliency of the 3D mesh is computed, then we render 2D projections from the 3D mesh and its corresponding 3D saliency map. Afterward, the obtained views are split to obtain 2D small patches that pass through a saliency filter to select the most relevant patches. Experiments are conducted on two MVQ assessment databases, and the results show that the trained CNN achieves good rates in terms of corre…
Assessing movie similarity using a multilayer network model
International audience; This work investigates the movie similarity issue. A multilayer network model capturing various aspects of the story is built from movie scripts. Based on this representation, movies are compared not from summary or actors but using their storyboard. We rely on the "Portrait divergence" to quantify distances between graph characteristics. We illustrate the effectiveness of this approach in comparing movie series.
Influential Spreaders in Modular Networks
International audience; Hassouni (2019). Centrality in Complex Networks with overlapping Community structure. Scientific Reports, 9(1).
Extracting modular-based backbones in weighted networks
Abstract Networks are an adequate representation for modeling and analyzing a great variety of complex systems. However, understanding networks with millions of nodes and billions of connections can be pretty challenging due to memory and time constraints. Therefore, selecting the relevant nodes and edges of these large-scale networks while preserving their core information is a major issue. In most cases, the so-called backbone extraction methods are based either on coarse-graining or filtering approaches. Coarse-graining techniques reduce the network size by gathering similar nodes into super-nodes, while filter-based methods eliminate nodes or edges according to a statistical property.In…
Searching for Influential Nodes in Modular Networks
International audience
Localization of Hubs in Modular Networks
International audience
A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network
International audience; No-reference quality assessment is a challenging issue due to the non-existence of any information related to the reference and the unknown distortion type. The main goal is to design a computational method to objectively predict the human perceived quality of a distorted mesh and deal with the practical situation when the reference is not available. In this work, we design a no reference method that relies on the general regression neural network (GRNN). Our network is trained using the mean curvature which is an important perceptual feature representing the visual aspect of a 3D mesh. Relatively to the human subjective scores, the trained network successfully asses…
Graphes multicouches pour mesurer la similarité entre des films
Un système de recommandation des films propose à ses utilisateurs un ensemble de films similaires à leurs séries préférées, en se basant sur le principe de filtration, par exemple la filtration de leurs données personnelles. Ces dernières années, les réseaux sociaux sont devenus de plus en plus utilisés pour représenter et analyser des histoires de films[1][2][3]. Une étude [6] s'est appuyée sur les réseaux sociaux pour classifier les films par genre. D'autres études [4][5] ont utilisé les réseaux sociaux pour analyser des films à partir des rôles des personnages. A notre connaissance, il n'existe pas une technique qui permet de trouver la similarité entre deux films en calculant la distanc…
Image Segmentation by Deep Community Detection Approach
International audience; To address the problem of segmenting an image into homogeneous communities this paper proposes an efficient algorithm to detect deep communities in the image by maximizing at each stage a new centrality measure, called the local Fiedler vector centrality (LFVC). This measure is associated with the sensitivity of algebraic connectivity to node removals. We show that a greedy node removal strategy, based on iterative maximization of LFVC, has bounded performance loss relative to the optimal, but intractable, combinatorial batch removal strategy. A remarkable feature of this method is the ability to segments the image automatically into homogeneous regions by maximizing…
Centrality in Networks with Overlapping Communities
International audience
On color image quality assessment using natural image statistics
Color distortion can introduce a significant damage in visual quality perception, however, most of existing reduced-reference quality measures are designed for gray scale images. In this paper, we consider a basic extension of well-known image-statistics based quality assessment measures to color images. In order to evaluate the impact of color information on the measures efficiency, two color spaces are investigated: RGB and CIELAB. Results of an extensive evaluation using TID 2013 benchmark demonstrates that significant improvement can be achieved for a great number of distortion type when the CIELAB color representation is used.
