Study of Gabor Wavelet for Face Recognition Invariant to Pose and Orientation

Karthika, R.; Parameswaran, Latha

doi:10.1007/978-81-322-2671-0_48

Cited by 23 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is beneficial to improve the performance of the SSPP face recognition problem. Therefore, many methods based on local features have been proposed in recent years, such as Local Binary Pattern (LBP) [35], Gabor transform [36], Histogram of Oriented Gradient (HOG) [37], etc.…”

Section: Feature Extraction Methodsmentioning

confidence: 99%

Face Recognition in Single Sample Per Person Fusing Multi-Scale Features Extraction and Virtual Sample Generation Methods

Yuan

Zhang

et al. 2022

Front. Appl. Math. Stat.

View full text Add to dashboard Cite

Although face recognition has received a lot of attention and development in recent years, it is one of the research hotspots due to the low efficiency of Single Sample Per Person (SSPP) information in face recognition. In order to solve this problem, this article proposes a face recognition method based on virtual sample generation and multi-scale feature extraction. First, in order to increase the training sample information, a new NMF-MSB virtual sample generation method is proposed by combining the Non-negative Matrix Factorization (NMF) reconstruction strategy with Mirror transform(M), Sliding window(S), and Bit plane(B) sample extension methods. Second, a feature extraction method (named WPD-HOG-P) based on Wavelet Packet Decomposition, Histograms of Oriented Gradients, and image Pyramid is proposed. The proposed WPD-HOG-P method is beneficial to multi-scale facial image feature extraction. Finally, based on the extracted WPD-HOG-P features, the recognition model is established by using a grid search optimization support vector machine. Experimental results on ORL and FERET data sets show that the proposed method has higher recognition rates and lower computational complexity than the benchmark methods.

show abstract

Section: Feature Extraction Methodsmentioning

confidence: 99%

Face Recognition in Single Sample Per Person Fusing Multi-Scale Features Extraction and Virtual Sample Generation Methods

Yuan

Zhang

et al. 2022

Front. Appl. Math. Stat.

View full text Add to dashboard Cite

show abstract

“…1D Log-Gabor filter: used for the extraction of the features. Features are determined by convolving the normalized iris image with the 1D Log-Gabor filter (6) and is phase quantised to generate a bitwise biometric template. Hamming distance can be used to find the distance between reference image template and the input image template.…”

Section: Feature Extraction and Recognitionmentioning

confidence: 99%

Improving the IRIS Recognition Under Different Illumination Using RETINEX Algorithms

Kumar¹,

Baskar²

2018

IJET

View full text Add to dashboard Cite

Iris detection and recognition provides more accurate and secure authentication nowadays. The probability of any two people having the same iris pattern is nearly zero, even the identical twins will not have the same iris pattern. The noise and illumination changes, challenges iris recognition correctness and security in authentication process. The available recent pre-processing techniques for iris detection address different type of noise suppression and removing unwanted information in iris, but still it strives with illumination issues. In this paper, we proposed Retinex algorithm for improving iris detection rate. The proposed work comprises into three steps: First we proposed Retinex algorithm in pre-processing, it works based on reflectance value of image and skips the illumination value in image, subsequently feature extraction uses Gabor filter for iris code generation. In conclusion, distance metrics Hamming distance used for iris recognition the proposed work evaluated MMU iris database under different illumination conditions and provides better results.

show abstract

“…Log‐Gabor transform is applied to extract the facial features. Generally, on the linear frequency scale, the structure of transfer function of the log‐Gabor transform is presented as [38]

G ()(, ω) = \exp (}{, \frac{- \log {()(, false(ω / ω_{0} false))}^{2}}{2 \times \log {()(, false(k / ω_{0} false))}^{2}})

where

ω_{0}

is the filter centre frequency,

ω

is the normalised radius from centre and k is the standard deviation of angular component. The constant shape filter is obtained by considering the ratio

{((k / ω_{0}))}^{2}

to be constant for varying values of

ω_{0}

.…”

Section: Unimodal Biometric Systemsmentioning

confidence: 99%

Optimum scheme selection for face–iris biometric

Eskandari

Sharifi

2017

IET biom.

View full text Add to dashboard Cite

Designing a new dynamic and optimal scheme for face-iris fusion based on the score level, feature level and decision level fusion is considered in this study. Prior to implementing the proposed combined level fusion, several schemes are separately implemented at each level of fusion to investigate the performance improvement of each level of fusion on face and iris modalities. In fact, the optimum scheme is constructed by selecting flexible and dynamic features and scores of face and iris biometrics and then combining the advantages of different levels of fusion. Consequently, the scheme produces a set of fast and flexible features and scores for fusion. On the other hand, the idea of threshold-optimised decisions is used in this study to fuse the optimised decisions of face and iris biometrics. Experimental results on verification rates demonstrate a significant improvement of proposed combined level fusion scheme over unimodal and multimodal fusion methods.

show abstract

Study of Gabor Wavelet for Face Recognition Invariant to Pose and Orientation

Cited by 23 publications

References 11 publications

Face Recognition in Single Sample Per Person Fusing Multi-Scale Features Extraction and Virtual Sample Generation Methods

Face Recognition in Single Sample Per Person Fusing Multi-Scale Features Extraction and Virtual Sample Generation Methods

Improving the IRIS Recognition Under Different Illumination Using RETINEX Algorithms

Optimum scheme selection for face–iris biometric

Contact Info

Product

Resources

About