Search results for "Computer Vision and Pattern Recognition"

Modified total variation regularization using fuzzy complement for image denoising

2015

In this paper, we propose a denoising algorithm based on the Total Variation (TV) model. Specifically, we associate to the regularization term of the Rodin-Osher-Fatimi (ROF) functional a small weight whenever denoising is performed in edge and texture regions, which means less regularization and more details preservation. On the other hand, a large weight is associated if the region being filtered is smooth which means noise will be well suppressed. The weight computation is inspired from the fuzzy edge complement. Experiments on well-known images and comparison with state of the art denoising algorithms demonstrate that the proposed method not only presents good denoising performance but …

A fully automatic method for biological target volume segmentation of brain metastases

2016

Leksell Gamma Knife is a mini-invasive technique to obtain a complete destruction of cerebral lesions delivering a single high dose radiation beam. Positron Emission Tomography (PET) imaging is increasingly utilized for radiation treatment planning. Nevertheless, lesion volume delineation in PET datasets is challenging because of the low spatial resolution and high noise level of PET images. Nowadays, the biological target volume (BTV) is manually contoured on PET studies. This procedure is time expensive and operator-dependent. In this article, a fully automatic algorithm for the BTV delineation based on random walks (RW) on graphs is proposed. The results are compared with the outcomes of…

Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection

2016

International audience; This paper addresses the problem of automatic classification of Spectral Domain OCT (SD-OCT) data for automatic identification of patients with Diabetic Macular Edema (DME) versus normal subjects. Optical Coherence Tomography (OCT) has been a valuable diagnostic tool for DME, which is among the most common causes of irreversible vision loss in individuals with diabetes. Here, a classification framework with five distinctive steps is proposed and we present an extensive study of each step. Our method considers combination of various pre-processings in conjunction with Local Binary Patterns (LBP) features and different mapping strategies. Using linear and non-linear cl…

Early warning thresholds for partially saturated slopes in volcanic ashes

2013

Rainfall-induced landslides in steep soil slopes of volcanic origin are a major threat to human lives and infrastructure. In the context of constructing early warning systems in regions where extensive data on landslide occurrences and associated rainfall are inexistent, physically-based tools offer the possibility to establish thresholds for measurable field quantities. In this paper, a combined finite element infinite slope model is presented to study the transient hydraulic response of volcanic ash slopes to a series of rainfall events and to estimate seasonal safety factors. Furthermore, analytical considerations of partially saturated infinite slopes are made to define capillary stress…

Contributions à la Vision par Ordinateur pour les Systèmes en Lumière Structurée et les Systèmes Catadioptriques

2008

Mes travaux de recherche concernent essentiellement la vision par ordinateur, ou vision artificielle. Basiquement, je me suis efforcé d'imaginer des dispositifs, d'étudier des algorithmes, d'intégrer des méthodes et techniques connues dans des méthodologies nouvelles, de développer çà et là des aspects théoriques originaux. Je me suis beaucoup intéressé à des systèmes de vision alternatifs comme les systèmes en lumière structurée ou catadioptriques. Ces systèmes permettent d'étudier les techniques usuelles de vision par ordinateur sous un éclairage différent, ils nous obligent à ajuster le problème aux caractéristiques qui leur sont propres ; ils permettent, en quelq…

Time Unification on Local Binary Patterns Three Orthogonal Planes for Facial Expression Recognition

2019

International audience; Machine learning has known a tremendous growth within the last years, and lately, thanks to that, some computer vision algorithms started to access what is difficult or even impossible to perceive by the human eye. While deep learning based computer vision algorithms have made themselves more and more present in the recent years, more classical feature extraction methods, such as the ones based on Local Binary Patterns (LBP), still present a non negligible interest, especially when dealing with small datasets. Furthermore, this operator has proven to be quite useful for facial emotions and human gestures recognition in general. Micro-Expression (ME) classification is…

Restoration and Enhancement of Historical Stereo Photos

2021

Restoration of digital visual media acquired from repositories of historical photographic and cinematographic material is of key importance for the preservation, study and transmission of the legacy of past cultures to the coming generations. In this paper, a fully automatic approach to the digital restoration of historical stereo photographs is proposed, referred to as Stacked Median Restoration plus (SMR+). The approach exploits the content redundancy in stereo pairs for detecting and fixing scratches, dust, dirt spots and many other defects in the original images, as well as improving contrast and illumination. This is done by estimating the optical flow between the images, and using it …

Semi-blind Source Extraction Methods: Application to the measurement of non-contact physiological signs

2018

Non-contact physiological measurements are highlydesirable in many biomedical fields such asdiagnosis of infants, geriartic patients, patients withextreme physical trauma, and fitness and well-being.Remote photoplethysmography is increasingly beingused for non-contact measurement of heart rate fromvideos which is one of the most common biomedicalproperty required for most medical diagnosis. Oneof the common techniques for performing remotephotoplethysmography involves using Blind SourceSeparation (BSS) methods to extract the cardiacsignal from video data.In this context, the objective of this thesis is todevelop different methods in the field of extractionand separation of sources by improv…

Editorial:Governance AI ethics

2022

Large-scale nonlinear dimensionality reduction for network intrusion detection

2017

International audience; Network intrusion detection (NID) is a complex classification problem. In this paper, we combine classification with recent and scalable nonlinear dimensionality reduction (NLDR) methods. Classification and DR are not necessarily adversarial, provided adequate cluster magnification occurring in NLDR methods like $t$-SNE: DR mitigates the curse of dimensionality, while cluster magnification can maintain class separability. We demonstrate experimentally the effectiveness of the approach by analyzing and comparing results on the big KDD99 dataset, using both NLDR quality assessment and classification rate for SVMs and random forests. Since data involves features of mixe…