Multilayer Network Model of Movie Script
Network models have been increasingly used in the past years to support summarization and analysis of narratives, such as famous TV series, books and news. Inspired by social network analysis, most of these models focus on the characters at play. The network model well captures all characters interactions, giving a broad picture of the narration’s content. A few works went beyond by introducing additional semantic elements, always captured in a single layer network. In contrast, we introduce in this work a multilayer network model to capture more elements of the narration of a movie from its script: people, locations, and other semantic elements. This model enables new measures and insights…
A backbone extraction method for complex weighted networks
International audience
No-Reference 3D Mesh Quality Assessment Based on Dihedral Angles Model and Support Vector Regression
International audience; 3D meshes are subject to various visual distortions during their transmission and geometrical processing. Several works have tried to evaluate the visual quality using either full reference or reduced reference approaches. However, these approaches require the presence of the reference mesh which is not available in such practical situations. In this paper, the main contribution lies in the design of a computational method to automatically predict the perceived mesh quality without reference and without knowing beforehand the distortion type. Following the no-reference (NR) quality assessment principle, the proposed method focuses only on the distorted mesh. Specific…
An Image Segmentation Algorithm based on Community Detection
International audience; With the recent advances in complex networks, image segmentation becomes one of the most appropriate application areas. In this context, we propose in this paper a new perspective of image segmentation by applying two efficient community detection algorithms. By considering regions as communities, these methods can give an over-segmented image that has many small regions. So, the proposed algorithms are improved to automatically merge those neighboring regions agglomerative to achieve the highest modularity/stability. To produce sizable regions and detect homogeneous communities, we use the combination of a feature based on the Histogram of Oriented Gradients of the …
A convolutional neural network framework for blind mesh visual quality assessment
In this paper, we propose a new method for blind mesh visual quality assessment using a deep learning approach. To do this, we first extract visual representative features by computing locally curvature and dihedral angles from each distorted mesh. Then, we determine from these features a set of 2D patches which are learned to a convolutional neural network (CNN). The network consists of two convolutional layers with two max-pooling layers. Then, a multilayer perceptron (MLP) with two fully connected layers is integrated to summarize the learned representation into an output node. With this network structure, feature learning and regression are used to predict the quality score of a given d…
3d mesh denoising using normal based myriad filter
We propose a new filtering scheme for denoising of 3D objects which are represented by a triangular mesh. This scheme consists on applying myriad filter to face normals and then updating the vertices positions in order to preserve the original shape of the object. The choice of the Myriad is justified by the assumption of Cauchy distributed angles between surface normals. This filter improves the performance of a normal-based method which is adapted to the underlying mesh structure. To evaluate these methods of filtering, we use three error metrics. The first is based on the vertices, the second is based on the normals and the third is based on Hausdorff distance. Experimental results demon…
Tetrolet-based reduced reference image quality assessment approach
In this paper, we propose a new reduced reference image quality assessment (RRIQA) scheme. For this purpose, we use a statistical-based method in a new adaptive Haar wavelet transform domain, called Tetrolet. Firstly, we decompose the reference and distorted images and we obtain the Tetrolet coefficients for each image. Secondly, we use a marginal Generalized Gaussian Density (GGD) to model each subband coefficients. Finally, the distortion measure is computed using the Kullback Leibler Divergence (KLD) between GGD Probability density function (PDFs). Experimental results show the efficiency of the proposed method when comparing to those reported in the literature.
