scholarly journals Reconstructed Error and Linear Representation Coefficients Restricted by l1-Minimization for Face Recognition under Different Illumination and Occlusion

2017 ◽  
Vol 2017 ◽  
pp. 1-16 ◽  
Author(s):  
Xuegang Wu ◽  
Bin Fang ◽  
Yuan Yan Tang ◽  
Xiaoping Zeng ◽  
Changyuan Xing
Keyword(s):  
Face Recognition ◽  
Linear Combination ◽  
High Performance ◽  
Linear Subspace ◽  
Linear Representation ◽  
Optimization Method ◽  
Reconstruction Error ◽  
Equivalent Transformation ◽  
L1 Minimization ◽  
Human Faces

The problem of recognizing human faces from frontal views with varying illumination, occlusion, and disguise is a great challenge to pattern recognition. A general knowledge is that face patterns from an objective set sit on a linear subspace. On the proof of the knowledge, some methods use the linear combination to represent a sample in face recognition. In this paper, in order to get the more discriminant information of reconstruction error, we constrain both the linear combination coefficients and the reconstruction error by l1-minimization which is not apt to be disturbed by outliners. Then, through an equivalent transformation of the model, it is convenient to compute the parameters in a new underdetermined linear system. Next, we use an optimization method to get the approximate solution. As a result, the minimum reconstruction error has contained much valuable discriminating information. The gradient of this variable is measured to decide the final recognition. The experiments show that the recognition protocol based on the reconstruction error achieves high performance on available databases (Extended Yale B and AR Face database).

scholarly journals A Collaborative Neighbor Representation Based Face Recognition Algorithm

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Zhengming Li ◽  
Qi Zhu ◽  
Binglei Xie ◽  
Jian Cao ◽  
Jin Zhang
Keyword(s):  
Face Recognition ◽  
Linear Combination ◽  
Test Sample ◽  
Reconstruction Error ◽  
Recognition Algorithm ◽  
Second Phase ◽  
Two Phase ◽  
Alternative Scheme ◽  
Training Samples ◽  
Discrimination Information

We propose a new collaborative neighbor representation algorithm for face recognition based on a revised regularized reconstruction error (RRRE), called the two-phase collaborative neighbor representation algorithm (TCNR). Specifically, the RRRE is the division of  l2-norm of reconstruction error of each class into a linear combination of  l2-norm of reconstruction coefficients of each class, which can be used to increase the discrimination information for classification. The algorithm is as follows: in the first phase, the test sample is represented as a linear combination of all the training samples by incorporating the neighbor information into the objective function. In the second phase, we use thekclasses to represent the test sample and calculate the collaborative neighbor representation coefficients. TCNR not only can preserve locality and similarity information of sparse coding but also can eliminate the side effect on the classification decision of the class that is far from the test sample. Moreover, the rationale and alternative scheme of TCNR are given. The experimental results show that TCNR algorithm achieves better performance than seven previous algorithms.

High-Performance Image Filters via Sparse Approximations

2020 ◽  
Vol 3 (2) ◽  
pp. 1-19
Author(s):  
Kersten Schuster ◽  
Philip Trettner ◽  
Leif Kobbelt
Keyword(s):  
High Performance ◽  
Hardware Acceleration ◽  
Optimization Method ◽  
Translation Invariant ◽  
Approximation Quality ◽  
Trade Offs ◽  
Sparse Approximations ◽  
Image Filters ◽  
Good Trade ◽  
And Performance

We present a numerical optimization method to find highly efficient (sparse) approximations for convolutional image filters. Using a modified parallel tempering approach, we solve a constrained optimization that maximizes approximation quality while strictly staying within a user-prescribed performance budget. The results are multi-pass filters where each pass computes a weighted sum of bilinearly interpolated sparse image samples, exploiting hardware acceleration on the GPU. We systematically decompose the target filter into a series of sparse convolutions, trying to find good trade-offs between approximation quality and performance. Since our sparse filters are linear and translation-invariant, they do not exhibit the aliasing and temporal coherence issues that often appear in filters working on image pyramids. We show several applications, ranging from simple Gaussian or box blurs to the emulation of sophisticated Bokeh effects with user-provided masks. Our filters achieve high performance as well as high quality, often providing significant speed-up at acceptable quality even for separable filters. The optimized filters can be baked into shaders and used as a drop-in replacement for filtering tasks in image processing or rendering pipelines.

