A5089464212- Face recognition and analysis
- Biometric Identification and Security
- Face and Expression Recognition
- Advanced Image and Video Retrieval Techniques
- Spectroscopy Techniques in Biomedical and Chemical Research
- Video Surveillance and Tracking Methods
- Digital Media Forensic Detection
- Generative Adversarial Networks and Image Synthesis
- User Authentication and Security Systems
- Sleep and Work-Related Fatigue
- Infant Health and Development
- Energy Efficient Wireless Sensor Networks
- Gait Recognition and Analysis
- Respiratory and Cough-Related Research
- Infrastructure Maintenance and Monitoring
- Machine Learning and ELM
- Phonocardiography and Auscultation Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Biosensors and Analytical Detection
- Image Retrieval and Classification Techniques
- Indoor and Outdoor Localization Technologies
- Handwritten Text Recognition Techniques
- Spectroscopy and Chemometric Analyses
- Advanced Neural Network Applications
- Forensic and Genetic Research
University of Ouargla
2015-2024
Université Polytechnique Hauts-de-France
2024
Université de Lille
2024
Centre National de la Recherche Scientifique
2024
Institut d'électronique de microélectronique et de nanotechnologie
2024
University of Oulu
2022
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 evaluate and compare the generalization performances mobile PAD techniques under some real-world variations, including unseen input sensors, instruments (PAI) illumination conditions, on larger scale OULU-NPU dataset using its standard evaluation protocols...
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 their high recognition accuracy and capability adapt with different acquisition images. However, high-dimensional data a large number of uncorrelated redundant features remain challenge computational complexity issues. Feature selection is process selecting subset relevant features, which aims decrease dimensionality,...
Facial demographic classification is an attractive topic in computer vision. Attributes such as age and gender can be used many real life application face recognition internet safety for minors. In this paper, we present a novel approach estimation under uncontrolled conditions following the standard protocols fair comparaison. Our proposed based on Multi Level Local Phase Quantization (ML-LPQ) features which are extracted from normalized images. Two different Support Vector Machines (SVM)...
Currently, face recognition technology is the most widely used method for verifying an individual's identity. Nevertheless, it has increased in popularity, raising concerns about presentation attacks, which a photo or video of authorized person's to obtain access services. Based on combination background subtraction (BS) and convolutional neural network(s) (CNN), as well ensemble classifiers, we propose efficient more robust attack detection algorithm. This algorithm includes fully connected...
Over the last decade, world has witnessed many breakthroughs in artificial intelligence, largely due to advances deep learning technology. Notably, computer vision solutions have significantly contributed these achievements. Human face analysis, a core area of vision, gained considerable attention its wide applicability fields such as law enforcement, social media, and marketing. However, existing methods for facial age estimation often struggle with accuracy limited feature extraction...
Clustering is inherently a process of exploratory data analysis. It has attracted more attention recently because much real-world consists multiple representations or views. However, it becomes increasingly problematic when dealing with large and heterogeneous data. worth noting that several approaches have been developed to increase computational efficiency, although most them some drawbacks: 1) Most existing techniques consider equal static weights quantify importance across different...
Todays biometric systems are vulnerable to spoof attacks made by non-real faces. The problem is when a person shows in front of camera print photo or picture from cell phone. We study this paper an anti-spoofing solution for distinguishing between 'live' and 'fake' In our approach we used overlapping block LBP operator extract features each region the image. To reduce Fisher-Score. Finally, nonlinear Support Vector Machine (SVM) classifier with kernel function determining whether input image...
Due to advances in technology, today’s biometric systems become vulnerable spoof attacks made by fake faces. These occur when an intruder attempts fool established face-based recognition system presenting a face (e.g., print photo or replay attacks) front of the camera instead intruder’s genuine face. For this purpose, antispoofing has hot topic analysis literature, where several applications with task have emerged recently. We propose solution for distinguishing between real faces and ones....
Human face aging is irreversible process causing changes in human characteristics such us hair whitening, muscles drop and wrinkles. Due to the importance of biometrics systems, age estimation became an attractive area for researchers. This paper presents a novel method estimate from images, using binarized statistical image features (BSIF) local binary patterns (LBP)histograms as performed by support vector regression (SVR) kernel ridge (KRR). We applied our on FG-NET PAL datasets. Our...
Biometric technology has become essential in our daily life. In such a biometric system, personal identification is based on behavioral or biological characteristics. Recently, the trait of Finger-Knuckle-Print (FKP) used due to its ease use and low cost. order develop an efficient recognition system these images, we propose deep learning method where own Convolutional Neural Network (CNN) identify persons. Excellent results were conducted with unimodal multimodal systems.
Currently, face recognition technologies are the most widely used methods for verifying 1an individual’s identity. Nevertheless, it has increased in popularity, raising concerns about spoofing attacks, which a photo or video of an authorized person’s is to get access services. Based on combination Background Subtraction (BS) and Convolutional Neural Networks (CNN), as well ensemble classifiers, we propose efficient more robust spoof detection algorithm. This algorithm...
The detection and quantification of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) virus particles in ambient waters using a membrane-based in-gel loop-mediated isothermal amplification (mgLAMP) method can play an important role large-scale environmental surveillance for early warning potential outbreaks. However, counting or cells fluorescence microscopy is expensive, time-consuming, tedious task that only highly trained technicians researchers perform. Although such objects...
Recently, 3D palmprint recognition systems have started to gain the attention of researchers compared their 2D counterpart. The key task in design a biometric identification system is choice method extracting discriminating information from 2D/3D images. Given enormous success deep learning approaches field feature extraction and classification, we propose this paper use Transfer networks order build based person system. Also, aims show efficiency selection improve performance. To do this,...
1. Pramono RX, Imtiaz SA, Rodriguez-Villegas E. Automatic cough detection in acoustic signal using spectral features. In2019 41st Annual International Conference of the IEEE Engineering Medicine and Biology Society (EMBC) 2019:7153-7156. https://doi.org/10.1109/EMBC.2.... CrossRef Google Scholar
In nearest past years object detection techniques becomes the magic key to solving several problems in computer vision, this work, we introduce our enhanced YOLO v5 detector for detecting SNCF (National Society of France Railroad) workers railway environment. Our contribution work is presented by creating a new dataset about use training model and improving reducing number its parameters where reduce classes layers only one class, that ensure augment speed increase accuracy detector....