k-Truss Decomposition for Modular Centrality
There is currently much interest in identifying influential spreaders in complex networks due to many applications concerned, such as controlling the outbreak of epidemics and conducting advertisements for commercial products, and so on. A plethora of centrality measures have been proposed over the years based on the topological properties of networks. However, most of these classical centrality measures fail to select the most influential nodes in networks with a modular structure despite that it is an omnipresent property in real-world networks. Few authors have introduced centrality measures tailored to networks with community structure. In a recent work, we have shown that, in this case…
A new image segmentation approach using community detection algorithms
Image segmentation has an important role in many image processing applications. Several methods exist for segmenting an image. However, this technique is still a relatively open topic for which various research works are regularly presented. With the recent developments on complex networks theory, image segmentation techniques based on graphs has considerably improved. In this paper, we present a new perspective of image segmentation, by applying three of the most efficient community detection algorithms, Louvain, infomap and stability optimization based on the louvain algorithm, and we extract communities in which the highest modularity feature is achieved. After we show that this measure …
A Robust Blind 3-D Mesh Watermarking Technique Based on SCS Quantization and Mesh Saliency for Copyright Protection
Due to the recent demand of 3-D meshes in a wide range of applications such as video games, medical imaging, film special effect making, computer-aided design (CAD), among others, the necessity of implementing 3-D mesh watermarking schemes aiming to protect copyright has increased in the last decade. Nowadays, the majority of robust 3-D watermarking approaches have mainly focused on the robustness against attacks while the imperceptibility of these techniques is still a serious challenge. In this context, a blind robust 3-D mesh watermarking method based on mesh saliency and scalar Costa scheme (SCS) for Copyright protection is proposed. The watermark is embedded by quantifying the vertex n…
Mesh Visual Quality based on the combination of convolutional neural networks
Blind quality assessment is a challenging issue since the evaluation is done without access to the reference nor any information about the distortion. In this work, we propose an objective blind method for the visual quality assessment of 3D meshes. The method estimates the perceived visual quality using only information from the distorted mesh to feed pre-trained deep convolutional neural networks. The input data is prepared by rendering 2D views from the 3D mesh and the corresponding saliency map. The views are split into small patches of fixed size that are filtered using a saliency threshold. Only the salient patches are selected as input data. After that, three pre-trained deep convolu…
A new weighted normal-based filter for 3D mesh denoising
In this paper, we propose a normal based filtering method for 3D mesh denoising. For this purpose, we compute the new triangle normal vectors by using a weighted sum of the average (smoothness) and the myriad (sharpness) filters in each neighborhood. These weights, that reflect the degree of the surface sharpness, are calculated according to the statistical distribution of the angles between the normal vectors of the triangles. The histogram of the angles between surface normal vectors is accurately fitted by the well known Cauchy distribution. Here, we justify the use of the myriad filter whose estimated value represents the optimum of the location parameter of the investigated distributio…
Extracting Backbones in Weighted Modular Complex Networks
AbstractNetwork science provides effective tools to model and analyze complex systems. However, the increasing size of real-world networks becomes a major hurdle in order to understand their structure and topological features. Therefore, mapping the original network into a smaller one while preserving its information is an important issue. Extracting the so-called backbone of a network is a very challenging problem that is generally handled either by coarse-graining or filter-based methods. Coarse-graining methods reduce the network size by grouping similar nodes, while filter-based methods prune the network by discarding nodes or edges based on a statistical property. In this paper, we pro…
No-reference mesh visual quality assessment via ensemble of convolutional neural networks and compact multi-linear pooling
Abstract Blind or No reference quality evaluation is a challenging issue since it is done without access to the original content. In this work, we propose a method based on deep learning for the mesh visual quality assessment without reference. For a given 3D model, we first compute its mesh saliency. Then, we extract views from the 3D mesh and the corresponding mesh saliency. After that, the views are split into small patches that are filtered using a saliency threshold. Only the salient patches are selected and used as input data. After that, three pre-trained deep convolutional neural networks are employed for feature learning: VGG, AlexNet, and ResNet. Each network is fine-tuned and pro…
A blind mesh visual quality assessment method based on convolutional neural network
International audience
Centrality in Complex Networks with Overlapping Community Structure
AbstractIdentifying influential spreaders in networks is an essential issue in order to prevent epidemic spreading, or to accelerate information diffusion. Several centrality measures take advantage of various network topological properties to quantify the notion of influence. However, the vast majority of works ignore its community structure while it is one of the main features of many real-world networks. In a recent study, we show that the centrality of a node in a network with non-overlapping communities depends on two features: Its local influence on the nodes belonging to its community, and its global influence on the nodes belonging to the other communities. Using global and local co…
Image Quality Assessment Measure Based on Natural Image Statistics in the Tetrolet Domain
This paper deals with a reduced reference (RR) image quality measure based on natural image statistics modeling. For this purpose, Tetrolet transform is used since it provides a convenient way to capture local geometric structures. This transform is applied to both reference and distorted images. Then, Gaussian Scale Mixture (GSM) is proposed to model subbands in order to take account statistical dependencies between tetrolet coefficients. In order to quantify the visual degradation, a measure based on Kullback Leibler Divergence (KLD) is provided. The proposed measure was tested on the Cornell VCL A-57 dataset and compared with other measures according to FR-TV1 VQEG framework.
