Showing papers by "Christine Fernandez-Maloigne published in 2019"

Toward Content-Based Hyperspectral Remote Sensing Image Retrieval (CB-HRSIR): A Preliminary Study Based on Spectral Sensitivity Functions

Abstract: With the emergence of huge volumes of high-resolution Hyperspectral Images (HSI) produced by different types of imaging sensors, analyzing and retrieving these images require effective image description and quantification techniques. Compared to remote sensing RGB images, HSI data contain hundreds of spectral bands (varying from the visible to the infrared ranges) allowing profile materials and organisms that only hyperspectral sensors can provide. In this article, we study the importance of spectral sensitivity functions in constructing discriminative representation of hyperspectral images. The main goal of such representation is to improve image content recognition by focusing the processing on only the most relevant spectral channels. The underlying hypothesis is that for a given category, the content of each image is better extracted through a specific set of spectral sensitivity functions. Those spectral sensitivity functions are evaluated in a Content-Based Image Retrieval (CBIR) framework. In this work, we propose a new HSI dataset for the remote sensing community, specifically designed for Hyperspectral remote sensing retrieval and classification. Exhaustive experiments have been conducted on this dataset and on a literature dataset. Obtained retrieval results prove that the physical measurements and optical properties of the scene contained in the HSI contribute in an accurate image content description than the information provided by the RGB image presentation.

A Survey of Stereoscopic 3D Just Noticeable Difference Models

Abstract: Just noticeable difference (JND) for stereoscopic 3D content reflects the maximum tolerable distortion; it corresponds to the visibility threshold of the asymmetric distortions in the left and right contents. The 3D-JND models can be used to improve the efficiency of the 3D compression or the 3D quality assessment. Compared to 2D-JND models, the 3D-JND models appeared recently and the related literature is rather limited. In this paper, we give a deep and comprehensive study of the pixel-based 3D-JND models. To our best knowledge, this is the first review on 3D-JND models. Each model is briefly described by giving its rationale and main components in addition to providing exhaustive information about the targeted application, the pros, and cons. Moreover, we present the characteristics of the human visual system presented in these models. In addition, we analyze and compare the 3D-JND models thoroughly using qualitative and quantitative performance evaluation based on Middlebury stereo datasets. Besides, we measure the JND thresholds of the asymmetric distortion based on psychophysical experiments and compare these experimental results to the estimates from the 3D-JND models in order to evaluate the accuracy of each model.

Improving Robustness of Image Tampering Detection for Compression

Abstract: The task of verifying the originality and authenticity of images puts numerous constraints on tampering detection algorithms. Since most images are acquired on the internet, there is a significant probability that they have undergone transformations such as compression, noising, resizing and/or filtering, both before and after the possible alteration. Therefore, it is essential to improve the robustness of tampered image detection algorithms for such manipulations. As compression is the most common type of post-processing, we propose in our work a robust framework against this particular transformation. Our experiments on benchmark datasets show the contribution of our proposal for camera model identification and image tampering detection compared to recent literature approaches.

Recent advances in Glioma grade classification using machine and deep learning on MR data

Abstract: Glioma grade classification based on Magnetic Resonance (MR) data and using Machine Learning approaches is a hot topic. Recently, considerable improvements have been made in this field especially in the last two years. This paper reviews a selection of the most recent methods from 2018 and 2019, details their preprocessing and priors, such as the different modalities used in their datasets. It then groups the different approaches by comparing their different learning scheme. While classical machine learning is present, more and more authors are using Convolutional Neural Networks. Multimodal MR sequencing, such as perfusion imaging, diffusion imaging or MR spectroscopy, gives an interesting diversity of information. Works using these modalities often reach an interesting accuracy level in classification.

ADC Maps Texture Analysis for the Evaluation of Kidney Function: A Preliminary Study *

Abstract: Assessment of renal microstructure and function non-invasively, has an important role in monitoring and predicting chronic kidney disease (CKD). The goal of this study is to differentiate healthy and CKD patients using texture analysis. Apparent diffusion coefficient (ADC) maps were generated from diffusion weighted magnetic resonance images (DWI), from which statistical and wavelet-transform based texture parameters were extracted. The results of this preliminary study indicated that chronic kidney disease affects texture parameters. The correlation and the energy of wavelet coefficient in “low-high” energy components in the third wavelet decomposition level were found to be the best textural predictors of kidney dysfunction.

Gradient in spectral and color images: from the Di Zenzo initial construction to a generic proposition

Abstract: In this article, we define a generic gradient for color and spectral images, considering a proposed taxonomy of the state of the art. A full-vector gradient, taking into account the sensor's characteristics, is in compliance with the metrological properties of genericity, robustness, and reproducibility. Here, we construct a protocol to compare gradients from different sensors. The comparison is developed by simulating sensors using their spectral characteristics. We develop three experiments using this protocol. The first experiment shows the consistency of results for similar sensors; the second demonstrates the genericity of the approach, adapted to any kind of imaging sensors; and the third focuses on the channel inter-correlation considering sensors such as in the color vision deficiency case.

Full-Vector Gradient for Multi-Spectral or Multivariate Images

Abstract: Gradient extraction is important for a lot of metrological applications, such as control quality by vision. In this paper, we propose a full-vector gradient for multi-spectral sensors. The full-vector gradient extends Di Zenzo expression to take into account the non-orthogonality of the acquisition channels thanks to a Gram matrix. This expression is generic and independent from channel count. Results are provided for a color and a multi-spectral snapshot sensor. Then, we show the accuracy improvement of the gradient calculation by creating a dedicated objective test and from real images.

