A5105892318- Face recognition and analysis
- Medical Image Segmentation Techniques
- Speech and Audio Processing
- Advanced MEMS and NEMS Technologies
- Dental Radiography and Imaging
- Remote-Sensing Image Classification
- Image Retrieval and Classification Techniques
- Advanced Vision and Imaging
- Video Surveillance and Tracking Methods
- Sensor Technology and Measurement Systems
- Geochemistry and Geologic Mapping
- Advanced Sensor Technologies Research
- Medical Imaging and Analysis
- Hand Gesture Recognition Systems
- Face and Expression Recognition
- 3D Shape Modeling and Analysis
- Acoustic Wave Resonator Technologies
- Oral microbiology and periodontitis research
- Oral and Maxillofacial Pathology
- Speech Recognition and Synthesis
- Computer Graphics and Visualization Techniques
- IoT and GPS-based Vehicle Safety Systems
- Music and Audio Processing
- Advanced Image Fusion Techniques
- dental development and anomalies
Digital Research Centre of Sfax
2023-2025
University of Gafsa
2025
University of Sfax
2011-2015
Centre National de la Recherche Scientifique
2010-2011
Université de Montpellier
2011
Laboratoire d'Informatique, de Robotique et de Microélectronique de Montpellier
2011
Centre de Recherche en Automatique de Nancy
2010
Université du littoral côte d'opale
2006
Lipreading involves recognizing spoken words by analyzing the movements of lips and surrounding area using visual data. It is an emerging research topic with many potential applications, such as human–machine interaction enhancing audio-based speech recognition. Recent deep learning approaches integrate features from mouth region lip contours. However, simple methods concatenation may not effectively optimize feature vector. In this article, we propose extracting optimal 3D convolution...
Abstract Objectives The shape is commonly used to describe the objects. State-of-the-art algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models used. This seen growing popularity of ShapeNet (51,300 models) Princeton ModelNet (127,915 models). However, a large collection anatomical shapes (e.g., bones, organs, vessels) 3D surgical instruments missing. Methods We present MedShapeNet translate...
Teeth segmentation and labeling are critical components of Computer-Aided Dentistry (CAD) systems. Indeed, before any orthodontic or prosthetic treatment planning, a CAD system needs to first accurately segment label each instance teeth visible in the 3D dental scan, this is avoid time-consuming manual adjustments by dentist. Nevertheless, developing such an automated accurate tool very challenging, especially given lack publicly available datasets benchmarks. This article introduces public...
Prior to the deep learning era, shape was commonly used describe objects. Nowadays, state-of-the-art (SOTA) algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models used. This is seen numerous shape-related publications premier vision conferences as well growing popularity of ShapeNet (about 51,300 models) Princeton ModelNet (127,915 models). For domain, we present a large collection anatomical shapes...
Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due variations anatomy, imaging protocols, limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg'22 challenge was organized conjunction with International...
The increasing availability of satellite images acquired periodically by on different area, makes it extremely interesting in many applications. In deed, the recent construction multi and hyper spectral will provide detailed data with information both spatial domain. This shows great promise for remote sensing applications ranging from environmental agricultural to national security interests. exploitation these requires use approach, notably founded unsupervised statistical segmentation...
In this paper, we propose an alternate electrical-only strategy to perform both test and calibration of MEMS convective accelerometers' sensitivity. The idea is calibrate device sensitivity through the adjustment power dissipated in heater element. For this, system equipped with on-chip programmable digital pulse modulated generator iterative search procedure based on simple impedance measurements implemented. method evaluated Monte-Carlo simulations considering typical process variations...
Video-endoscopy is the standard clinical procedure for visual exploration of internal walls hollow organs. For bladder, lesion diagnosis complex because endoscopic images are bi-dimensional and cover only small bladder areas. 3D endoscopes, based on stereoscopic active vision principles, were recently proposed validated. This paper presents a reconstruction algorithm using 2D texture few points located wall surfaces provided by such endoscopes. The constructs panoramic surface method guided...
This paper presents a new method for 3D face pose tracking in arbitrary illumination change conditions using color image and depth data acquired by RGB-D cameras (e.g., Microsoft Kinect, Asus Xtion Pro Live, etc.). The is based on an optimization process of objective function combining photometric geometric energy. energy computed from while the at each frame comparing current texture to its corresponding reference defined first frame. To handle effect changing lighting condition, we use...
Lipreading involves using visual data to recognize spoken words by analyzing the movements of lips and surrounding area. It is a hot research topic with many potential applications, such as human-machine interaction enhancing audio speech recognition. Recent deep-learning based works aim integrate features extracted from mouth region landmark points on lip contours. However, employing simple combination method concatenation may not be most effective approach get optimal feature vector. To...