scholarly journals A Classification Framework for Large-Scale Face Recognition Systems

2009 ◽  
pp. 337-346 ◽  
Author(s):  
Ziheng Zhou ◽  
Samuel Chindaro ◽  
Farzin Deravi
Keyword(s):  
Face Recognition ◽  
Large Scale ◽  
Classification Framework ◽  
Recognition Systems

scholarly journals Learning Meta Model for Zero- and Few-Shot Face Anti-Spoofing

2020 ◽  
Vol 34 (07) ◽  
pp. 11916-11923 ◽  
Author(s):  
Yunxiao Qin ◽  
Chenxu Zhao ◽  
Xiangyu Zhu ◽  
Zezheng Wang ◽  
Zitong Yu ◽  
...  
Keyword(s):  
Face Recognition ◽  
Supervised Learning ◽  
Large Scale ◽  
Training Data ◽  
Learning Problem ◽  
Meta Model ◽  
Meta Learning ◽  
Recognition Systems

Face anti-spoofing is crucial to the security of face recognition systems. Most previous methods formulate face anti-spoofing as a supervised learning problem to detect various predefined presentation attacks, which need large scale training data to cover as many attacks as possible. However, the trained model is easy to overfit several common attacks and is still vulnerable to unseen attacks. To overcome this challenge, the detector should: 1) learn discriminative features that can generalize to unseen spoofing types from predefined presentation attacks; 2) quickly adapt to new spoofing types by learning from both the predefined attacks and a few examples of the new spoofing types. Therefore, we define face anti-spoofing as a zero- and few-shot learning problem. In this paper, we propose a novel Adaptive Inner-update Meta Face Anti-Spoofing (AIM-FAS) method to tackle this problem through meta-learning. Specifically, AIM-FAS trains a meta-learner focusing on the task of detecting unseen spoofing types by learning from predefined living and spoofing faces and a few examples of new attacks. To assess the proposed approach, we propose several benchmarks for zero- and few-shot FAS. Experiments show its superior performances on the presented benchmarks to existing methods in existing zero-shot FAS protocols.

scholarly journals Discriminative Aging Subspace Learning for Age Estimation

2021 ◽  
Author(s):  
Manisha Sawant ◽  
Kishor Bhurchandi
Keyword(s):  
Factor Analysis ◽  
Face Recognition ◽  
Age Estimation ◽  
Large Scale ◽  
Subspace Learning ◽  
Analysis Model ◽  
Factor Analysis Model ◽  
Age Related ◽  
Age Factor ◽  
Recognition Systems

Abstract Hidden factor analysis ( HFA ) has been widely used in age invariant face recognition systems. It decomposes facial features into independent age factor and identity factor. Age invariant face recognition systems utilize identity factor for face recognition; however, the age factor remains unutilized . The age component of the hidden factor analysis model depends on the subject's age, hence it carries a significant age related information. In this paper, we propose the HFA model based discriminative manifold learning method for age estimation. Further, multiple regression methods are applied on low dimensional features learned from the aging subspace. Extensive experiments are performed on a large scale aging database MORPH II and the accuracy of our method is found superior to the current state-of-the-art methods.

YÜZ TANIMA TABANLI DUYURU SİSTEMİ TASARIMI VE KULLANILABİLİRLİĞİ

2021 ◽  
Vol 8 (16) ◽  
pp. 21-35
Author(s):  
Berk YILMAZER ◽  
Serdar SOLAK
Keyword(s):  
Cloud Computing ◽  
Face Recognition ◽  
Large Scale ◽  
Facial Recognition ◽  
Experimental Studies ◽  
Shopping Mall ◽  
Person Recognition ◽  
Additional Equipment ◽  
Recognition Systems ◽  
The Cost

The rapid developments in technology have an increasing impact and use on biometric person recognition systems. Facial recognition-based systems, one of the biometric person recognition systems, have been widely used in recent years thanks to their easy implementation, fast integration and simple usage as they do not require any additional equipment. Especially the widespread use of computer vision and cloud-computing based applications, smart face recognition systems have become an indispensable part of our lives in recent years. The use of these systems, which have become widespread in security, health, education, military, shopping mall and industrial areas, has increased more during the pandemic period. Institutions and organizations do not want to allocate time and cost to write their own software for face recognition based systems. The services offered by major cloud computing providers can be used to solve this problem. In this context, the article presents a smart announcement system design using cloud computing based face recognition technology. In the past, making an announcement has been seen as a difficult task. It was thought to be a time consuming task, both because of the cost of printing and because all the operations had to be repeated when there were changes in the announcement. Today, signs have left their places to digital screens. It will especially ensure that announcements, warnings, promotions, and notifications are performed effectively at the developed system for large scale institutions, organizations, factories, universities, shopping malls and health institutions. Facial recognition based smart announcement system detects features such as person recognition, gender, and age estimation at a rate of 100% and displays personal announcements according to their priority status. In addition, according to the experimental studies, it was observed that the person recognition and the presentation of the announcements on the screen took an average of 1.3 seconds. According to the announcement system survey, 85% of those who use the system stated that it is useful and user-friendly.

Large scale database face recognition based on region constriction

2013 ◽  
Vol 32 (7) ◽  
pp. 2049-2052
Author(s):  
Chao-you LI ◽  
Ji-zhou SUN
Keyword(s):  
Face Recognition ◽  
Large Scale

scholarly journals PEM-PCA: A Parallel Expectation-Maximization PCA Face Recognition Architecture

2014 ◽  
Vol 2014 ◽  
pp. 1-16 ◽  
Author(s):  
Kanokmon Rujirakul ◽  
Chakchai So-In ◽  
Banchar Arnonkijpanich
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Expectation Maximization ◽  
High Speed ◽  
Expectation Maximization Algorithm ◽  
Parallel Architecture ◽  
Principal Component ◽  
Eigenvalue Decomposition ◽  
Computational Time ◽  
Recognition Systems

Principal component analysis or PCA has been traditionally used as one of the feature extraction techniques in face recognition systems yielding high accuracy when requiring a small number of features. However, the covariance matrix and eigenvalue decomposition stages cause high computational complexity, especially for a large database. Thus, this research presents an alternative approach utilizing an Expectation-Maximization algorithm to reduce the determinant matrix manipulation resulting in the reduction of the stages’ complexity. To improve the computational time, a novel parallel architecture was employed to utilize the benefits of parallelization of matrix computation during feature extraction and classification stages including parallel preprocessing, and their combinations, so-called a Parallel Expectation-Maximization PCA architecture. Comparing to a traditional PCA and its derivatives, the results indicate lower complexity with an insignificant difference in recognition precision leading to high speed face recognition systems, that is, the speed-up over nine and three times over PCA and Parallel PCA.

Sign in / Sign up

Export Citation Format

Share Document