A Metrological Framework For Hyperspectral Texture Analysis Using Relative Spectral Difference Occurrence Matrix

Abstract: A new hyperspectral texture descriptor, Relative Spectral Difference Occurrence Matrix (RSDOM) is proposed. Developed in a metrological framework, it simultaneously considers the distribution of spectra and their spatial arrangement in the hyperspectral image. It is generic and adapted for any number of spectral band or range. As validation, a texture classification scheme is applied on HyTexiLa dataset using RSDOM. The obtained accuracy is excellent (95.6%), comparable to Opponent Band Local Binary Pattern (OBLBP) but at a much-reduced feature size (0.1% of OBLBP’s).

L’intelligence artificielle au service de l’imagerie et de la santé des femmes

Abstract: Resume Les approches d’apprentissage automatique ont recemment gagne en popularite et de nombreux travaux actuels tendent a utiliser les reseaux de neurones convolutifs pour concevoir un systeme de prediction et de diagnostic medical. Des resultats tres interessants ont ainsi ete produits en 2017 et 2018 pour les pathologies retiniennes, pulmonaires, cardiaques, abdominales, musculosquelettiques. Cet article se propose de decrire les concepts de base de l’apprentissage profond, de faire un court etat de l’art des methodes les plus recentes en imagerie medicale et de montrer en quoi il peut etre pertinent pour l’imagerie de la femme, en particulier dans le depistage du cancer du sein. Nous conclurons sur certaines difficultes et les nouveaux defis pour la sante, introduits par l’apprentissage machine.

Stability of the metrological texture feature using colour contrast occurrence matrix

Abstract: Texture discrimination was studied a lot for texture classification/recognition in image databases, but less under the metrological point of view. In this work, we focused on the metrological behaviour related to the human vision for Control Quality purposes. Inside this study, we introduce as a pair a novel texture feature associated to an adapted similarity measure. The main idea was to define a compact representation adapted from the human visual characteristics in order to obtain an accurate description of the texture. Combined to an adapted similarity measure, the obtained pair feature/similarity becomes highly efficient. Performance Classification of the proposed texture feature is assessed on six popular and challenging databases used to provide the reference results in the state-of-the-art. Obtained results show the efficiency and the robustness of the proposed pair feature/similarity measure defined by the relocated Colour Contrast Occurrence Matrix.

Just Noticeable Difference Model for Asymmetrically Distorted Stereoscopic Images

Abstract: In this paper, we propose a saliency-weighted stereoscopic JND (SSJND) model constructed based on psychophysical experiments, accounting for binocular disparity and spatial masking effects of the human visual system (HVS). Specifically, a disparity-aware binocular JND model is first developed using psychophysical data, and then is employed to estimate the JND threshold for non-occluded pixel (NOP). In addition, to derive a reliable 3D-JND prediction, we determine the visibility threshold for occluded pixel (OP) by including a robust 2D-JND model. Finally, SSJND thresholds of one view are obtained by weighting the resulting JND for NOP and OP with their visual saliency. Based on subjective experiments, we demonstrate that the proposed model outperforms the other 3D-JND models in terms of perceptual quality at the same noise level.

Detection of Image Splicing using Illuminant Color Estimation

Abstract: Digital image forensics is a set of techniques used for digital image forgery detection and is widely used to certify the content or the authenticity of a document. The splicing operation, which crops and pastes one or several regions from separate images, is a common technique used for image forgery. In the literature, most image forgery detection techniques are based on machine learning. Only a few methods take advantage of physical features to detect the tampering. In this paper, we propose a new method to detect image splicing from an analysis of regions of interest in the uv chromaticity space. Their pixels are compared to the Planckian locus and the closest ones, seen as achromatic, are stored in a weighted histogram depicting Gaussian distribution. After a selection of the suitable Gaussians, the illuminant color is estimated. Results on spiced images are presented and discussed.

Classical optics in France: introduction.

Abstract: This special issue of the Journal of the Optical Society of America A (JOSA A) is devoted to the wide array of French researchers from universities and state research organisms, offering them the opportunity to share and showcase their current research in the fields of optics and imaging sciences to the global community.

A Metrological Measurement of Texture in Hyperspectral Images Using Relocated Spectral Difference Occurrence Matrix

Abstract: A new hyperspectral texture descriptor, Relocated Spectral Difference Occurrence Matrix (rSDOM) is proposed. It assesses the distribution of spectral difference in a given neighborhood. For metrological purposes, rSDOM employs Kullback-Leibler pseudo-divergence (KLPD) for spectral difference calculation. It is generic and adapted for any spectral range and number of band. As validation, a texture classification scheme based on nearest neighbor classifier is applied on HyTexiLa dataset using rSDOM. The performance is close to Opponent Band Local Binary Pattern (OBLBP) with classification accuracy of 94.7%, but at a much-reduced feature size (0.24% of OBLBP’s) and computational complexity.

Blind Image Quality Assessment Based on the Use of Saliency Maps and a Multivariate Gaussian Distribution

Abstract: With the widespread use of image processing technologies, objective image quality metrics are a fundamental and challenging problem. In this paper, we present a new No-Reference Image Quality Assessment (NR-IQA) algorithm based on visual attention modeling and a multivariate Gaussian distribution to predict the final quality score from the extracted features. Computational modeling of visual attention is performed to compute saliency maps at three resolution levels. At each level, distortions of the input image are extracted and weighted by the saliency maps in order to highlight degradations of visually attracting regions. The generated features are used by a probabilistic model to predict the final quality score. Experimental results demonstrate the effectiveness of the metric and show better performance when compared to well known NR-IQA algorithms.

New Journal prize to recognize the best paper from an emerging researcher: editorial.

Abstract: Editor-in-Chief P. Scott Carney and Deputy Editor Christine Fernandez-Maloigne introduce a new prize for the best paper published by an emerging researcher in the Journal in 2018.