Personal Identification System using Hand Geometry and Iris Pattern Fusion

2006 ◽  
Author(s):  
Nongluk Covavisaruch ◽  
Pipat Prateepamornkul
Keyword(s):  
Personal Identification ◽  
Identification System ◽  
Hand Geometry

scholarly journals FPGA Implementation for GMM-Based Speaker Identification

2011 ◽  
Vol 2011 ◽  
pp. 1-8 ◽  
Author(s):  
Phaklen EhKan ◽  
Timothy Allen ◽  
Steven F. Quigley
Keyword(s):  
Vocal Tract ◽  
Speaker Identification ◽  
Hardware Acceleration ◽  
Statistical Modelling ◽  
Gaussian Mixture ◽  
Personal Identification ◽  
Identification System ◽  
Call Centre ◽  
Mel Frequency Cepstral Coefficients ◽  
High Level

In today's society, highly accurate personal identification systems are required. Passwords or pin numbers can be forgotten or forged and are no longer considered to offer a high level of security. The use of biological features, biometrics, is becoming widely accepted as the next level for security systems. Biometric-based speaker identification is a method of identifying persons from their voice. Speaker-specific characteristics exist in speech signals due to different speakers having different resonances of the vocal tract. These differences can be exploited by extracting feature vectors such as Mel-Frequency Cepstral Coefficients (MFCCs) from the speech signal. A well-known statistical modelling process, the Gaussian Mixture Model (GMM), then models the distribution of each speaker's MFCCs in a multidimensional acoustic space. The GMM-based speaker identification system has features that make it promising for hardware acceleration. This paper describes the hardware implementation for classification of a text-independent GMM-based speaker identification system. The aim was to produce a system that can perform simultaneous identification of large numbers of voice streams in real time. This has important potential applications in security and in automated call centre applications. A speedup factor of ninety was achieved compared to a software implementation on a standard PC.

scholarly journals Who_Is : Identification system of human faces

2002 ◽  
Vol Volume 1, 2002 ◽  
Author(s):  
Mohamed Tayeb Laskri ◽  
Djallel Chefrour
Keyword(s):  
Face Recognition ◽  
Geometric Model ◽  
Personal Identification ◽  
Identification System ◽  
K Nearest Neighbors ◽  
City Block ◽  
The Face ◽  
Characteristic Points ◽  
The Individual ◽  
Application Fields

International audience Although human face recognition is a hard topic due to many parameters involved (e.g. variability of the position, lighting, hairstyle, existence of glasses, beard, moustaches, wrinkles...), it becomes of increasing interest in numerous application fields (personal identification, video watch, man machine interfaces...). In this work, we present WHO_IS, a system for person identification based on face recognition. A geometric model of the face is definedfrom a set of characteristic points which are extracted from the face image. The identification consists in calculating the K nearest neighbors of the individual test by using the City-Block distance. The system is tested on a sample of 100 people with a success rate of 86 %. Bien que la reconnaissance des visages humains soit un domaine difficile à cause de la multitude des paramètres qu'il faut prendre en compte (variation de posture, éclairage, style de coiffure, port de lunettes, de barbes, de moustaches, vieillesse…), il est très important de s'en intéresser vu les nombreux champs d'applications (vérification de personnes, télésurveillance, interfaces homme-machine …). Dans ce travail nous présentons la mise en œuvre de WHO_IS, un système d'identification de personnes par reconnaissance des visages humains. Nous avons développé un modèle géométrique du visage basé sur un ensemble de points caractéristiques extraits à partir de l'image du visage. La procédure d'identification consiste à calculer les K plus proches voisins de l'individu test dans le sens de la distance City-Block. Le système WHO_IS a été testé sur un échantillon de 100 personnes. Un taux de reconnaissance correcte de 86% a été obtenu

Sign in / Sign up

Export Citation Format

Share Document