Kernel Null Space Marginal Fisher Analysis for Face Recognition

2014 ◽  
Vol 889-890 ◽  
pp. 1065-1068
Author(s):  
Yu’e Lin ◽  
Xing Zhu Liang ◽  
Hua Ping Zhou
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Sample Size ◽  
High Performance ◽  
Null Space ◽  
Small Sample Size ◽  
Recognition Rate ◽  
Original Data ◽  
Small Sample ◽  
Neighborhood Structure

In the recent years, the feature extraction algorithms based on manifold learning, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure, have drawn much attention. Among them, the Marginal Fisher Analysis (MFA) achieved high performance for face recognition. However, MFA suffers from the small sample size problems and is still a linear technique. This paper develops a new nonlinear feature extraction algorithm, called Kernel Null Space Marginal Fisher Analysis (KNSMFA). KNSMFA based on a new optimization criterion is presented, which means that all the discriminant vectors can be calculated in the null space of the within-class scatter. KNSMFA not only exploits the nonlinear features but also overcomes the small sample size problems. Experimental results on ORL database indicate that the proposed method achieves higher recognition rate than the MFA method and some existing kernel feature extraction algorithms.

The Adaboost Algorithm Applied in ATM Automatic Identification System

2013 ◽  
Vol 753-755 ◽  
pp. 2941-2944
Author(s):  
Ming Hui Zhang ◽  
Yao Yu Zhang
Keyword(s):  
Face Recognition ◽  
Face Detection ◽  
Computing Time ◽  
Automatic Identification ◽  
Identification System ◽  
Human Face ◽  
Detection Experiment ◽  
Adaboost Algorithm ◽  
Face Features ◽  
Human Faces

Seeing that human face features are unique, an increasing number of face recognition algorithms on existing ATM are proposed. Since face detection is a primary link of face recognition, our system adopts AdaBoost algorithm which is based on face detection. Experiment results demonstrated that the computing time of face detection using this algorithm is about 70ms, and the single and multiple human faces can be effectively measured under well environment, which meets the demand of the system.

Algorithmic Analysis of Automatic Attendance System using Facial Recognition

2022 ◽  
Vol 14 (1) ◽  
pp. 0-0
Keyword(s):  
Face Recognition ◽  
Daily Life ◽  
Real Life ◽  
Student Attendance ◽  
Surveillance Camera ◽  
Daily Life Activities ◽  
The Face ◽  
Algorithmic Analysis ◽  
Human Faces ◽  
Face Biometrics

Attendance management can become a tedious task for teachers if it is performed manually.. This problem can be solved with the help of an automatic attendance management system. But validation is one of the main issues in the system. Generally, biometrics are used in the smart automatic attendance system. Managing attendance with the help of face recognition is one of the biometric methods with better efficiency as compared to others. Smart Attendance with the help of instant face recognition is a real-life solution that helps in handling daily life activities and maintaining a student attendance system. Face recognition-based attendance system uses face biometrics which is based on high resolution monitor video and other technologies to recognize the face of the student. In project, the system will be able to find and recognize human faces fast and accurately with the help of images or videos that will be captured through a surveillance camera. It will convert the frames of the video into images so that our system can easily search that image in the attendance database.

scholarly journals Face Recognition Using Neural Networks

2011 ◽  
pp. 76-79
Author(s):  
V. Ramya ◽  
G. Sivashankari
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Recognition Performance ◽  
Back Propagation ◽  
Rbf Networks ◽  
End Point ◽  
Novel Approach ◽  
Wide Variability ◽  
Human Faces ◽  
Face Localization

