Incremental methods in face recognition: a survey
- PDF / 1,858,188 Bytes
- 51 Pages / 439.37 x 666.142 pts Page_size
- 58 Downloads / 253 Views
Incremental methods in face recognition: a survey Suresh Madhavan1 · Nitin Kumar1
© Springer Nature B.V. 2019
Abstract Face Recognition has rapidly grown as a commercial requirement for a variety of applications in recent years. There are certain situations in which all the face images may not be available before training or the face images may be distributed at geographically apart locations. Incremental face recognition addresses these problems and possesses certain advantages i.e. being time efficient and dynamic model updation allows addition/deletion of samples on the fly. In this paper, a comprehensive review on the Incremental learning algorithms that are aimed at Face Recognition or tested over Face datasets. The contribution of this paper is three-fold: (a) a novel taxonomy of the Incremental methods have been proposed (b) a review of the face datasets used in Incremental face recognition have been carried out and (c) a performance analysis of the Incremental face recognition methods over various face datasets is also presented. Important conclusions have been drawn that will help the researchers in making suitable choices amongst various methods and datasets. This survey shall act as a useful reference to the researchers and practitioners working in incremental face recognition. Furthermore, several viable research directions have been given at the end. Keywords Supervised · Unsupervised · Semi-supervised · Learning · Hybrid · Taxonomy · Datasets · Performance
1 Introduction Human identity has always been their faces since inception. Intuitively, Machine-based recognition algorithms have often been focused on human face recognition which is popularly known as Face Recognition and is an active area of research due to its criticality in government, commercial and forensic applications (Prabhakar et al. 2003). Some of its critical applications in both public and private sectors include areas such as Law Enforcement, Counter-terrorism, Immigration, Residential Security, Banking, etc., as summarised in Table 1. Due to its criticality as well as the number of commercial implementations, face recognition is among the most happening areas that attract researchers around the world from various disciplines such as Pattern Recognition, Machine Learning, Data Analytics, Computer Vision, Image Processing, to name a few. Over 40 years of research on face recognition
B 1
Nitin Kumar [email protected] Department of Computer Science and Engineering, National Institute of Technology, Uttarakhand, India
123
S. Madhavan, N. Kumar Table 1 Face recognition applications Sector Public sector
Private sector
Specific area
Sample application
Law enforcement
Criminal records identification
Counter-terrorism
Identification of known fugitives at public places
Immigration
Customs process progression
Voter verification
A voting process to overcome malpractices
Residential security
Alerting home owners of trespassers
Banking
Customer face verification over ATM pins
Home appliances
Physical access control at smart
Data Loading...
