Efficiency of Recognition Methods for Single Sample per Person Based Face Recognition

Oravec, Milos; Pavlovičová, Jarmila; Mazanec, Jan; Omelina, Luboš; Feder, Matej; Ban, Jozef

doi:10.5772/18432

Cited by 8 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We decided to use a method based on LBP features with Chi-square distance as a similarity metric which is described in details in [5,12]. The selected method provides a trade-of between accuracy and computational complexity; thus it can run in real-time while maintaining state-ofthe-art recognition accuracy (13).…”

Section: Recognition Of a Patientmentioning

confidence: 99%

Interaction Detection with Depth Sensing and Body Tracking Cameras in Physical Rehabilitation

Omelina¹,

Jansen²,

Bonnechère³

et al. 2016

Methods Inf Med

View full text Add to dashboard Cite

show abstract

Section: Recognition Of a Patientmentioning

confidence: 99%

Interaction Detection with Depth Sensing and Body Tracking Cameras in Physical Rehabilitation

Omelina¹,

Jansen²,

Bonnechère³

et al. 2016

Methods Inf Med

View full text Add to dashboard Cite

show abstract

“…Two subsets (FERET-1 and FERET-2) are used to evaluate the performance of our method on SSS and SSPP face recognition, respectively. Similar to [ 7 ], FERET-1 contains all available subjects that have more than four frontal images. There are 665 images from 82 subjects in total.…”

Section: System Performance Analysismentioning

confidence: 99%

“…We have compared our method with several conventional face recognition algorithms without ensemble, including: PCA family [ 7 ], LDA family [ 32 ], LPP family (locality preserving projections) [ 32 ], CCA family (canonical correlation analysis) [ 6 ] and several other representative methods, such as SVM, neural network-based methods (MLP (multilayer perception) and RBF (radial basis function network)) [ 7 ]. For a fair comparison, we reported the performances of these methods presented in their published papers.…”

Section: System Performance Analysismentioning

confidence: 99%

“…We have compared our method with three kinds of representative methods: (1) global feature selection based on a random subspace [ 5 ]; (2) patch (block)-based local feature extraction, such as PCRC [ 9 ], and a patch-based method using LBP (local binary pattern) [ 7 ], which partition face images into small patches of the same size; and (3) global and local feature integration-based methods, such as the 30 region method [ 8 ], which defines 30 regions with large overlaps according to experimental experience, and the multi-scale patch-based method, MPCRC [ 9 ], which integrates the collaboration of patches of multi-scales to generate global feature representation. We reported the performance of LBP-based methods in [ 7 ]. We implemented the 30 region method and used the source code of PCRC and MPCRC in [ 9 ].…”

Section: System Performance Analysismentioning

confidence: 99%

See 1 more Smart Citation

Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks

Zhang

Liang

Matsuyama

2014

Sensors

View full text Add to dashboard Cite

Multi-camera networks have gained great interest in video-based surveillance systems for security monitoring, access control, etc. Person re-identification is an essential and challenging task in multi-camera networks, which aims to determine if a given individual has already appeared over the camera network. Individual recognition often uses faces as a trial and requires a large number of samples during the training phrase. This is difficult to fulfill due to the limitation of the camera hardware system and the unconstrained image capturing conditions. Conventional face recognition algorithms often encounter the “small sample size” (SSS) problem arising from the small number of training samples compared to the high dimensionality of the sample space. To overcome this problem, interest in the combination of multiple base classifiers has sparked research efforts in ensemble methods. However, existing ensemble methods still open two questions: (1) how to define diverse base classifiers from the small data; (2) how to avoid the diversity/accuracy dilemma occurring during ensemble. To address these problems, this paper proposes a novel generic learning-based ensemble framework, which augments the small data by generating new samples based on a generic distribution and introduces a tailored 0–1 knapsack algorithm to alleviate the diversity/accuracy dilemma. More diverse base classifiers can be generated from the expanded face space, and more appropriate base classifiers are selected for ensemble. Extensive experimental results on four benchmarks demonstrate the higher ability of our system to cope with the SSS problem compared to the state-of-the-art system.

show abstract

“…Facial recognition is a very common application of machine vision. There are many approaches to facial recognition, including both holistic and local comparisons [17].…”

Section: …………………………………………………………………………………………………… Introduction:-mentioning

confidence: 99%

A Survey on Face Recognition System and Its Techniques.

Raveendra¹,

Ravi²

2016

IJAR

View full text Add to dashboard Cite

show abstract

Efficiency of Recognition Methods for Single Sample per Person Based Face Recognition

Cited by 8 publications

References 39 publications

Interaction Detection with Depth Sensing and Body Tracking Cameras in Physical Rehabilitation

Interaction Detection with Depth Sensing and Body Tracking Cameras in Physical Rehabilitation

Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks

A Survey on Face Recognition System and Its Techniques.

Contact Info

Product

Resources

About