An experimental evaluation of linear and kernel-based methods for face recognition

Author(s):  
H. Gupta ◽  
A.K. Agrawal ◽  
T. Pruthi ◽  
C. Shekhar ◽  
R. Chellappa
2003 ◽  
Vol 03 (01) ◽  
pp. 81-94 ◽  
Author(s):  
LONGBIN CHEN ◽  
BAOGANG HU ◽  
LEI ZHANG ◽  
MINGJING LI ◽  
HONGJIANG ZHANG

In this paper, we propose a framework to semi-automatically annotate faces in family photo albums. The core of the framework is the features used to define face similarity and this results in the learning algorithm used to refine automatic face annotation. We have adopted similarity based search and relevance feedback ideas developed for content-based image retrieval and a set of simple yet effective color and texture based features, in addition to the traditional face recognition features, in performing candidate annotation search. The experimental evaluation of the proposed approach has been conducted with a family album of 1707 photos and the results show that the proposed approach is an effective and efficient one for semi-automatic family photo album annotation.


2016 ◽  
Vol 9 (2) ◽  
pp. 53-65 ◽  
Author(s):  
T.P. Budyakova

The paper experimentally investigate questions of psychology of human face recognition. The investigative and operational and investigative practice, there are difficulties in assessing the reliability of the identification of a witness or victim of a criminal offense. The method used to identify the presentation does not correspond to the psychological laws of human perception. The experiment proved that the verbal portrait of the system as part of the identification procedure does not improve, but on the contrary, worsens the accuracy of recognition. It was found that the recommendation not to carry out an identification, if recognized by the man known personally identified, and psychologically not always justified in the case of similar faces.


Author(s):  
Imran Naseem ◽  
Imran Naseem ◽  
Roberto Togneri ◽  
Roberto Togneri ◽  
Mohammed Bennamoun

In this chapter, the authors discuss the problem of face recognition using sparse representation classification (SRC). The SRC classifier has recently emerged as one of the latest paradigm in the context of view-based face recognition. The main aim of the chapter is to provide an insight of the SRC algorithm with thorough discussion of the underlying “Compressive Sensing” theory. Comprehensive experimental evaluation of the approach is conducted on a number of standard databases using exemplary evaluation protocols to provide a comparative index with the benchmark face recognition algorithms. The algorithm is also extended to the problem of video-based face recognition for more realistic applications.


2012 ◽  
Vol 7 (3) ◽  
pp. 932-943 ◽  
Author(s):  
Sri-Kaushik Pavani ◽  
Federico M. Sukno ◽  
David Delgado-Gomez ◽  
Constantine Butakoff ◽  
Xavier Planes ◽  
...  

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Yoanna Martinez-Diaz ◽  
Heydi Mendez-Vazquez ◽  
Luis S. Luevano ◽  
Miguel Nicolas-Diaz ◽  
Leonardo Chang ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document