Mesh Visual Quality Assessment Metrics: A Comparison Study
3D graphics technologies have known a developed progress in the last years, and several processing operations can be applied on 3D meshes such as watermarking, compression, simplification and so forth. Mesh visual quality assessment becomes an important issue to evaluate the visual appearance of the 3D shape after specific modifications. Several metrics have been proposed in this context, from the classical distance-based metrics to the perceptual-based metrics which include perceptual information about the human visual system. In this paper, we propose to study the performance of several mesh visual quality metrics. First, the comparison is conducted regardless the distortion types neither…
Betweenness Centrality for Networks with Non-Overlapping Community Structure
Evaluating the centrality of nodes in complex networks is one of the major research topics being explored due to its wide range of applications. Among the various measures that have been developed over the years, Betweenness centrality is one of the most popular. Indeed, it has proved to be efficient in many real-world situations. In this paper, we propose an extension of the Betweenness centrality designed for networks with nonoverlapping community structure. It is a linear combination of the so-called “local” and “global” Betweenness measures. The Local measure takes into account the influence of a node at the community level while the global measure depends only on the interactions betwe…
Multilayer Network Model of Movie Script
Network models have been increasingly used in the past years to support summarization and analysis of narratives, such as famous TV series, books and news. Inspired by social network analysis, most of these models focus on the characters at play. The network model well captures all characters interactions, giving a broad picture of the narration's content. A few works went beyond by introducing additional semantic elements, always captured in a single layer network. In contrast, we introduce in this work a multilayer network model to capture more elements of the narration of a movie from its script: people, locations, and other semantic elements. This model enables new measures and insights…
Localization of hubs in complex networks with overlapping modular structure
International audience
Interactions between overlapping nodes and hubs in complex networks with modular structure
International audience
Reduced reference 3D mesh quality assessment based on statistical models
International audience; During their geometry processing and transmission 3D meshes are subject to various visual processing operations like compression, watermarking, remeshing, noise addition and so forth. In this context it is indispensable to evaluate the quality of the distorted mesh, we talk here about the mesh visual quality (MVQ) assessment. Several works have tried to evaluate the MVQ using simple geometric measures, However this metrics do not correlate well with the subjective score since they fail to reflect the perceived quality. In this paper we propose a new objective metric to evaluate the visual quality between a mesh with a perfect quality called reference mesh and its dis…
Convolutional Neural Network for Blind Mesh Visual Quality Assessment Using 3D Visual Saliency
International audience
Combination Of Handcrafted And Deep Learning-Based Features For 3d Mesh Quality Assessment
We propose in this paper a novel objective method to evaluate the perceived visual quality of 3D meshes. The proposed method in no-reference, it relies only on the distorted mesh for the quality estimation. It is based on a pre-trained convolutional neural network (i.e VGG to extract features from the distorted mesh) and handcrafted features extracted directly from the 3D mesh (i.e curvature and dihedral angle). A General Regression Neural Network (GRNN) is used to learn the statistical parameters of the feature vectors and estimate the quality score. Experimental results from for subjective databases (LIRIS masking, LIRIS/EPFL generalpurpose, UWB compression and LEETA simplification) and c…
Hybrid blind robust image watermarking technique based on DFT-DCT and Arnold transform
In this paper, a robust blind image watermarking method is proposed for copyright protection of digital images. This hybrid method relies on combining two well-known transforms that are the discrete Fourier transform (DFT) and the discrete cosine transform (DCT). The motivation behind this combination is to enhance the imperceptibility and the robustness. The imperceptibility requirement is achieved by using magnitudes of DFT coefficients while the robustness improvement is ensured by applying DCT to the DFT coefficients magnitude. The watermark is embedded by modifying the coefficients of the middle band of the DCT using a secret key. The security of the proposed method is enhanced by appl…
Color image quality assessment measure using multivariate generalized Gaussian distribution
This paper deals with color image quality assessment in the reduced-reference framework based on natural scenes statistics. In this context, we propose to model the statistics of the steer able pyramid coefficients by a Multivariate Generalized Gaussian distribution (MGGD). This model allows taking into account the high correlation between the components of the RGB color space. For each selected scale and orientation, we extract a parameter matrix from the three color components sub bands. In order to quantify the visual degradation, we use a closed-form of Kullback-Leibler Divergence (KLD) between two MGGDs. Using "TID 2008" benchmark, the proposed measure has been compared with the most i…