Face recognition from the images is challenging due to the wide variability of face appearances and the complexity of the image background. This paper proposes a novel approach for recognizing the human faces. The recognition is done by comparing the characteristics of the new face to that of known individuals. It has Face localization part, where mouth end point and eyeballs will be obtained. In feature Extraction, Distance between eyeballs and mouth end point will be calculated. The recognition is performed by Neural Network (NN) using Back Propagation Networks (BPN) and Radial Basis Function (RBF) networks. The recognition performance of the proposed method is tabulated based on the experiments performed on a number of images.

Face Recognition with Active Appearance Model (AAM)

2013 ◽  
pp. 1124-1144 ◽  
Author(s):  
Patrycia Barros de Lima Klavdianos ◽  
Lourdes Mattos Brasil ◽  
Jairo Simão Santana Melo
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Face Recognition ◽  
Face Processing ◽  
Research Field ◽  
Appearance Model ◽  
Active Appearance Model ◽  
Human Face ◽  
Active Appearance ◽  
Human Faces

Recognition of human faces has been a fascinating subject in research field for many years. It is considered a multidisciplinary field because it includes understanding different domains such as psychology, neuroscience, computer vision, artificial intelligence, mathematics, and many others. Human face perception is intriguing and draws our attention because we accomplish the task so well that we hope to one day witness a machine performing the same task in a similar or better way. This chapter aims to provide a systematic and practical approach regarding to one of the most current techniques applied on face recognition, known as AAM (Active Appearance Model). AAM method is addressed considering 2D face processing only. This chapter doesn’t cover the entire theme, but offers to the reader the necessary tools to construct a consistent and productive pathway toward this involving subject.

Biometrical Processing of Faces in Security and Forensics

2010 ◽  
pp. 79-103
Author(s):  
Pawel T. Puslecki
Keyword(s):  
Face Recognition ◽  
Face Detection ◽  
Face Processing ◽  
Facial Features ◽  
Comprehensive Description ◽  
Facial Processing ◽  
Human Faces

The aim of this chapter is the overall and comprehensive description of the machine face processing issue and presentation of its usefulness in security and forensic applications. The chapter overviews the methods of face processing as the field deriving from various disciplines. After a brief introduction to the field, the conclusions concerning human processing of faces that have been drawn by the psychology researchers and neuroscientists are described. Then the most important tasks related to the computer facial processing are shown: face detection, face recognition and processing of facial features, and the main strategies as well as the methods applied in the related fields are presented. Finally, the applications of digital biometrical processing of human faces are presented.

Heterogeneous Electrode Designs for Planar SOFC Optimizations

2011 ◽  
Author(s):  
Junxiang Shi ◽  
Xingjian Xue
Keyword(s):  
Solid Oxide Fuel Cells ◽  
High Performance ◽  
Performance Enhancement ◽  
High Current Density ◽  
Porous Electrode ◽  
Model Development ◽  
Optimization Method ◽  
Operating Conditions ◽  
Algorithm Optimization ◽  
Pressure Losses

Suitable porous electrode design may play a significant role in the performance enhancement of solid oxide fuel cells (SOFCs). In this paper, a genetic algorithm optimization method is employed to design electrodes based on a 2-D planar SOFC model development. The objective is to find out suitable porosity and particle size distributions for both anode and cathode electrodes so that the cell performance can be maximized. The results indicate that the optimized heterogeneous electrode may better improve SOFC performance than the homogeneous count-part, particularly under relatively high current density conditions. The optimization results are dependent on the operating conditions. The effects of pressure losses along the anode/cathode channels and inlet fuel compositions are investigated. The proposed approach provides a systematical method for electrode microstructure designs of high performance SOFCs.

Sign in / Sign up

Export Citation Format

Share Document